%0 Journal Article %@ 1438-8871 %I JMIR Publications %V 27 %N %P e68757 %T How to Refine and Prioritize Key Performance Indicators for Digital Health Interventions: Tutorial on Using Consensus Methodology to Enable Meaningful Evaluation of Novel Digital Health Interventions %A McCabe,Catherine %A Connolly,Leona %A Quintana,Yuri %A Weir,Arielle %A Moen,Anne %A Ingvar,Martin %A McCann,Margaret %A Doyle,Carmel %A Hughes,Mary %A Brenner,Maria %+ School of Nursing and Midwifery, Trinity College Dublin, 24 D`Olier At, Dublin 2, Dublin, D02 T283, Ireland, 353 1 8933019, camccabe@tcd.ie %K digital health interventions %K key performance indicators %K Delphi technique %K consensus methodology %K drug-related side effects and adverse reactions %K referral %K consultation %D 2025 %7 16.4.2025 %9 Tutorial %J J Med Internet Res %G English %X Digital health interventions (DHIs) have the potential to improve health care and health promotion. However, there is a lack of guidance in the literature for the development, refinement, and prioritization of key performance indicators (KPIs) for the evaluation of DHIs. This paper presents a 4-stage process used in the Gravitate Health project based on stakeholder consultation and consensus for this purpose. The Gravitate Health consortium, which comprises private and public partners from across Europe and the United States, is developing innovative digital health solutions in the form of Federated Open-Source Platform and G-lens to present users with individualized digital information about their medicines. The first stage of this was the consultative process for the development of KPIs involving stakeholder (Gravitate Health project leads) consultations at the planning stages of the project. This resulted in the formation of an extensive list of KPIs organized into 7 categories. The second stage was conducting a scoping review, which confirmed the need for extensive stakeholder consultation in all stages of the KPI development, refinement, and prioritization process. The third stage was a period of further consultation with all consortium members, which resulted in the elimination of 1 category of KPIs. The fourth stage involved using the Delphi technique for refining and prioritizing the remaining 6 categories of KPIs. It is unusual to use this methodology in a nonresearch exercise, but it provided a clear consultative framework and structure that facilitated the achievement of consensus within a large consortium of 250 members on a substantial list of KPIs for the project. Consortium members ranked the relevance and importance of each KPI. The final list of KPIs provides substantial indicators sensitive to the needs of a broad group of stakeholders that are being used to capture real-world data in developing and evaluating DHIs. %M 40239207 %R 10.2196/68757 %U https://www.jmir.org/2025/1/e68757 %U https://doi.org/10.2196/68757 %U http://www.ncbi.nlm.nih.gov/pubmed/40239207 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 27 %N %P e70481 %T How to Design, Create, and Evaluate an Instruction-Tuning Dataset for Large Language Model Training in Health Care: Tutorial From a Clinical Perspective %A Nazar,Wojciech %A Nazar,Grzegorz %A Kamińska,Aleksandra %A Danilowicz-Szymanowicz,Ludmila %+ Department of Allergology, Faculty of Medicine, Gdańsk Medical University, Smoluchowskiego 17, Gdansk, 80-214, Poland, 48 585844300, wojciech.nazar@gumed.edu.pl %K generative artificial intelligence %K large language models %K instruction-tuning datasets %K tutorials %K evaluation framework %K health care %D 2025 %7 18.3.2025 %9 Tutorial %J J Med Internet Res %G English %X High-quality data are critical in health care, forming the cornerstone for accurate diagnoses, effective treatment plans, and reliable conclusions. Similarly, high-quality datasets underpin the development and performance of large language models (LLMs). Among these, instruction-tuning datasets (ITDs) used for instruction fine-tuning have been pivotal in enhancing LLM performance and generalization capabilities across diverse tasks. This tutorial provides a comprehensive guide to designing, creating, and evaluating ITDs for health care applications. Written from a clinical perspective, it aims to make the concepts accessible to a broad audience, especially medical practitioners. Key topics include identifying useful data sources, defining the characteristics of well-designed datasets, and crafting high-quality instruction-input-output examples. We explore practical approaches to dataset construction, examining the advantages and limitations of 3 primary methods: fully manual preparation by expert annotators, fully synthetic generation using artificial intelligence (AI), and an innovative hybrid approach in which experts draft the initial dataset and AI generates additional data. Moreover, we discuss strategies for metadata selection and human evaluation to ensure the quality and effectiveness of ITDs. By integrating these elements, this tutorial provides a structured framework for establishing ITDs. It bridges technical and clinical domains, supporting the continued interdisciplinary advancement of AI in medicine. Additionally, we address the limitations of current practices and propose future directions, emphasizing the need for a global, unified framework for ITDs. We also argue that artificial general intelligence (AGI), if realized, will not replace empirical research in medicine. AGI will depend on human-curated datasets to process and apply medical knowledge. At the same time, ITDs will likely remain the most effective method of supplying this knowledge to AGI, positioning them as a critical tool in AI-driven health care. %M 40100270 %R 10.2196/70481 %U https://www.jmir.org/2025/1/e70481 %U https://doi.org/10.2196/70481 %U http://www.ncbi.nlm.nih.gov/pubmed/40100270 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e56790 %T Reporting Guidelines for the Early-Phase Clinical Evaluation of Applications Using Extended Reality: RATE-XR Qualitative Study Guideline %A Vlake,Johan H %A Drop,Denzel L Q %A Van Bommel,Jasper %A Riva,Giuseppe %A Wiederhold,Brenda K %A Cipresso,Pietro %A Rizzo,Albert S %A Rothbaum,Barbara O %A Botella,Cristina %A Hooft,Lotty %A Bienvenu,Oscar J %A Jung,Christian %A Geerts,Bart %A Wils,Evert-Jan %A Gommers,Diederik %A van Genderen,Michel E %A , %+ Department of Intensive Care, Erasmus Medical Center, Doctor Molewaterplein, Rotterdam, 3015 GD, Netherlands, 31 107040704, m.vangenderen@erasmusmc.nl %K extended reality %K XR %K virtual reality %K augmented reality %K mixed reality %K reporting guideline %K Delphi process %K consensus %K computer-generated simulation %K simulation %K virtual world %K simulation experience %K clinical evaluation %D 2024 %7 29.11.2024 %9 Tutorial %J J Med Internet Res %G English %X Background: Extended reality (XR), encompassing technologies such as virtual reality, augmented reality, and mixed reality, has rapidly gained prominence in health care. However, existing XR research often lacks rigor, proper controls, and standardization. Objective: To address this and to enhance the transparency and quality of reporting in early-phase clinical evaluations of XR applications, we present the “Reporting for the early-phase clinical evaluation of applications using extended reality” (RATE-XR) guideline. Methods: We conducted a 2-round modified Delphi process involving experts from diverse stakeholder categories, and the RATE-XR is therefore the result of a consensus-based, multistakeholder effort. Results: The guideline comprises 17 XR-specific (composed of 18 subitems) and 14 generic reporting items, each with a complementary Explanation & Elaboration section. Conclusions: The items encompass critical aspects of XR research, from clinical utility and safety to human factors and ethics. By offering a comprehensive checklist for reporting, the RATE-XR guideline facilitates robust assessment and replication of early-stage clinical XR studies. It underscores the need for transparency, patient-centeredness, and balanced evaluation of the applications of XR in health care. By providing an actionable checklist of minimal reporting items, this guideline will facilitate the responsible development and integration of XR technologies into health care and related fields. %R 10.2196/56790 %U https://www.jmir.org/2024/1/e56790 %U https://doi.org/10.2196/56790 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e62761 %T Exploring Participants’ Experiences of Digital Health Interventions With Qualitative Methods: Guidance for Researchers %A Harrison Ginsberg,Kristin %A Babbott,Katie %A Serlachius,Anna %+ Department of Psychological Medicine, University of Auckland, 22-30 Park Avenue, Grafton, Auckland, 1023, New Zealand, 64 9 923 3073, a.serlachius@auckland.ac.nz %K qualitative methods %K content analysis %K thematic analysis %K digital health evaluation %K user engagement %K user experience %K digital health intervention %K innovation %K patient experience %K health care %K researcher %K technology %K mobile health %K mHealth %K telemedicine %K digital health %K behavior change %K usability %K tutorial %K research methods %K qualitative research %K study design %D 2024 %7 28.11.2024 %9 Viewpoint %J J Med Internet Res %G English %X Digital health interventions have gained prominence in recent years, offering innovative solutions to improve health care delivery and patient outcomes. Researchers are increasingly using qualitative approaches to explore patient experiences of using digital health interventions. Yet, the qualitative methods used in these studies can vary widely, and some methods are frequently misapplied. We highlight the methods we find most fit for purpose to explore user experiences of digital tools and propose 5 questions for researchers to use to help them select a qualitative method that best suits their research aims. %M 39607999 %R 10.2196/62761 %U https://www.jmir.org/2024/1/e62761 %U https://doi.org/10.2196/62761 %U http://www.ncbi.nlm.nih.gov/pubmed/39607999 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e58419 %T Adapting a Telehealth Physical Activity and Diet Intervention to a Co-Designed Website for Self-Management After Stroke: Tutorial %A Pogrebnoy,Dina %A Ashton,Lee %A Beh,Brian A %A Burke,Meredith %A Cullen,Richard %A Czerenkowski,Jude %A Davey,Julie %A Dennett,Amy M %A English,Kevin %A Godecke,Erin %A Harper,Nicole %A Lynch,Elizabeth %A MacDonald-Wicks,Lesley %A Patterson,Amanda %A Ramage,Emily %A Schelfhaut,Ben %A Simpson,Dawn B %A Zacharia,Karly %A English,Coralie %+ Department of Physiotherapy, Western Health, 176 Furlong Rd, St Albans, 3021, Australia, 61 0403432415, dina.pogrebnoy@uon.edu.au %K stroke %K secondary prevention %K co-design %K how-to guide, website development %K accessibility %K navigation %K self-management %D 2024 %7 22.10.2024 %9 Tutorial %J J Med Internet Res %G English %X People who experience a stroke are at a higher risk of recurrent stroke when compared with people who have not had a stroke. Addressing modifiable risk factors like physical inactivity and poor diet has been shown to improve blood pressure, a leading contributor to stroke. However, survivors of stroke often experience challenges with accessing risk reduction services including long wait lists, difficulty with transportation, fatigue, impaired function, and diminished exercise capacity. Providing health interventions via a website can extend the reach when compared with programs that are only offered face to face or via real-time telehealth. Given global challenges of accessing secondary prevention programs, it is important to consider alternative ways that this information can be made available to survivors of stroke worldwide. Using the “design thinking” framework and drawing on principles of the integrated knowledge translation approach, we adapted 2 co-designed telehealth programs called i-REBOUND – Let’s get moving (physical activity intervention) and i-REBOUND – Eat for health (diet Intervention) to create the i-REBOUND after stroke website. The aim of this paper is to describe the systematic process undertaken to adapt resources from the telehealth delivered i-REBOUND – Let’s get moving and i-REBOUND – Eat for health programs to a website prototype with a focus on navigation requirements and accessibility for survivors of stroke. We engaged a variety of key stakeholders with diverse skills and expertise in areas of stroke recovery, research, and digital health. We established a governance structure, formed a consumer advisory group, appointed a diverse project team, and agreed on scope of the project. Our process of adaptation had the following 3 phases: (1) understand, (2) explore, (3) materialize. Our approach considered the survivor of stroke at the center of all decisions, which helped establish guiding principles related to our prototype design. Careful and iterative engagement with survivors of stroke together with the application of design thinking principles allowed us to establish the functional requirements for our website prototype. Through user testing, we were able to confirm the technical requirements needed to build an accessible and easy-to-navigate website catering to the unique needs of survivors of stroke. We describe the process of adapting existing content and co-creating new digital content in partnership with, and featuring, people who have lived experience of stroke. In this paper, we provide a road map for the steps taken to adapt resources from 2 telehealth-delivered programs to a website format that meets specific navigation and accessibility needs of survivors of stroke. %M 39437389 %R 10.2196/58419 %U https://www.jmir.org/2024/1/e58419 %U https://doi.org/10.2196/58419 %U http://www.ncbi.nlm.nih.gov/pubmed/39437389 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e58502 %T Transforming Digital Phenotyping Raw Data Into Actionable Biomarkers, Quality Metrics, and Data Visualizations Using Cortex Software Package: Tutorial %A Burns,James %A Chen,Kelly %A Flathers,Matthew %A Currey,Danielle %A Macrynikola,Natalia %A Vaidyam,Aditya %A Langholm,Carsten %A Barnett,Ian %A Byun,Andrew (Jin Soo) %A Lane,Erlend %A Torous,John %+ Division of Digital Psychiatry, Beth Israel Deaconess Medical Center, Harvard Medical School, 330 Brookline Ave, Boston, MA, 02215, United States, 1 6176676700, jtorous@bidmc.harvard.edu %K digital phenotyping %K mental health %K data visualization %K data analysis %K smartphones %K smartphone %K Cortex %K open-source %K data processing %K mindLAMP %K app %K apps %K data set %K clinical %K real world %K methodology %K mobile phone %D 2024 %7 23.8.2024 %9 Tutorial %J J Med Internet Res %G English %X As digital phenotyping, the capture of active and passive data from consumer devices such as smartphones, becomes more common, the need to properly process the data and derive replicable features from it has become paramount. Cortex is an open-source data processing pipeline for digital phenotyping data, optimized for use with the mindLAMP apps, which is used by nearly 100 research teams across the world. Cortex is designed to help teams (1) assess digital phenotyping data quality in real time, (2) derive replicable clinical features from the data, and (3) enable easy-to-share data visualizations. Cortex offers many options to work with digital phenotyping data, although some common approaches are likely of value to all teams using it. This paper highlights the reasoning, code, and example steps necessary to fully work with digital phenotyping data in a streamlined manner. Covering how to work with the data, assess its quality, derive features, and visualize findings, this paper is designed to offer the reader the knowledge and skills to apply toward analyzing any digital phenotyping data set. More specifically, the paper will teach the reader the ins and outs of the Cortex Python package. This includes background information on its interaction with the mindLAMP platform, some basic commands to learn what data can be pulled and how, and more advanced use of the package mixed with basic Python with the goal of creating a correlation matrix. After the tutorial, different use cases of Cortex are discussed, along with limitations. Toward highlighting clinical applications, this paper also provides 3 easy ways to implement examples of Cortex use in real-world settings. By understanding how to work with digital phenotyping data and providing ready-to-deploy code with Cortex, the paper aims to show how the new field of digital phenotyping can be both accessible to all and rigorous in methodology. %M 39178032 %R 10.2196/58502 %U https://www.jmir.org/2024/1/e58502 %U https://doi.org/10.2196/58502 %U http://www.ncbi.nlm.nih.gov/pubmed/39178032 %0 Journal Article %@ 2561-326X %I JMIR Publications %V 8 %N %P e54407 %T A Simple and Systematic Approach to Qualitative Data Extraction From Social Media for Novice Health Care Researchers: Tutorial %A Pretorius,Kelly %+ School of Health Sciences, St. Edward's University, 3001 South Congress Avenue, Austin, TX, 78704, United States, 1 (512) 448 8500, kpretori@stedwards.edu %K social media analysis %K data extraction %K health care research %K extraction tutorial %K Facebook extraction %K Facebook analysis %K safe sleep %K sudden unexpected infant death %K social media %K analysis %K systematic approach %K qualitative data %K data extraction %K Facebook %K health-related %K maternal perspective %K maternal perspectives %K sudden infant death syndrome %K mother %K mothers %K women %K United States %K SIDS %K SUID %K post %K posts %D 2024 %7 9.7.2024 %9 Tutorial %J JMIR Form Res %G English %X Social media analyses have become increasingly popular among health care researchers. Social media continues to grow its user base and, when analyzed, offers unique insight into health problems. The process of obtaining data for social media analyses varies greatly and involves ethical considerations. Data extraction is often facilitated by software tools, some of which are open source, while others are costly and therefore not accessible to all researchers. The use of software for data extraction is accompanied by additional challenges related to the uniqueness of social media data. Thus, this paper serves as a tutorial for a simple method of extracting social media data that is accessible to novice health care researchers and public health professionals who are interested in pursuing social media research. The discussed methods were used to extract data from Facebook for a study of maternal perspectives on sudden unexpected infant death. %M 38980712 %R 10.2196/54407 %U https://formative.jmir.org/2024/1/e54407 %U https://doi.org/10.2196/54407 %U http://www.ncbi.nlm.nih.gov/pubmed/38980712 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e50182 %T Developing a Chatbot to Support Individuals With Neurodevelopmental Disorders: Tutorial %A Singla,Ashwani %A Khanna,Ritvik %A Kaur,Manpreet %A Kelm,Karen %A Zaiane,Osmar %A Rosenfelt,Cory Scott %A Bui,Truong An %A Rezaei,Navid %A Nicholas,David %A Reformat,Marek Z %A Majnemer,Annette %A Ogourtsova,Tatiana %A Bolduc,Francois %+ Department of Pediatrics, University of Alberta, 11315 87th Avenue, Edmonton, AB, T6G 2E1, Canada, 1 780 492 9713, fbolduc@ualberta.ca %K chatbot %K user interface %K knowledge graph %K neurodevelopmental disability %K autism %K intellectual disability %K attention-deficit/hyperactivity disorder %D 2024 %7 18.6.2024 %9 Tutorial %J J Med Internet Res %G English %X Families of individuals with neurodevelopmental disabilities or differences (NDDs) often struggle to find reliable health information on the web. NDDs encompass various conditions affecting up to 14% of children in high-income countries, and most individuals present with complex phenotypes and related conditions. It is challenging for their families to develop literacy solely by searching information on the internet. While in-person coaching can enhance care, it is only available to a minority of those with NDDs. Chatbots, or computer programs that simulate conversation, have emerged in the commercial sector as useful tools for answering questions, but their use in health care remains limited. To address this challenge, the researchers developed a chatbot named CAMI (Coaching Assistant for Medical/Health Information) that can provide information about trusted resources covering core knowledge and services relevant to families of individuals with NDDs. The chatbot was developed, in collaboration with individuals with lived experience, to provide information about trusted resources covering core knowledge and services that may be of interest. The developers used the Django framework (Django Software Foundation) for the development and used a knowledge graph to depict the key entities in NDDs and their relationships to allow the chatbot to suggest web resources that may be related to the user queries. To identify NDD domain–specific entities from user input, a combination of standard sources (the Unified Medical Language System) and other entities were used which were identified by health professionals as well as collaborators. Although most entities were identified in the text, some were not captured in the system and therefore went undetected. Nonetheless, the chatbot was able to provide resources addressing most user queries related to NDDs. The researchers found that enriching the vocabulary with synonyms and lay language terms for specific subdomains enhanced entity detection. By using a data set of numerous individuals with NDDs, the researchers developed a knowledge graph that established meaningful connections between entities, allowing the chatbot to present related symptoms, diagnoses, and resources. To the researchers’ knowledge, CAMI is the first chatbot to provide resources related to NDDs. Our work highlighted the importance of engaging end users to supplement standard generic ontologies to named entities for language recognition. It also demonstrates that complex medical and health-related information can be integrated using knowledge graphs and leveraging existing large datasets. This has multiple implications: generalizability to other health domains as well as reducing the need for experts and optimizing their input while keeping health care professionals in the loop. The researchers' work also shows how health and computer science domains need to collaborate to achieve the granularity needed to make chatbots truly useful and impactful. %M 38888947 %R 10.2196/50182 %U https://www.jmir.org/2024/1/e50182 %U https://doi.org/10.2196/50182 %U http://www.ncbi.nlm.nih.gov/pubmed/38888947 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e44443 %T Mental Wellness Self-Care in Singapore With mindline.sg: A Tutorial on the Development of a Digital Mental Health Platform for Behavior Change %A Weng,Janice Huiqin %A Hu,Yanyan %A Heaukulani,Creighton %A Tan,Clarence %A Chang,Julian Kuiyu %A Phang,Ye Sheng %A Rajendram,Priyanka %A Tan,Weng Mooi %A Loke,Wai Chiong %A Morris,Robert J T %+ MOH Office for Healthcare Transformation, 1 Maritime Square, Harbourfront Centre, Singapore, 099253, Singapore, 65 66793209, creighton.heaukulani@moht.com.sg %K digital mental health %K artificial intelligence %K AI %K AI chatbot %K digital therapeutics %K mental health %K mental wellness %K mobile phone %D 2024 %7 4.6.2024 %9 Tutorial %J J Med Internet Res %G English %X Background: Singapore, like the rest of Asia, faces persistent challenges to mental health promotion, including stigma around unwellness and seeking treatment and a lack of trained mental health personnel. The COVID-19 pandemic, which created a surge in mental health care needs and simultaneously accelerated the adoption of digital health solutions, revealed a new opportunity to quickly scale innovative solutions in the region. Objective: In June 2020, the Singaporean government launched mindline.sg, an anonymous digital mental health resource website that has grown to include >500 curated local mental health resources, a clinically validated self-assessment tool for depression and anxiety, an artificial intelligence (AI) chatbot from Wysa designed to deliver digital therapeutic exercises, and a tailored version of the website for working adults called mindline at work. The goal of the platform is to empower Singapore residents to take charge of their own mental health and to be able to offer basic support to those around them through the ease and convenience of a barrier-free digital solution. Methods: Website use is measured through click-level data analytics captured via Google Analytics and custom application programming interfaces, which in turn drive a customized analytics infrastructure based on the open-source platforms Titanium Database and Metabase. Unique, nonbounced (users that do not immediately navigate away from the site), engaged, and return users are reported. Results: In the 2 years following launch (July 1, 2020, through June 30, 2022), the website received >447,000 visitors (approximately 15% of the target population of 3 million), 62.02% (277,727/447,783) of whom explored the site or engaged with resources (referred to as nonbounced visitors); 10.54% (29,271/277,727) of those nonbounced visitors returned. The most popular features on the platform were the dialogue-based therapeutic exercises delivered by the chatbot and the self-assessment tool, which were used by 25.54% (67,626/264,758) and 11.69% (32,469/277,727) of nonbounced visitors. On mindline at work, the rates of nonbounced visitors who engaged extensively (ie, spent ≥40 seconds exploring resources) and who returned were 51.56% (22,474/43,588) and 13.43% (5,853/43,588) over a year, respectively, compared to 30.9% (42,829/138,626) and 9.97% (13,822/138,626), respectively, on the generic mindline.sg site in the same year. Conclusions: The site has achieved desired reach and has seen a strong growth rate in the number of visitors, which required substantial and sustained digital marketing campaigns and strategic outreach partnerships. The site was careful to preserve anonymity, limiting the detail of analytics. The good levels of overall adoption encourage us to believe that mild to moderate mental health conditions and the social factors that underly them are amenable to digital interventions. While mindline.sg was primarily used in Singapore, we believe that similar solutions with local customization are widely and globally applicable. %M 38833294 %R 10.2196/44443 %U https://www.jmir.org/2024/1/e44443 %U https://doi.org/10.2196/44443 %U http://www.ncbi.nlm.nih.gov/pubmed/38833294 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e50890 %T Machine Learning and Health Science Research: Tutorial %A Cho,Hunyong %A She,Jane %A De Marchi,Daniel %A El-Zaatari,Helal %A Barnes,Edward L %A Kahkoska,Anna R %A Kosorok,Michael R %A Virkud,Arti V %+ Department of Biostatistics, University of North Carolina at Chapel Hill, 3101 McGavran-Greenberg Hall, CB #7420, Chapel Hill, NC, 27599-7420, United States, 1 (919) 966 7250, jane.she@unc.edu %K health science researcher %K machine learning pipeline %K machine learning %K medical machine learning %K precision medicine %K reproducibility %K unsupervised learning %D 2024 %7 30.1.2024 %9 Tutorial %J J Med Internet Res %G English %X Machine learning (ML) has seen impressive growth in health science research due to its capacity for handling complex data to perform a range of tasks, including unsupervised learning, supervised learning, and reinforcement learning. To aid health science researchers in understanding the strengths and limitations of ML and to facilitate its integration into their studies, we present here a guideline for integrating ML into an analysis through a structured framework, covering steps from framing a research question to study design and analysis techniques for specialized data types. %M 38289657 %R 10.2196/50890 %U https://www.jmir.org/2024/1/e50890 %U https://doi.org/10.2196/50890 %U http://www.ncbi.nlm.nih.gov/pubmed/38289657 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e51125 %T Selecting an Ecological Momentary Assessment Platform: Tutorial for Researchers %A Henry,Lauren M %A Hansen,Eleanor %A Chimoff,Justin %A Pokstis,Kimberly %A Kiderman,Miryam %A Naim,Reut %A Kossowsky,Joe %A Byrne,Meghan E %A Lopez-Guzman,Silvia %A Kircanski,Katharina %A Pine,Daniel S %A Brotman,Melissa A %+ Emotion and Development Branch, National Institute of Mental Health, 9000 Rockville Pike, Building 15K, Bethesda, MD, 20892, United States, 1 301 480 3895, lauren.henry@nih.gov %K ecological momentary assessment %K methodology %K psychology and psychiatry %K child and adolescent %K in vivo and real time %D 2024 %7 4.1.2024 %9 Tutorial %J J Med Internet Res %G English %X Background: Although ecological momentary assessment (EMA) has been applied in psychological research for decades, delivery methods have evolved with the proliferation of digital technology. Technological advances have engendered opportunities for enhanced accessibility, convenience, measurement precision, and integration with wearable sensors. Notwithstanding, researchers must navigate novel complexities in EMA research design and implementation. Objective: In this paper, we aimed to provide guidance on platform selection for clinical scientists launching EMA studies. Methods: Our team includes diverse specialties in child and adolescent behavioral and mental health with varying expertise on EMA platforms (eg, users and developers). We (2 research sites) evaluated EMA platforms with the goal of identifying the platform or platforms with the best fit for our research. We created a list of extant EMA platforms; conducted a web-based review; considered institutional security, privacy, and data management requirements; met with developers; and evaluated each of the candidate EMA platforms for 1 week. Results: We selected 2 different EMA platforms, rather than a single platform, for use at our 2 research sites. Our results underscore the importance of platform selection driven by individualized and prioritized laboratory needs; there is no single, ideal platform for EMA researchers. In addition, our project generated 11 considerations for researchers in selecting an EMA platform: (1) location; (2) developer involvement; (3) sample characteristics; (4) onboarding; (5) survey design features; (6) sampling scheme and scheduling; (7) viewing results; (8) dashboards; (9) security, privacy, and data management; (10) pricing and cost structure; and (11) future directions. Furthermore, our project yielded a suggested timeline for the EMA platform selection process. Conclusions: This study will guide scientists initiating studies using EMA, an in vivo, real-time research tool with tremendous promise for facilitating advances in psychological assessment and intervention. %M 38175682 %R 10.2196/51125 %U https://www.jmir.org/2024/1/e51125 %U https://doi.org/10.2196/51125 %U http://www.ncbi.nlm.nih.gov/pubmed/38175682 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 25 %N %P e44206 %T Mobilizing Patient and Public Involvement in the Development of Real-World Digital Technology Solutions: Tutorial %A Keogh,Alison %A Mc Ardle,Ríona %A Diaconu,Mara Gabriela %A Ammour,Nadir %A Arnera,Valdo %A Balzani,Federica %A Brittain,Gavin %A Buckley,Ellen %A Buttery,Sara %A Cantu,Alma %A Corriol-Rohou,Solange %A Delgado-Ortiz,Laura %A Duysens,Jacques %A Forman-Hardy,Tom %A Gur-Arieh,Tova %A Hamerlijnck,Dominique %A Linnell,John %A Leocani,Letizia %A McQuillan,Tom %A Neatrour,Isabel %A Polhemus,Ashley %A Remmele,Werner %A Saraiva,Isabel %A Scott,Kirsty %A Sutton,Norman %A van den Brande,Koen %A Vereijken,Beatrix %A Wohlrab,Martin %A Rochester,Lynn %A , %+ Insight Centre Data Analytics, University College Dublin, Beech Hill, Dublin4, D04 P7W1, Ireland, 353 1 716 7777, Alison.keogh@tcd.ie %K patient involvement %K patient engagement %K public-private partnership %K research consortium %K digital mobility outcomes %K real-world mobility %K digital mobility measures %D 2023 %7 27.10.2023 %9 Tutorial %J J Med Internet Res %G English %X Although the value of patient and public involvement and engagement (PPIE) activities in the development of new interventions and tools is well known, little guidance exists on how to perform these activities in a meaningful way. This is particularly true within large research consortia that target multiple objectives, include multiple patient groups, and work across many countries. Without clear guidance, there is a risk that PPIE may not capture patient opinions and needs correctly, thereby reducing the usefulness and effectiveness of new tools. Mobilise-D is an example of a large research consortium that aims to develop new digital outcome measures for real-world walking in 4 patient cohorts. Mobility is an important indicator of physical health. As such, there is potential clinical value in being able to accurately measure a person’s mobility in their daily life environment to help researchers and clinicians better track changes and patterns in a person’s daily life and activities. To achieve this, there is a need to create new ways of measuring walking. Recent advancements in digital technology help researchers meet this need. However, before any new measure can be used, researchers, health care professionals, and regulators need to know that the digital method is accurate and both accepted by and produces meaningful outcomes for patients and clinicians. Therefore, this paper outlines how PPIE structures were developed in the Mobilise-D consortium, providing details about the steps taken to implement PPIE, the experiences PPIE contributors had within this process, the lessons learned from the experiences, and recommendations for others who may want to do similar work in the future. The work outlined in this paper provided the Mobilise-D consortium with a foundation from which future PPIE tasks can be created and managed with clearly defined collaboration between researchers and patient representatives across Europe. This paper provides guidance on the work required to set up PPIE structures within a large consortium to promote and support the creation of meaningful and efficient PPIE related to the development of digital mobility outcomes. %M 37889531 %R 10.2196/44206 %U https://www.jmir.org/2023/1/e44206 %U https://doi.org/10.2196/44206 %U http://www.ncbi.nlm.nih.gov/pubmed/37889531 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 25 %N %P e49949 %T Democratizing Artificial Intelligence Imaging Analysis With Automated Machine Learning: Tutorial %A Thirunavukarasu,Arun James %A Elangovan,Kabilan %A Gutierrez,Laura %A Li,Yong %A Tan,Iris %A Keane,Pearse A %A Korot,Edward %A Ting,Daniel Shu Wei %+ University of Cambridge School of Clinical Medicine, Addenbrooke's Hospital, Hills Rd, Cambridge, CB2 0SP, United Kingdom, 44 01223 336700, ajt205@cantab.ac.uk %K machine learning %K automated machine learning %K autoML %K artificial intelligence %K democratization %K autonomous AI %K imaging %K image analysis %K automation %K AI engineering %D 2023 %7 12.10.2023 %9 Tutorial %J J Med Internet Res %G English %X Deep learning–based clinical imaging analysis underlies diagnostic artificial intelligence (AI) models, which can match or even exceed the performance of clinical experts, having the potential to revolutionize clinical practice. A wide variety of automated machine learning (autoML) platforms lower the technical barrier to entry to deep learning, extending AI capabilities to clinicians with limited technical expertise, and even autonomous foundation models such as multimodal large language models. Here, we provide a technical overview of autoML with descriptions of how autoML may be applied in education, research, and clinical practice. Each stage of the process of conducting an autoML project is outlined, with an emphasis on ethical and technical best practices. Specifically, data acquisition, data partitioning, model training, model validation, analysis, and model deployment are considered. The strengths and limitations of available code-free, code-minimal, and code-intensive autoML platforms are considered. AutoML has great potential to democratize AI in medicine, improving AI literacy by enabling “hands-on” education. AutoML may serve as a useful adjunct in research by facilitating rapid testing and benchmarking before significant computational resources are committed. AutoML may also be applied in clinical contexts, provided regulatory requirements are met. The abstraction by autoML of arduous aspects of AI engineering promotes prioritization of data set curation, supporting the transition from conventional model-driven approaches to data-centric development. To fulfill its potential, clinicians must be educated on how to apply these technologies ethically, rigorously, and effectively; this tutorial represents a comprehensive summary of relevant considerations. %M 37824185 %R 10.2196/49949 %U https://www.jmir.org/2023/1/e49949 %U https://doi.org/10.2196/49949 %U http://www.ncbi.nlm.nih.gov/pubmed/37824185 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 25 %N %P e50638 %T Prompt Engineering as an Important Emerging Skill for Medical Professionals: Tutorial %A Meskó,Bertalan %+ The Medical Futurist Institute, Povl Bang-Jensen u. 2/B1. 4/1., Budapest, 1118, Hungary, 36 703807260, berci@medicalfuturist.com %K artificial intelligence %K AI %K digital health %K future %K technology %K ChatGPT %K GPT-4 %K large language models %K language model %K LLM %K prompt %K prompts %K prompt engineering %K AI tool %K engineering %K healthcare professional %K decision-making %K LLMs %K chatbot %K chatbots %K conversational agent %K conversational agents %K NLP %K natural language processing %D 2023 %7 4.10.2023 %9 Tutorial %J J Med Internet Res %G English %X Prompt engineering is a relatively new field of research that refers to the practice of designing, refining, and implementing prompts or instructions that guide the output of large language models (LLMs) to help in various tasks. With the emergence of LLMs, the most popular one being ChatGPT that has attracted the attention of over a 100 million users in only 2 months, artificial intelligence (AI), especially generative AI, has become accessible for the masses. This is an unprecedented paradigm shift not only because of the use of AI becoming more widespread but also due to the possible implications of LLMs in health care. As more patients and medical professionals use AI-based tools, LLMs being the most popular representatives of that group, it seems inevitable to address the challenge to improve this skill. This paper summarizes the current state of research about prompt engineering and, at the same time, aims at providing practical recommendations for the wide range of health care professionals to improve their interactions with LLMs. %M 37792434 %R 10.2196/50638 %U https://www.jmir.org/2023/1/e50638 %U https://doi.org/10.2196/50638 %U http://www.ncbi.nlm.nih.gov/pubmed/37792434 %0 Journal Article %@ 2369-3762 %I JMIR Publications %V 9 %N %P e42154 %T Creating Custom Immersive 360-Degree Videos for Use in Clinical and Nonclinical Settings: Tutorial %A Naef,Aileen C %A Jeitziner,Marie-Madlen %A Jakob,Stephan M %A Müri,René M %A Nef,Tobias %+ Gerontechnology and Rehabilitation Group, ARTORG Center for Biomedical Engineering Research, University of Bern, Freiburgstrasse 3, Bern, 3010, Switzerland, 41 031 632 75 79, tobias.nef@unibe.ch %K 360-degree video %K head-mounted display %K healthcare %K relaxing content %K technology %K video content %K video production %K virtual reality %K VR %D 2023 %7 14.9.2023 %9 Tutorial %J JMIR Med Educ %G English %X The use of virtual reality (VR) stimulation in clinical settings has increased in recent years. In particular, there has been increasing interest in the use of VR stimulation for a variety of purposes, including medical training, pain therapy, and relaxation. Unfortunately, there is still a limited amount of real-world 360-degree content that is both available and suitable for these applications. Therefore, this tutorial paper describes a pipeline for the creation of custom VR content. It covers the planning and designing of content; the selection of appropriate equipment; the creation and processing of footage; and the deployment, visualization, and evaluation of the VR experience. This paper aims to provide a set of guidelines, based on first-hand experience, that readers can use to help create their own 360-degree videos. By discussing and elaborating upon the challenges associated with making 360-degree content, this tutorial can help researchers and health care professionals anticipate and avoid common pitfalls during their own content creation process. %M 37707883 %R 10.2196/42154 %U https://mededu.jmir.org/2023/1/e42154 %U https://doi.org/10.2196/42154 %U http://www.ncbi.nlm.nih.gov/pubmed/37707883 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 25 %N %P e42187 %T GATEKEEPER’s Strategy for the Multinational Large-Scale Piloting of an eHealth Platform: Tutorial on How to Identify Relevant Settings and Use Cases %A de Batlle,Jordi %A Benítez,Ivan D %A Moncusí-Moix,Anna %A Androutsos,Odysseas %A Angles Barbastro,Rosana %A Antonini,Alessio %A Arana,Eunate %A Cabrera-Umpierrez,Maria Fernanda %A Cea,Gloria %A Dafoulas,George Ε %A Folkvord,Frans %A Fullaondo,Ane %A Giuliani,Francesco %A Huang,Hsiao-Ling %A Innominato,Pasquale F %A Kardas,Przemyslaw %A Lou,Vivian W Q %A Manios,Yannis %A Matsangidou,Maria %A Mercalli,Franco %A Mokhtari,Mounir %A Pagliara,Silvio %A Schellong,Julia %A Stieler,Lisa %A Votis,Konstantinos %A Currás,Paula %A Arredondo,Maria Teresa %A Posada,Jorge %A Guillén,Sergio %A Pecchia,Leandro %A Barbé,Ferran %A Torres,Gerard %A Fico,Giuseppe %A , %+ Group of Translational Research in Respiratory Medicine, Institut de Recerca Biomedica de Lleida, Hospital Universitari Arnau de Vilanova-Santa Maria, Alcalde Rovira Roure 80, Lleida, 25198, Spain, 34 973702489, jordidebatlle@gmail.com %K big data %K chronic diseases %K eHealth %K healthy aging %K integrated care %K large-scale pilots %D 2023 %7 28.6.2023 %9 Tutorial %J J Med Internet Res %G English %X Background: The World Health Organization’s strategy toward healthy aging fosters person-centered integrated care sustained by eHealth systems. However, there is a need for standardized frameworks or platforms accommodating and interconnecting multiple of these systems while ensuring secure, relevant, fair, trust-based data sharing and use. The H2020 project GATEKEEPER aims to implement and test an open-source, European, standard-based, interoperable, and secure framework serving broad populations of aging citizens with heterogeneous health needs. Objective: We aim to describe the rationale for the selection of an optimal group of settings for the multinational large-scale piloting of the GATEKEEPER platform. Methods: The selection of implementation sites and reference use cases (RUCs) was based on the adoption of a double stratification pyramid reflecting the overall health of target populations and the intensity of proposed interventions; the identification of a principles guiding implementation site selection; and the elaboration of guidelines for RUC selection, ensuring clinical relevance and scientific excellence while covering the whole spectrum of citizen complexities and intervention intensities. Results: Seven European countries were selected, covering Europe’s geographical and socioeconomic heterogeneity: Cyprus, Germany, Greece, Italy, Poland, Spain, and the United Kingdom. These were complemented by the following 3 Asian pilots: Hong Kong, Singapore, and Taiwan. Implementation sites consisted of local ecosystems, including health care organizations and partners from industry, civil society, academia, and government, prioritizing the highly rated European Innovation Partnership on Active and Healthy Aging reference sites. RUCs covered the whole spectrum of chronic diseases, citizen complexities, and intervention intensities while privileging clinical relevance and scientific rigor. These included lifestyle-related early detection and interventions, using artificial intelligence–based digital coaches to promote healthy lifestyle and delay the onset or worsening of chronic diseases in healthy citizens; chronic obstructive pulmonary disease and heart failure decompensations management, proposing integrated care management based on advanced wearable monitoring and machine learning (ML) to predict decompensations; management of glycemic status in diabetes mellitus, based on beat to beat monitoring and short-term ML-based prediction of glycemic dynamics; treatment decision support systems for Parkinson disease, continuously monitoring motor and nonmotor complications to trigger enhanced treatment strategies; primary and secondary stroke prevention, using a coaching app and educational simulations with virtual and augmented reality; management of multimorbid older patients or patients with cancer, exploring novel chronic care models based on digital coaching, and advanced monitoring and ML; high blood pressure management, with ML-based predictions based on different intensities of monitoring through self-managed apps; and COVID-19 management, with integrated management tools limiting physical contact among actors. Conclusions: This paper provides a methodology for selecting adequate settings for the large-scale piloting of eHealth frameworks and exemplifies with the decisions taken in GATEKEEPER the current views of the WHO and European Commission while moving forward toward a European Data Space. %M 37379060 %R 10.2196/42187 %U https://www.jmir.org/2023/1/e42187 %U https://doi.org/10.2196/42187 %U http://www.ncbi.nlm.nih.gov/pubmed/37379060 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 25 %N %P e45662 %T Generate Analysis-Ready Data for Real-world Evidence: Tutorial for Harnessing Electronic Health Records With Advanced Informatic Technologies %A Hou,Jue %A Zhao,Rachel %A Gronsbell,Jessica %A Lin,Yucong %A Bonzel,Clara-Lea %A Zeng,Qingyi %A Zhang,Sinian %A Beaulieu-Jones,Brett K %A Weber,Griffin M %A Jemielita,Thomas %A Wan,Shuyan Sabrina %A Hong,Chuan %A Cai,Tianrun %A Wen,Jun %A Ayakulangara Panickan,Vidul %A Liaw,Kai-Li %A Liao,Katherine %A Cai,Tianxi %+ Department of Biomedical Informatics, Harvard Medical School, 10 Shattuck Street, Room 434, Boston, MA, 02115, United States, 1 617 432 4923, tcai@hsph.harvard.edu %K electronic health records %K real-world evidence %K data curation %K medical informatics %K randomized controlled trials %K reproducibility %D 2023 %7 25.5.2023 %9 Tutorial %J J Med Internet Res %G English %X Although randomized controlled trials (RCTs) are the gold standard for establishing the efficacy and safety of a medical treatment, real-world evidence (RWE) generated from real-world data has been vital in postapproval monitoring and is being promoted for the regulatory process of experimental therapies. An emerging source of real-world data is electronic health records (EHRs), which contain detailed information on patient care in both structured (eg, diagnosis codes) and unstructured (eg, clinical notes and images) forms. Despite the granularity of the data available in EHRs, the critical variables required to reliably assess the relationship between a treatment and clinical outcome are challenging to extract. To address this fundamental challenge and accelerate the reliable use of EHRs for RWE, we introduce an integrated data curation and modeling pipeline consisting of 4 modules that leverage recent advances in natural language processing, computational phenotyping, and causal modeling techniques with noisy data. Module 1 consists of techniques for data harmonization. We use natural language processing to recognize clinical variables from RCT design documents and map the extracted variables to EHR features with description matching and knowledge networks. Module 2 then develops techniques for cohort construction using advanced phenotyping algorithms to both identify patients with diseases of interest and define the treatment arms. Module 3 introduces methods for variable curation, including a list of existing tools to extract baseline variables from different sources (eg, codified, free text, and medical imaging) and end points of various types (eg, death, binary, temporal, and numerical). Finally, module 4 presents validation and robust modeling methods, and we propose a strategy to create gold-standard labels for EHR variables of interest to validate data curation quality and perform subsequent causal modeling for RWE. In addition to the workflow proposed in our pipeline, we also develop a reporting guideline for RWE that covers the necessary information to facilitate transparent reporting and reproducibility of results. Moreover, our pipeline is highly data driven, enhancing study data with a rich variety of publicly available information and knowledge sources. We also showcase our pipeline and provide guidance on the deployment of relevant tools by revisiting the emulation of the Clinical Outcomes of Surgical Therapy Study Group Trial on laparoscopy-assisted colectomy versus open colectomy in patients with early-stage colon cancer. We also draw on existing literature on EHR emulation of RCTs together with our own studies with the Mass General Brigham EHR. %M 37227772 %R 10.2196/45662 %U https://www.jmir.org/2023/1/e45662 %U https://doi.org/10.2196/45662 %U http://www.ncbi.nlm.nih.gov/pubmed/37227772 %0 Journal Article %@ 2561-326X %I JMIR Publications %V 7 %N %P e37269 %T An Emerging Screening Method for Interrogating Human Brain Function: Tutorial %A Sudre,Gustavo %A Bagić,Anto I %A Becker,James T %A Ford,John P %+ Brain FIT Imaging, LLC, 141 Main Street, Unadilla, NY, 13849, United States, 1 607 435 0930, gsudre@brainfitimaging.com %K screening %K brain function %K cognition %K magnetoencephalography %K MEG %K neuroimaging %K tutorial %K tool %K cognitive test %K neuroimaging %K signal %K cognitive function %D 2023 %7 27.4.2023 %9 Tutorial %J JMIR Form Res %G English %X Cognitive decline can be observed due to a myriad of causes. Clinicians would benefit from a noninvasive quantitative tool to screen and monitor brain function based on direct measures of neural features. In this study, we used neuroimaging data from magnetoencephalography (with a whole-head Elekta Neuromag 306 sensor system) to derive a set of features that strongly correlate with brain function. We propose that simple signal characteristics related to peak variability, timing, and abundance can be used by clinicians as a screening tool to investigate cognitive function in at-risk individuals. Using a minimalistic set of features, we were able to perfectly distinguish between participants with normative and nonnormative brain function, and we were also able to successfully predict participants’ Mini-Mental Test score (r=0.99; P<.001; mean absolute error=0.413). This set of features can be easily visualized in an analog fashion, providing clinicians with several graded measurements (in comparison to a single binary diagnostic tool) that can be used for screening and monitoring cognitive decline. %M 37103988 %R 10.2196/37269 %U https://formative.jmir.org/2023/1/e37269 %U https://doi.org/10.2196/37269 %U http://www.ncbi.nlm.nih.gov/pubmed/37103988 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 24 %N 12 %P e40730 %T Avoiding Under- and Overrecruitment in Behavioral Intervention Trials Using Bayesian Sequential Designs: Tutorial %A Bendtsen,Marcus %+ Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, 581 83, Sweden, 46 13 28 10 00, marcus.bendtsen@liu.se %K digital alcohol intervention %K Bayesian sequential design %K sample size %K randomized controlled trial %K trial recruitment %K behavioural intervention %K participant recruitment %K research participants %K research methods %K effect size %K trial procedure %D 2022 %7 16.12.2022 %9 Tutorial %J J Med Internet Res %G English %X Reducing research waste and protecting research participants from unnecessary harm should be top priorities for researchers studying interventions. However, the traditional use of fixed sample sizes exposes trials to risks of under- and overrecruitment by requiring that effect sizes be determined a priori. One mitigating approach is to adopt a Bayesian sequential design, which enables evaluation of the available evidence continuously over the trial period to decide when to stop recruitment. Target criteria are defined, which encode researchers’ intentions for what is considered findings of interest, and the trial is stopped once the scientific question is sufficiently addressed. In this tutorial, we revisit a trial of a digital alcohol intervention that used a fixed sample size of 2129 participants. We show that had a Bayesian sequential design been used, the trial could have ended after collecting data from approximately 300 participants. This would have meant exposing far fewer individuals to trial procedures, including being allocated to the waiting list control condition, and the evidence from the trial could have been made public sooner. %M 36525297 %R 10.2196/40730 %U https://www.jmir.org/2022/12/e40730 %U https://doi.org/10.2196/40730 %U http://www.ncbi.nlm.nih.gov/pubmed/36525297 %0 Journal Article %@ 1929-073X %I JMIR Publications %V 11 %N 2 %P e37036 %T Creating the Map of Interactive Services Aiding and Assisting Persons With Disabilities (MSAADA) Project: Tutorial for the Novel Use of a Store Locator App %A Etling,Mary Ann %A Musili,Michael %A Eastes,Kaytlin %A Oyungu,Eren %A McHenry,Megan S %+ Department of Pediatrics, Indiana University School of Medicine, 340 W 10th St, Indianapolis, IN, 46202, United States, 1 317 274 8157, maetling@iu.edu %K map %K virtual %K interactive %K disability %K resources %K inclusion %K mHealth %K Kenya %K global health %K public health %D 2022 %7 8.12.2022 %9 Tutorial %J Interact J Med Res %G English %X Background: An estimated 15% of the global population is living with a disability. In Kenya, children with disabilities remain among the most vulnerable populations, experiencing substantial barriers to wellness and inclusion. Smartphone ownership and internet access have been increasing across sub-Saharan Africa, including in Kenya. Despite these advances, online or mobile resources remain limited and difficult to find and navigate. Objective: This paper aims to describe the novel use of a store locator app to develop an interactive map of organizations that provide medical, educational, and socioeconomic resources to individuals with disabilities in Kenya. The target audience is individuals with disabilities, medical professionals, and organization leaders. Methods: A comprehensive list of organizations, government county offices, educational assessment and resource centers, and institutions was compiled. Organizations were contacted via email, WhatsApp, or in person for semistructured interviews. Based on the services offered, each organization was assigned categorical search tags. The data were entered into a third-party store locator app. The resulting map was inserted into a page on the Academic Model Providing Access to Healthcare (AMPATH) website. Results: The Map of Interactive Services Aiding and Assisting Persons With Disabilities (MSAADA; this abbreviation is also Swahili for “help”) was launched in July 2020 in both English and Swahili. The map included 89 organizations across Kenya. Of these, 51 were reached for an interview (for a 57% response rate). Interviewees cited limited paid staff and dependence on grant-based funding as primary challenges to growth and sustainability. Conclusions: MSAADA is an interactive, virtual map that aims to connect individuals with disabilities, medical professionals, and organization leaders to resources in Kenya. The novel use of a store locator app to compile resources in remote settings has the potential to improve access to health care for a wide variety of specialties and patient populations. Innovators in global health should consider the use of store locator apps to connect individuals to resources in regions with limited mapping. %M 36480245 %R 10.2196/37036 %U https://www.i-jmr.org/2022/2/e37036 %U https://doi.org/10.2196/37036 %U http://www.ncbi.nlm.nih.gov/pubmed/36480245 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 24 %N 4 %P e26339 %T From the United Kingdom to Australia—Adapting a Web-Based Self-management Education Program to Support the Management of Type 2 Diabetes: Tutorial %A Olson,Jenny %A Hadjiconstantinou,Michelle %A Luff,Carly %A Watts,Karen %A Watson,Natasha %A Miller,Venus %A Schofield,Deborah %A Khunti,Kamlesh %A Davies,Melanie J %A Calginari,Sara %+ Department of Kinesiology, The Pennsylvania State University, Recreation Hall, University Park, PA, 16801, United States, 1 8143083411, Jenny.Olson@psu.edu %K diabetes mellitus %K type 2 %K technology %K self-management %D 2022 %7 20.4.2022 %9 Tutorial %J J Med Internet Res %G English %X Diabetes self-management education and support can improve outcomes in people with diabetes. Providing health interventions via digital modes of delivery can extend the reach of programs delivered through traditional means. The web-based version of the Diabetes Education and Self-Management for Ongoing and Newly Diagnosed (MyDESMOND) is a digital diabetes education and support program for people with type 2 diabetes. The program was originally developed in the United Kingdom and is evidence-based, grounded in behavioral theory, and designed through a rigorous process of intervention mapping. As such, MyDESMOND was considered an ideal candidate for adaptation to the Australian setting. Program content and the digital platform were modified to suit the local context to increase the likelihood that the revised version of MyDESMOND will deliver similar outcomes to the original program. The aim of this paper is to describe the systematic processes undertaken to adapt the digital MyDESMOND diabetes education and support program for people with type 2 diabetes to the Australian setting. The adaptation involved a multidisciplinary group with a diverse range of skills and expertise—a governance structure was established, a skilled project team was appointed, and stakeholder engagement was strategically planned. The adaptation of the program content included modifications to the clinical recommendations, the inclusion of local resources, practical changes, and revisions to optimize readability. A 2-stage independent review of the modified content was enacted. Digital adaptations were informed by relevant standards, local legislative requirements, and considerations of data sovereignty. The digital platform was extensively tested before deployment to the production setting. MyDESMOND is the first evidence-based digital diabetes education and support program for Australians with type 2 diabetes. This paper provides a road map for the adaptation of digital health interventions to new contexts. %M 35442198 %R 10.2196/26339 %U https://www.jmir.org/2022/4/e26339 %U https://doi.org/10.2196/26339 %U http://www.ncbi.nlm.nih.gov/pubmed/35442198 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 24 %N 4 %P e28291 %T Methodological Guidelines for Systematic Assessments of Health Care Websites Using Web Analytics: Tutorial %A Fundingsland Jr,Edwin Lauritz %A Fike,Joseph %A Calvano,Joshua %A Beach,Jeffrey %A Lai,Deborah %A He,Shuhan %+ Center for Innovation in Digital HealthCare, Lab of Computer Science, Massachusetts General Hospital, 55 Fruit St., Boston, MA, 02114, United States, 1 (617) 726 2000, she@mgh.harvard.edu %K Google Analytics %K website usability %K conversion rate %K website engagement %K user demographics %K website traffic %K website content %K internet browsers %K healthcare websites %K web analytics %K healthcare industry %K usability %D 2022 %7 15.4.2022 %9 Tutorial %J J Med Internet Res %G English %X With the growing importance of communicating with the public via the web, many industries have used web analytics to provide information that organizations can use to better achieve their goals. Although the importance of health care websites has also grown, the health care industry has been slower to adopt the use of web analytics. Web analytics are the measurement, collection, analysis, and reporting of internet data used to measure direct user interaction. Our objective is to provide generalized methods for using web analytics as key performance metrics to evaluate websites and outline actionable recommendations for improvement. By deconstructing web analytic categories such as engagement, users, acquisition, content, and platform, we describe how web analytics are used to evaluate websites and how improvements can be made using this information. Engagement is how a user interacts with a website. It can be evaluated using the daily active users to monthly active users (DAU/MAU) ratio, bounce rate, pages viewed, and time on site. Poor engagement indicates potential problems with website usability. Users pertains to demographic information regarding the users interacting with a website. This data can help administrators understand who is engaging with their website. Acquisition refers to the overall website traffic and the method of traffic, which allows administrators to see how people are accessing their website. This information helps websites expand their methods of attracting users. Content refers to the overall relevancy, accuracy, and trustworthiness of a website’s content. If a website has poor content, it will likely experience difficulty with user engagement. Finally, platform refers to the technical aspects of how people access a website. It includes both the internet browsers and devices used. By providing detailed descriptions of these categories, we have identified how web administrators can use web analytics to systematically assess their websites. We have also provided generalized recommendations for actionable improvements. By introducing the potential of web analytics to augment usability and the conversion rate, we hope to assist health care organizations in better communicating with the public and therefore accomplishing the goals of their websites. %M 35436216 %R 10.2196/28291 %U https://www.jmir.org/2022/4/e28291 %U https://doi.org/10.2196/28291 %U http://www.ncbi.nlm.nih.gov/pubmed/35436216 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 10 %P e32365 %T Understanding Uptake of Digital Health Products: Methodology Tutorial for a Discrete Choice Experiment Using the Bayesian Efficient Design %A Szinay,Dorothy %A Cameron,Rory %A Naughton,Felix %A Whitty,Jennifer A %A Brown,Jamie %A Jones,Andy %+ Behavioural and Implementation Science Group, School of Health Sciences, University of East Anglia, Norwich Research Park Earlham Road, Norwich, NR4 7TJ, United Kingdom, 44 1603593064, d.szinay@uea.ac.uk %K discrete choice experiment %K stated preference methods %K mHealth %K digital health %K quantitative methodology %K uptake %K engagement %K methodology %K preference %K Bayesian %K design %K tutorial %K qualitative %K user preference %D 2021 %7 11.10.2021 %9 Tutorial %J J Med Internet Res %G English %X Understanding the preferences of potential users of digital health products is beneficial for digital health policy and planning. Stated preference methods could help elicit individuals’ preferences in the absence of observational data. A discrete choice experiment (DCE) is a commonly used stated preference method—a quantitative methodology that argues that individuals make trade-offs when engaging in a decision by choosing an alternative of a product or a service that offers the greatest utility, or benefit. This methodology is widely used in health economics in situations in which revealed preferences are difficult to collect but is much less used in the field of digital health. This paper outlines the stages involved in developing a DCE. As a case study, it uses the application of a DCE to reveal preferences in targeting the uptake of smoking cessation apps. It describes the establishment of attributes, the construction of choice tasks of 2 or more alternatives, and the development of the experimental design. This tutorial offers a guide for researchers with no prior knowledge of this research technique. %M 34633290 %R 10.2196/32365 %U https://www.jmir.org/2021/10/e32365 %U https://doi.org/10.2196/32365 %U http://www.ncbi.nlm.nih.gov/pubmed/34633290 %0 Journal Article %@ 2369-3762 %I JMIR Publications %V 7 %N 3 %P e29157 %T Creation of a Student-Run Medical Education Podcast: Tutorial %A Milligan,Kevin John %A Daulton,Robert Scott %A St Clair,Zachary Taylor %A Epperson,Madison Veronica %A Holloway,Rachel Mackenzie %A Schlaudecker,Jeffrey David %+ University of Cincinnati College of Medicine, 3230 Eden Ave, Cincinnati, OH, 45267, United States, 1 5135587333, milligkj@mail.uc.edu %K podcast %K medical student %K near-peer %K medical education %D 2021 %7 8.7.2021 %9 Tutorial %J JMIR Med Educ %G English %X Background: Podcasting has become a popular medium for medical education content. Educators and trainees of all levels are turning to podcasts for high-quality, asynchronous content. Although numerous medical education podcasts have emerged in recent years, few student-run podcasts exist. Student-run podcasts are a novel approach to supporting medical students. Near-peer mentoring has been shown to promote medical students’ personal and professional identity formation. Student-run podcasts offer a new medium for delivering near-peer advice to medical students in an enduring and accessible manner. Objective: This paper describes the creation of the UnsCripted Medicine Podcast—a student-run medical education podcast produced at the University of Cincinnati College of Medicine. Methods: The planning and preparatory phases spanned 6 months. Defining a target audience and establishing a podcast mission were key first steps. Efforts were directed toward securing funding; obtaining necessary equipment; and navigating the technical considerations of recording, editing, and publishing a podcast. In order to ensure that high professionalism standards were met, key partnerships were created with faculty from the College of Medicine. Results: The UnsCripted Medicine Podcast published 53 episodes in its first 2 years. The number of episodes released per month ranges from 0 to 5, with a mean of 2.0 episodes. The podcast has a Twitter account with 217 followers. The number of listeners who subscribed to the podcast via Apple Podcasts grew to 86 in the first year and then to 218 in the second year. The show has an average rating of 4.8 (out of 5) on Apple Podcasts, which is based on 24 ratings. The podcast has hosted 70 unique guests, including medical students, resident physicians, attending physicians, nurses, physicians’ family members, graduate medical education leadership, and educators. Conclusions: Medical student–run podcasts are a novel approach to supporting medical students and fostering professional identity formation. Podcasts are widely available and convenient for listeners. Additionally, podcast creators can publish content with lower barriers of entry compared to those of other forms of published content. Medical schools should consider supporting student podcast initiatives to allow for near-peer mentoring, augment the community, facilitate professional identity formation, and prepare the rising physician workforce for the technological frontier of medical education and practice. %M 34255694 %R 10.2196/29157 %U https://mededu.jmir.org/2021/3/e29157 %U https://doi.org/10.2196/29157 %U http://www.ncbi.nlm.nih.gov/pubmed/34255694 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 5 %P e25077 %T Establishing and Facilitating Large-Scale Manuscript Collaborations via Social Media: Novel Method and Tools for Replication %A Acquaviva,Kimberly D %+ School of Nursing, University of Virginia, 4005 McLeod Hall, Charlottesville, VA, 22903, United States, 1 202 423 0984, kda8xj@virginia.edu %K social media %K crowdsourcing %K collaboration %K health professions %K medicine %K scholarship %K literature %K research %D 2021 %7 17.5.2021 %9 Tutorial %J J Med Internet Res %G English %X Background: Authorship teams in the health professions are typically composed of scholars who are acquainted with one another before a manuscript is written. Even if a scholar has identified a diverse group of collaborators outside their usual network, writing an article with a large number of co-authors poses significant logistical challenges. Objective: This paper describes a novel method for establishing and facilitating large-scale manuscript collaborations via social media. Methods: On September 11, 2020, I used the social media platform Twitter to invite people to collaborate on an article I had drafted. Anyone who wanted to collaborate was welcome, regardless of discipline, specialty, title, country of residence, or degree completion. During the 25 days that followed, I used Google Docs, Google Sheets, and Google Forms to manage all aspects of the collaboration. Results: The collaboration resulted in the completion of 2 manuscripts in a 25-day period. The International Council of Medical Journal Editors authorship criteria were met by 40 collaborators for the first article (“Documenting Social Media Engagement as Scholarship: A New Model for Assessing Academic Accomplishment for the Health Professions”) and 35 collaborators for the second article (“The Benefits of Using Social Media as a Health Professional in Academia”). The authorship teams for both articles were notably diverse, with 17%-18% (7/40 and 6/35, respectively) of authors identifying as a person of color and/or underrepresented minority, 37%-38% (15/40 and 13/35, respectively) identifying as LGBTQ+ (lesbian, gay, bisexual, transgender, gender non-conforming, queer and/or questioning), 73%-74% (29/40 and 26/35, respectively) using she/her pronouns, and 20%-23% (9/40 and 7/35, respectively) identifying as a person with a disability. Conclusions: Scholars in the health professions can use this paper in conjunction with the tools provided to replicate this process in carrying out their own large-scale manuscript collaborations. %M 33999002 %R 10.2196/25077 %U https://www.jmir.org/2021/5/e25077 %U https://doi.org/10.2196/25077 %U http://www.ncbi.nlm.nih.gov/pubmed/33999002 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 5 %P e20803 %T Determination of Patient Sentiment and Emotion in Ophthalmology: Infoveillance Tutorial on Web-Based Health Forum Discussions %A Nguyen,Anne Xuan-Lan %A Trinh,Xuan-Vi %A Wang,Sophia Y %A Wu,Albert Y %+ Department of Ophthalmology, Byers Eye Institute, Stanford University, 2452 Watson Court, Palo Alto, CA, 94303, United States, 1 650 497 0758, awu1@stanford.edu %K sentiment analysis %K emotions analysis %K natural language processing %K online forums %K social media %K patient attitudes %K medicine %K infodemiology %K infoveillance %K digital health %D 2021 %7 17.5.2021 %9 Tutorial %J J Med Internet Res %G English %X Background: Clinical data in social media are an underused source of information with great potential to allow for a deeper understanding of patient values, attitudes, and preferences. Objective: This tutorial aims to describe a novel, robust, and modular method for the sentiment analysis and emotion detection of free text from web-based forums and the factors to consider during its application. Methods: We mined the discussion and user information of all posts containing search terms related to a medical subspecialty (oculoplastics) from MedHelp, the largest web-based platform for patient health forums. We used data cleaning and processing tools to define the relevant subset of results and prepare them for sentiment analysis. We executed sentiment and emotion analyses by using IBM Watson Natural Language Understanding to generate sentiment and emotion scores for the posts and their associated keywords. The keywords were aggregated using natural language processing tools. Results: Overall, 39 oculoplastic-related search terms resulted in 46,381 eligible posts within 14,329 threads. Posts were written by 18,319 users (117 doctors; 18,202 patients) and included 201,611 associated keywords. Keywords that occurred ≥500 times in the corpus were used to identify the most prominent topics, including specific symptoms, medication, and complications. The sentiment and emotion scores of these keywords and eligible posts were analyzed to provide concrete examples of the potential of this methodology to allow for a better understanding of patients’ attitudes. The overall sentiment score reflects a positive, neutral, or negative sentiment, whereas the emotion scores (anger, disgust, fear, joy, and sadness) represent the likelihood of the presence of the emotion. In keyword grouping analyses, medical signs, symptoms, and diseases had the lowest overall sentiment scores (−0.598). Complications were highly associated with sadness (0.485). Forum posts mentioning body parts were related to sadness (0.416) and fear (0.321). Administration was the category with the highest anger score (0.146). The top 6 forum subgroups had an overall negative sentiment score; the most negative one was the Neurology forum, with a score of −0.438. The Undiagnosed Symptoms forum had the highest sadness score (0.448). The least likely fearful posts were those from the Eye Care forum, with a score of 0.260. The overall sentiment score was much more negative before the doctor replied. The anger, disgust, fear, and sadness emotion scores decreased in likelihood, whereas joy was slightly more likely to be expressed after doctors replied. Conclusions: This report allows physicians and researchers to efficiently mine and perform sentiment analysis on social media to better understand patients’ perspectives and promote patient-centric care. Important factors to be considered during its application include evaluating the scope of the search; selecting search terms and understanding their linguistic usages; and establishing selection, filtering, and processing criteria for posts and keywords tailored to the desired results. %M 33999001 %R 10.2196/20803 %U https://www.jmir.org/2021/5/e20803 %U https://doi.org/10.2196/20803 %U http://www.ncbi.nlm.nih.gov/pubmed/33999001 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 4 %P e25502 %T The Healing Hearts Together Randomized Controlled Trial and the COVID-19 Pandemic: A Tutorial for Transitioning From an In-Person to a Web-Based Intervention %A Lalande,Kathleen %A Greenman,Paul S %A Bouchard,Karen %A Johnson,Susan M %A Tulloch,Heather %+ Division of Cardiac Prevention and Rehabilitation, University of Ottawa Heart Institute, 40 Ruskin St, Ottawa, ON, K1Y 4W7, Canada, 1 613 696 7000 ext 19705, hetulloch@ottawaheart.ca %K web-based intervention %K internet-based intervention %K randomized controlled trial %K COVID-19 %K research %K tutorial %K digital medicine %K behavioral medicine %K telehealth %K telemedicine %K cardiovascular rehabilitation %D 2021 %7 6.4.2021 %9 Tutorial %J J Med Internet Res %G English %X Supportive couple relationships are associated with reduced risk of chronic illness development, such as cardiovascular disease, as well as improved secondary prevention. Healing Hearts Together (HHT) is an 8-week couples-based intervention designed to improve relationship quality, mental health, quality of life, and cardiovascular health among couples in which one partner has experienced a cardiac event. A randomized controlled trial began in October 2019 to test the efficacy of the in-person, group-based HHT program as compared to usual care. In March of 2020, all recruitment, assessments, and interventions halted due to the COVID-19 pandemic. Guided by optimal virtual care principles, as well as by Hom and colleagues’ four-stage framework—consultation, adaptation, pilot-testing, and test launch—this paper is a tutorial for the step-by-step transition planning and implementation of a clinical research intervention from an in-person to a web-based format, using the HHT program as an example. Clinical and research considerations are reviewed, including (1) privacy, (2) therapeutic aspects of the intervention, (3) group cohesion, (4) research ethics, (5) participant recruitment, (6) assessment measures, (7) data collection, and (8) data analyses. This tutorial can assist clinical researchers in transitioning their research programs to a web-based format during the pandemic and beyond. %M 33729984 %R 10.2196/25502 %U https://www.jmir.org/2021/4/e25502 %U https://doi.org/10.2196/25502 %U http://www.ncbi.nlm.nih.gov/pubmed/33729984 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 3 %P e25173 %T Guidelines for Conducting Virtual Cognitive Interviews During a Pandemic %A Shepperd,James A %A Pogge,Gabrielle %A Hunleth,Jean M %A Ruiz,Sienna %A Waters,Erika A %+ Department of Psychology, University of Florida, 945 Center Drive, Gainesville, FL, 32611, United States, 1 352 273 2165, shepperd@ufl.edu %K cognitive interview %K COVID-19 %K guidelines %K teleresearch %K pandemic %K tablet computer %K telehealth %K training %D 2021 %7 11.3.2021 %9 Viewpoint %J J Med Internet Res %G English %X The COVID-19 pandemic has challenged researchers working in physical contact with research participants. Cognitive interviews examine whether study components (most often questionnaire items) are worded or structured in a manner that allows study participants to interpret the items in a way intended by the researcher. We developed guidelines to conduct cognitive interviews virtually to accommodate interviewees who have limited access to the internet. The guidelines describe the essential communication and safety equipment requirements and outline a procedure for collecting responses while maintaining the safety of the participants and researchers. Furthermore, the guidelines provide suggestions regarding training of participants to use the technology, encouraging them to respond aloud (a potential challenge given that the researcher is not physically present with the participant), and testing and deploying the equipment prior to the interview. Finally, the guidelines emphasize the need to adapt the interview to the circumstances and anticipate potential problems that might arise. %M 33577464 %R 10.2196/25173 %U https://www.jmir.org/2021/3/e25173 %U https://doi.org/10.2196/25173 %U http://www.ncbi.nlm.nih.gov/pubmed/33577464 %0 Journal Article %@ 2561-326X %I JMIR Publications %V 4 %N 12 %P e23379 %T Starter Kit for Geotagging and Geovisualization in Health Care: Resource Paper %A Do,Quan %A Marc,David %A Plotkin,Marat %A Pickering,Brian %A Herasevich,Vitaly %+ Mayo Clinic, 200 First St SW, Rochester, MN , United States, 1 507 255 4055, vitaly@mayo.edu %K geographic mapping %K medicalGIS guidelines %K information storage and retrieval %K mapping %K geotagging %K data visualization %K population %K public health %D 2020 %7 24.12.2020 %9 Original Paper %J JMIR Form Res %G English %X Background: Geotagging is the process of attaching geospatial tags to various media data types. In health care, the goal of geotagging is to gain a better understanding of health-related questions applied to populations. Although there has been a prevalence of geographic information in public health, in order to effectively use and expand geotagging across health care there is a requirement to understand other factors such as the disposition, standardization, data sources, technologies, and limitations. Objective: The objective of this document is to serve as a resource for new researchers in the field. This report aims to be comprehensive but easy for beginners to understand and adopt in practice. The optimal geocodes, their sources, and a rationale for use are suggested. Geotagging’s issues and limitations are also discussed. Methods: A comprehensive review of technical instructions and articles was conducted to evaluate guidelines for geotagging, and online resources were curated to support the implementation of geotagging practices. Summary tables were developed to describe the available geotagging resources (free and for fee) that can be leveraged by researchers and quality improvement personnel to effectively perform geospatial analyses primarily targeting US health care. Results: This paper demonstrated steps to develop an initial geotagging and geovisualization project with clear structure and instructions. The geotagging resources were summarized. These resources are essential for geotagging health care projects. The discussion section provides better understanding of geotagging’s limitations and suggests suitable way to approach it. Conclusions: We explain how geotagging can be leveraged in health care and offer the necessary initial resources to obtain geocodes, adjustment data, and health-related measures. The resources outlined in this paper can support an individual and/or organization in initiating a geotagging health care project. %M 33361054 %R 10.2196/23379 %U http://formative.jmir.org/2020/12/e23379/ %U https://doi.org/10.2196/23379 %U http://www.ncbi.nlm.nih.gov/pubmed/33361054 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 12 %P e22420 %T Developing Virtual Reality Trauma Training Experiences Using 360-Degree Video: Tutorial %A Patel,Devika %A Hawkins,Jessica %A Chehab,Lara Zena %A Martin-Tuite,Patrick %A Feler,Joshua %A Tan,Amy %A Alpers,Benjamin S %A Pink,Sophia %A Wang,Jerome %A Freise,Jonathan %A Kim,Phillip %A Peabody,Christopher %A Bowditch,John %A Williams,Eric R %A Sammann,Amanda %+ Department of Surgery, University of California, San Francisco, 1001 Potrero Ave, San Francisco, CA, 94110, United States, 1 628 206 3764, devika.patel@ucsf.edu %K virtual reality %K cineVR %K 360-degree video %K trauma training %K medical education %D 2020 %7 16.12.2020 %9 Tutorial %J J Med Internet Res %G English %X Historically, medical trainees were educated in the hospital on real patients. Over the last decade, there has been a shift to practicing skills through simulations with mannequins or patient actors. Virtual reality (VR), and in particular, the use of 360-degree video and audio (cineVR), is the next-generation advancement in medical simulation that has novel applications to augment clinical skill practice, empathy building, and team training. In this paper, we describe methods to design and develop a cineVR medical education curriculum for trauma care training using real patient care scenarios at an urban, safety-net hospital and Level 1 trauma center. The purpose of this publication is to detail the process of finding a cineVR production partner; choosing the camera perspectives; maintaining patient, provider, and staff privacy; ensuring data security; executing the cineVR production process; and building the curriculum. %M 33325836 %R 10.2196/22420 %U http://www.jmir.org/2020/12/e22420/ %U https://doi.org/10.2196/22420 %U http://www.ncbi.nlm.nih.gov/pubmed/33325836 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 9 %P e19217 %T Leveraging Interdisciplinary Teams to Develop and Implement Secure Websites for Behavioral Research: Applied Tutorial %A Martin,Christie L %A Kramer-Kostecka,Eydie N %A Linde,Jennifer A %A Friend,Sarah %A Zuroski,Vanessa R %A Fulkerson,Jayne A %+ School of Nursing, University of Minnesota, 5-140 Weaver-Densford Hall, 308 Harvard Street SE, Minneapolis, MN, 55455, United States, 1 612 624 9600, mart1026@umn.edu %K research ethics and compliance %K website development %K behavioral research %K digital interventions %K website authentication %K website security %D 2020 %7 23.9.2020 %9 Tutorial %J J Med Internet Res %G English %X Behavioral researchers are increasingly using interactive digital platforms, either as standalone or supplementary intervention tools, to facilitate positive changes in research participants’ health habits. Research-oriented interactive websites optimally offer a variety of participatory mediums, such as blogs, user-driven content, or health activities. Owing to the multidirectional features of interactive websites, and a corresponding need to protect research participants’ identity and data, it is paramount that researchers design ethical platforms that ensure privacy and minimize loss of anonymity and confidentiality. Authentication (ie, digital verification of one’s identity) of interactive sites is one viable solution to these concerns. Although previous publications have addressed ethical requirements related to authenticated platforms, few applied guidelines in the literature facilitate adherence to ethical principles and legally compliant study protocols during all phases of research website creation (feasibility, design, implementation, and maintenance). Notably, to remain compliant with ethical standards and study protocols, behavioral researchers must collaborate with interdisciplinary teams to ensure that the authenticated site remains secure and usable in all stages of the project. In this tutorial, we present a case study conducted at a large research university. Through iterative and practical recommendations, we detail lessons learned from collaborations with the Institutional Review Board, legal experts, and information technology teams. Although the intricacies of our applied tutorial may require adaptations based on each institution’s technological capacity, we are confident that the core takeaways are universal and thus useful to behavioral researchers creating ethically responsible and compliant interactive websites. %M 32965234 %R 10.2196/19217 %U http://www.jmir.org/2020/9/e19217/ %U https://doi.org/10.2196/19217 %U http://www.ncbi.nlm.nih.gov/pubmed/32965234 %0 Journal Article %@ 2368-7959 %I JMIR Publications %V 7 %N 7 %P e15878 %T Methodological Challenges in Web-Based Trials: Update and Insights From the Relatives Education and Coping Toolkit Trial %A Robinson,Heather %A Appelbe,Duncan %A Dodd,Susanna %A Flowers,Susan %A Johnson,Sonia %A Jones,Steven H %A Mateus,Céu %A Mezes,Barbara %A Murray,Elizabeth %A Rainford,Naomi %A Rosala-Hallas,Anna %A Walker,Andrew %A Williamson,Paula %A Lobban,Fiona %+ Division of Health Research, Spectrum Centre for Mental Health Research, Lancaster University, Bailrigg, Lancaster LA1 4YW, Lancaster, , United Kingdom, 44 (0)1524 593, s.jones7@lancaster.ac.uk %K randomized controlled trial %K research design %K methods %K internet %K web %K mental health %K relatives %K carers %D 2020 %7 17.7.2020 %9 Tutorial %J JMIR Ment Health %G English %X There has been a growth in the number of web-based trials of web-based interventions, adding to an increasing evidence base for their feasibility and effectiveness. However, there are challenges associated with such trials, which researchers must address. This discussion paper follows the structure of the Down Your Drink trial methodology paper, providing an update from the literature for each key trial parameter (recruitment, registration eligibility checks, consent and participant withdrawal, randomization, engagement with a web-based intervention, retention, data quality and analysis, spamming, cybersquatting, patient and public involvement, and risk management and adverse events), along with our own recommendations based on designing the Relatives Education and Coping Toolkit randomized controlled trial for relatives of people with psychosis or bipolar disorder. The key recommendations outlined here are relevant for future web-based and hybrid trials and studies using iterative development and test models such as the Accelerated Creation-to-Sustainment model, both within general health research and specifically within mental health research for relatives. Researchers should continue to share lessons learned from conducting web-based trials of web-based interventions to benefit future studies.International Registered Report Identifier (IRRID): RR2-10.1136/bmjopen-2017-016965 %M 32497018 %R 10.2196/15878 %U https://mental.jmir.org/2020/7/e15878 %U https://doi.org/10.2196/15878 %U http://www.ncbi.nlm.nih.gov/pubmed/32497018 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 22 %N 5 %P e17316 %T Using Intervention Mapping to Develop a Digital Self-Management Program for People With Type 2 Diabetes: Tutorial on MyDESMOND %A Hadjiconstantinou,Michelle %A Schreder,Sally %A Brough,Christopher %A Northern,Alison %A Stribling,Bernie %A Khunti,Kamlesh %A Davies,Melanie J %+ Leicester Diabetes Centre, NHS Trust, University Hospitals of Leicester, Gwendolen Road, Leicester, United Kingdom, 44 116 258 4320, sally.schreder@uhl-tr.nhs.uk %K diabetes mellitus, type 2 %K technology %K self-management %D 2020 %7 11.5.2020 %9 Tutorial %J J Med Internet Res %G English %X Digital health interventions (DHIs) are increasingly becoming integrated into diabetes self-management to improve behavior. Despite DHIs becoming available to people with chronic conditions, the development strategies and processes undertaken are often not well described. With theoretical frameworks available in current literature, it is vital that DHIs follow a shared language and communicate a robust development process in a comprehensive way. This paper aims to bring a unique perspective to digital development, as it describes the systematic process of developing a digital self-management program for people with type 2 diabetes, MyDESMOND. We provide a step-by-step guide, based on the intervention mapping (IM) framework to illustrate the process of adapting an existing face-to-face self-management program (diabetes education and self- management for ongoing and newly diagnosed, DESMOND) and translating it to a digital platform (MyDESMOND). Overall, this paper describes the 4 IM steps that were followed to develop MyDESMOND—step 1 to establish a planning group and a patient and public involvement group to describe the context of the intervention and program goals, step 2 to identify objectives and determinants at early design stages to maintain a focus on the strategies adopted, step 3 to generate the program components underpinned by appropriate psychological theories and models, and step 4 to develop the program content and describe the iterative process of refining the content and format of the digital program for implementation. This paper concludes with a number of key learnings collated throughout our development process, which we hope other researchers may find useful when developing DHIs for chronic conditions. %M 32391797 %R 10.2196/17316 %U https://www.jmir.org/2020/5/e17316 %U https://doi.org/10.2196/17316 %U http://www.ncbi.nlm.nih.gov/pubmed/32391797 %0 Journal Article %@ 2291-5222 %I JMIR Publications %V 8 %N 4 %P e15561 %T Developing Mental or Behavioral Health Mobile Apps for Pilot Studies by Leveraging Survey Platforms: A Do-it-Yourself Process %A Chow,Philip I %+ Center for Behavioral Health and Technology, Department of Psychiatry and Neurobehavioral Sciences, University of Virginia, 560 Ray C. Hunt Dr., Charlottesville, VA, 22908, United States, 1 434 924 5401, philip.i.chow@gmail.com %K app %K mental health %K mHealth %D 2020 %7 20.4.2020 %9 Tutorial %J JMIR Mhealth Uhealth %G English %X Background: Behavioral health researchers are increasingly recognizing the potential of mobile phone apps to deliver empirically supported treatments. However, current options for developing apps typically require large amounts of expertise or money. Objective: This paper aims to describe a pragmatic do-it-yourself approach for researchers to create and pilot an Android mobile phone app using existing survey software (eg, Qualtrics survey platform). Methods: This study was conducted at an academic research center in the United States focused on developing and evaluating behavioral health technologies. The process outlined in this paper was derived and condensed from the steps to building an existing app intervention, iCanThrive, which was developed to enhance mental well-being in women cancer survivors. Results: This paper describes an inexpensive, practical process that uses a widely available survey software, such as Qualtrics, to create and pilot a mobile phone intervention that is presented to participants as a Web viewer app that is downloaded from the Google Play store. Health researchers who are interested in using this process to pilot apps are encouraged to inquire about the survey platforms available to them, the level of security those survey platforms provide, and the regulatory guidelines set forth by their institution. Conclusions: As app interventions continue to gain interest among researchers and consumers alike, it is important to find new ways to efficiently develop and pilot app interventions before committing a large amount of resources. Mobile phone app interventions are an important component to discovering new ways to reach and support individuals with behavioral or mental health disorders. %M 32310143 %R 10.2196/15561 %U https://mhealth.jmir.org/2020/4/e15561 %U https://doi.org/10.2196/15561 %U http://www.ncbi.nlm.nih.gov/pubmed/32310143 %0 Journal Article %@ 2561-6722 %I JMIR Publications %V 2 %N 2 %P e16335 %T Voices in Evidence-Based Newborn Care: A How-to-Guide on Developing a Parent-Facing Podcast %A Parga-Belinkie,Joanna %A Merchant,Raina M %+ Children's Hospital of Philadelphia, 3401 Civic Center Blvd, Division of Neonatology, 2NW35, Philadelphia, PA, 19104, United States, 1 5164268898, jo.parga@gmail.com %K neonatology %K social media %K medical education %K patient education %D 2019 %7 20.12.2019 %9 Tutorial %J JMIR Pediatr Parent %G English %X Podcasting is becoming a more popular form of media. Its use in medical education is being researched—but what about its use in public education? In this tutorial, the authors offer a how-to-guide on starting a public or patient-facing podcast. The authors hope to inspire more physicians to utilize this type of media to share evidence-based information. More research is needed looking into how podcasting can be used to help with patient education. %M 31859674 %R 10.2196/16335 %U http://pediatrics.jmir.org/2019/2/e16335/ %U https://doi.org/10.2196/16335 %U http://www.ncbi.nlm.nih.gov/pubmed/31859674 %0 Journal Article %@ 2291-5222 %I JMIR Publications %V 7 %N 8 %P e11966 %T Deep Learning Intervention for Health Care Challenges: Some Biomedical Domain Considerations %A Tobore,Igbe %A Li,Jingzhen %A Yuhang,Liu %A Al-Handarish,Yousef %A Kandwal,Abhishek %A Nie,Zedong %A Wang,Lei %+ Center for Medical Robotics and Minimally Invasive Surgical Devices, Shenzhen Institutes of Advance Technology, Chinese Academy of Sciences, 1068 Xueyuan Avenue, Shenzhen University, Xili Town, Nanshan District, Shenzhen,, China, 86 755 86585213, zd.nie@siat.ac.cn %K machine learning %K deep learning %K big data %K mHealth %K medical imaging %K electronic health record %K biologicals %K biomedical %K ECG %K EEG %K artificial intelligence %D 2019 %7 02.08.2019 %9 Viewpoint %J JMIR Mhealth Uhealth %G English %X The use of deep learning (DL) for the analysis and diagnosis of biomedical and health care problems has received unprecedented attention in the last decade. The technique has recorded a number of achievements for unearthing meaningful features and accomplishing tasks that were hitherto difficult to solve by other methods and human experts. Currently, biological and medical devices, treatment, and applications are capable of generating large volumes of data in the form of images, sounds, text, graphs, and signals creating the concept of big data. The innovation of DL is a developing trend in the wake of big data for data representation and analysis. DL is a type of machine learning algorithm that has deeper (or more) hidden layers of similar function cascaded into the network and has the capability to make meaning from medical big data. Current transformation drivers to achieve personalized health care delivery will be possible with the use of mobile health (mHealth). DL can provide the analysis for the deluge of data generated from mHealth apps. This paper reviews the fundamentals of DL methods and presents a general view of the trends in DL by capturing literature from PubMed and the Institute of Electrical and Electronics Engineers database publications that implement different variants of DL. We highlight the implementation of DL in health care, which we categorize into biological system, electronic health record, medical image, and physiological signals. In addition, we discuss some inherent challenges of DL affecting biomedical and health domain, as well as prospective research directions that focus on improving health management by promoting the application of physiological signals and modern internet technology. %M 31376272 %R 10.2196/11966 %U https://mhealth.jmir.org/2019/8/e11966/ %U https://doi.org/10.2196/11966 %U http://www.ncbi.nlm.nih.gov/pubmed/31376272 %0 Journal Article %@ 2369-2960 %I JMIR Publications %V 5 %N 2 %P e13439 %T Google Trends in Infodemiology and Infoveillance: Methodology Framework %A Mavragani,Amaryllis %A Ochoa,Gabriela %+ Department of Computing Science and Mathematics, Faculty of Natural Sciences, University of Stirling, University Campus, Stirling, FK94LA, United Kingdom, 44 7523782711, amaryllis.mavragani1@stir.ac.uk %K big data %K health %K infodemiology %K infoveillance %K internet behavior %K Google Trends %D 2019 %7 29.05.2019 %9 Tutorial %J JMIR Public Health Surveill %G English %X Internet data are being increasingly integrated into health informatics research and are becoming a useful tool for exploring human behavior. The most popular tool for examining online behavior is Google Trends, an open tool that provides information on trends and the variations of online interest in selected keywords and topics over time. Online search traffic data from Google have been shown to be useful in analyzing human behavior toward health topics and in predicting disease occurrence and outbreaks. Despite the large number of Google Trends studies during the last decade, the literature on the subject lacks a specific methodology framework. This article aims at providing an overview of the tool and data and at presenting the first methodology framework in using Google Trends in infodemiology and infoveillance, including the main factors that need to be taken into account for a strong methodology base. We provide a step-by-step guide for the methodology that needs to be followed when using Google Trends and the essential aspects required for valid results in this line of research. At first, an overview of the tool and the data are presented, followed by an analysis of the key methodological points for ensuring the validity of the results, which include selecting the appropriate keyword(s), region(s), period, and category. Overall, this article presents and analyzes the key points that need to be considered to achieve a strong methodological basis for using Google Trends data, which is crucial for ensuring the value and validity of the results, as the analysis of online queries is extensively integrated in health research in the big data era. %M 31144671 %R 10.2196/13439 %U http://publichealth.jmir.org/2019/2/e13439/ %U https://doi.org/10.2196/13439 %U http://www.ncbi.nlm.nih.gov/pubmed/31144671 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 21 %N 1 %P e12128 %T Human-Centered Design of Video-Based Health Education: An Iterative, Collaborative, Community-Based Approach %A Adam,Maya %A McMahon,Shannon A %A Prober,Charles %A Bärnighausen,Till %+ Stanford Center for Health Education, Stanford School of Medicine, Stanford University, 408 Panama Mall, Stanford, CA, 94305, United States, 1 650 839 3600, madam@stanford.edu %K human-centered design %K health promotion %K health behavior %K health knowledge, attitudes, practice %K community health workers %K telemedicine %K eHealth %K mHealth %D 2019 %7 30.01.2019 %9 Tutorial %J J Med Internet Res %G English %X Drawing on 5 years of experience designing, producing, and disseminating video health education programs globally, we outline the process of creating accessible, engaging, and relevant video health education content using a community-based, human-centered design approach. We show that this approach can yield a new generation of interventions, which are better aligned with the needs and contexts of target communities. The participation of target communities and local stakeholders in the content production and design process fosters ownership of the content and increases the likelihood that the resulting intervention will resonate within its intended primary audience and be disseminated broadly. Ease of future adaptation for additional global audiences and modification of the content for multiple dissemination pathways are important early considerations to ensure scalability and long-term impact of the intervention. Recent advances in mobile technology can facilitate the dissemination of accessible, engaging health education at scale, thereby enhancing the potential impact of video-based educational tools.Accessible and engaging health education is a cornerstone of health behavior change. Especially in low- and middle-income countries, increasing access to effective health education can contribute to improved health outcomes. Prior research has identified several characteristics of effective health education interventions. These include the integration of pictures, narratives, and entertainment-education, in which the health messages that make up the educational content are embedded. However, the effectiveness and long-term impact of health messages ultimately depend on how well the end users can identify with the content that is presented. This identification, in turn, is a function of how well the messages correspond to user needs and wants and how this correspondence is communicated through the design characteristics of the health education intervention. %M 30698531 %R 10.2196/12128 %U http://www.jmir.org/2019/1/e12128/ %U https://doi.org/10.2196/12128 %U http://www.ncbi.nlm.nih.gov/pubmed/30698531 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 20 %N 11 %P e290 %T Using Facebook for Large-Scale Online Randomized Clinical Trial Recruitment: Effective Advertising Strategies %A Akers,Laura %A Gordon,Judith S %+ Oregon Research Institute, 1776 Millrace Drive, Eugene, OR, 97403, United States, 1 541 484 2123, lauraa@ori.org %K research subject recruitment %K advertisements %K social media %D 2018 %7 08.11.2018 %9 Tutorial %J J Med Internet Res %G English %X Targeted Facebook advertising can be an effective strategy to recruit participants for a large-scale online study. Facebook advertising is useful for reaching people in a wide geographic area, matching a specific demographic profile. It can also target people who would be unlikely to search for the information and would thus not be accessible via Google AdWords. It is especially useful when it is desirable not to raise awareness of the study in a demographic group that would be ineligible for the study. This paper describes the use of Facebook advertising to recruit and enroll 1145 women over a 15-month period for a randomized clinical trial to teach support skills to female partners of male smokeless tobacco users. This tutorial shares our study team’s experiences, lessons learned, and recommendations to help researchers design Facebook advertising campaigns. Topics covered include designing the study infrastructure to optimize recruitment and enrollment tracking, creating a Facebook presence via a fan page, designing ads that attract potential participants while meeting Facebook’s strict requirements, and planning and managing an advertising campaign that accommodates the rapid rate of diminishing returns for each ad. %M 30409765 %R 10.2196/jmir.9372 %U http://www.jmir.org/2018/11/e290/ %U https://doi.org/10.2196/jmir.9372 %U http://www.ncbi.nlm.nih.gov/pubmed/30409765 %0 Journal Article %@ 2369-3762 %I JMIR Publications %V 4 %N 2 %P e10347 %T Use of Grading of Recommendations, Assessment, Development, and Evaluation to Combat Fake News: A Case Study of Influenza Vaccination in Pregnancy %A Zafar,Sidra %A Habboush,Yacob %A Beidas,Sary %+ Department of Internal Medicine, Orange Park Medical Center, 2001 Kingsley Avenue, Orange Park, Jacksonville, FL, 32073, United States, 1 904 639 8500, sary.beidas@hcahealthcare.com %K GRADE %K influenza %K vaccination %K spontaneous abortion %K miscarriage %D 2018 %7 07.11.2018 %9 Review %J JMIR Med Educ %G English %X Background: The Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) framework is a validated evaluation tool used to assess the quality of scientific publications. It helps in enhancing clinicians’ decision-making process and supports production of informed healthy policy. Objective: The purpose of this report was two-fold. First, we reviewed the interpretation of observational studies. The second purpose was to share or provide an example using the GRADE criteria. Methods: To illustrate the use of the GRADE framework to assess publications, we selected a study evaluating the risk of spontaneous abortion (SAB) after influenza vaccine administration. Results: Since 2004, the Centers for Disease Control and Prevention and the Advisory Committee on Immunization Practice have recommended influenza vaccination of pregnant women. Previous studies have not found an association between influenza vaccination and SAB. However, in a recent case-control study by Donahue et al, a correlation with SAB in women who received the H1N1 influenza vaccine was identified. For women who received H1N1–containing vaccine in the previous and current influenza season, the adjusted odds ratio (aOR) for SAB was 7.7 (95% CI, 2.2-27.3), while the aOR for women not vaccinated in the previous season but vaccinated in the current season was 1.3 (95% CI, 0.7-2.7). Conclusions: Our goal is to enable the readers to critique published literature using appropriate evaluation tools such as GRADE. %M 30404772 %R 10.2196/10347 %U http://mededu.jmir.org/2018/2/e10347/ %U https://doi.org/10.2196/10347 %U http://www.ncbi.nlm.nih.gov/pubmed/30404772 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 20 %N 10 %P e10873 %T A Gentle Introduction to the Comparison Between Null Hypothesis Testing and Bayesian Analysis: Reanalysis of Two Randomized Controlled Trials %A Bendtsen,Marcus %+ Division of Community Medicine, Department of Medical and Health Sciences, Linköping University, Linköping, 58183, Sweden, 46 733140708, marcus.bendtsen@liu.se %K null hypothesis testing %K Bayesian analysis %K randomized controlled trials %K Bayes theorem %K randomized controlled trials as topic %D 2018 %7 24.10.2018 %9 Tutorial %J J Med Internet Res %G English %X The debate on the use and misuse of P values has risen and fallen throughout their almost century-long existence in scientific discovery. Over the past few years, the debate has again received front-page attention, particularly through the public reminder by the American Statistical Association on how P values should be used and interpreted. At the core of the issue lies a fault in the way that scientific evidence is dichotomized and research is subsequently reported, and this fault is exacerbated by researchers giving license to statistical models to do scientific inference. This paper highlights a different approach to handling the evidence collected during a randomized controlled trial, one that does not dichotomize, but rather reports the evidence collected. Through the use of a coin flipping experiment and reanalysis of real-world data, the traditional approach of testing null hypothesis significance is contrasted with a Bayesian approach. This paper is meant to be understood by those who rely on statistical models to draw conclusions from data, but are not statisticians and may therefore not be able to grasp the debate that is primarily led by statisticians. %M 30148453 %R 10.2196/10873 %U http://www.jmir.org/2018/10/e10873/ %U https://doi.org/10.2196/10873 %U http://www.ncbi.nlm.nih.gov/pubmed/30148453 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 20 %N 7 %P e239 %T Creating Low-Cost 360-Degree Virtual Reality Videos for Hospitals: A Technical Paper on the Dos and Don’ts %A O’Sullivan,Benjamin %A Alam,Fahad %A Matava,Clyde %+ Department of Anesthesia and Pain Medicine, Hospital for Sick Children, Toronto, 555 University Ave, Toronto, ON,, Canada, 1 8137445, clyde.matava@sickkids.ca %K 360-degree video %K VR %K virtual reality %K video production %K anesthetic preparation %K preoperative anxiety %K preoperative preparation %D 2018 %7 16.07.2018 %9 Tutorial %J J Med Internet Res %G English %X This article will provide a framework for producing immersive 360-degree videos for pediatric and adult patients in hospitals. This information may be useful to hospitals across the globe who may wish to produce similar videos for their patients. Advancements in immersive 360-degree technologies have allowed us to produce our own “virtual experience” where our children can prepare for anesthesia by “experiencing” all the sights and sounds of receiving and recovering from an anesthetic. We have shown that health care professionals, children, and their parents find this form of preparation valid, acceptable and fun. Perhaps more importantly, children and parents have self-reported that undertaking our virtual experience has led to a reduction in their anxiety when they go to the operating room. We provide definitions, and technical aspects to assist other health care professionals in the development of low-cost 360-degree videos. %M 30012545 %R 10.2196/jmir.9596 %U http://www.jmir.org/2018/7/e239/ %U https://doi.org/10.2196/jmir.9596 %U http://www.ncbi.nlm.nih.gov/pubmed/30012545 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 20 %N 6 %P e214 %T Tutorial for Using Control Systems Engineering to Optimize Adaptive Mobile Health Interventions %A Hekler,Eric B %A Rivera,Daniel E %A Martin,Cesar A %A Phatak,Sayali S %A Freigoun,Mohammad T %A Korinek,Elizabeth %A Klasnja,Predrag %A Adams,Marc A %A Buman,Matthew P %+ Department of Family Medicine & Public Health, University of California, San Diego, 9500 Gilman Drive, Atkinson Hall (Mail Code 0811, Office 6113), La Jolla, CA, 92093-0811, United States, 1 858 822 7482, ehekler@ucsd.edu %K adaptive interventions %K mHealth %K eHealth %K digital health %K control systems engineering %K behavior change %K optimization %K multiphase optimization strategy %K physical activity %K behavioral maintenance %D 2018 %7 28.06.2018 %9 Tutorial %J J Med Internet Res %G English %X Background: Adaptive behavioral interventions are individualized interventions that vary support based on a person's evolving needs. Digital technologies enable these adaptive interventions to function at scale. Adaptive interventions show great promise for producing better results compared with static interventions related to health outcomes. Our central thesis is that adaptive interventions are more likely to succeed at helping individuals meet and maintain behavioral targets if its elements can be iteratively improved via data-driven testing (ie, optimization). Control systems engineering is a discipline focused on decision making in systems that change over time and has a wealth of methods that could be useful for optimizing adaptive interventions. Objective: The purpose of this paper was to provide an introductory tutorial on when and what to do when using control systems engineering for designing and optimizing adaptive mobile health (mHealth) behavioral interventions. Overview: We start with a review of the need for optimization, building on the multiphase optimization strategy (MOST). We then provide an overview of control systems engineering, followed by attributes of problems that are well matched to control engineering. Key steps in the development and optimization of an adaptive intervention from a control engineering perspective are then summarized, with a focus on why, what, and when to do subtasks in each step. Implications: Control engineering offers exciting opportunities for optimizing individualization and adaptation elements of adaptive interventions. Arguably, the time is now for control systems engineers and behavioral and health scientists to partner to advance interventions that can be individualized, adaptive, and scalable. This tutorial should aid in creating the bridge between these communities. %M 29954725 %R 10.2196/jmir.8622 %U http://www.jmir.org/2018/6/e214/ %U https://doi.org/10.2196/jmir.8622 %U http://www.ncbi.nlm.nih.gov/pubmed/29954725 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 6 %N 8 %P e156 %T Opening the Black Box of Electronic Health: Collecting, Analyzing, and Interpreting Log Data %A Sieverink,Floor %A Kelders,Saskia %A Poel,Mannes %A van Gemert-Pijnen,Lisette %+ Centre for eHealth and Wellbeing Research, Department of Psychology, Health and Technology, University of Twente, P.O. Box 217, Enschede, 7500 AE, Netherlands, 31 628554510, f.sieverink@utwente.nl %K eHealth %K black box %K evaluation %K log data analysis %D 2017 %7 07.08.2017 %9 Tutorial %J JMIR Res Protoc %G English %X In electronic health (eHealth) research, limited insight has been obtained on process outcomes or how the use of technology has contributed to the users’ ability to have a healthier life, improved well-being, or activate new attitudes in their daily tasks. As a result, eHealth is often perceived as a black box. To open this black box of eHealth, methodologies must extend beyond the classic effect evaluations. The analyses of log data (anonymous records of real-time actions performed by each user) can provide continuous and objective insights into the actual usage of the technology. However, the possibilities of log data in eHealth research have not been exploited to their fullest extent. The aim of this paper is to describe how log data can be used to improve the evaluation and understand the use of eHealth technology with a broader approach than only descriptive statistics. This paper serves as a starting point for using log data analysis in eHealth research. Here, we describe what log data is and provide an overview of research questions to evaluate the system, the context, the users of a technology, as well as the underpinning theoretical constructs. We also explain the requirements for log data, the starting points for the data preparation, and methods for data collection. Finally, we describe methods for data analysis and draw a conclusion regarding the importance of the results for both scientific and practical applications. The analysis of log data can be of great value for opening the black box of eHealth. A deliberate log data analysis can give new insights into how the usage of the technology contributes to found effects and can thereby help to improve the persuasiveness and effectiveness of eHealth technology and the underpinning behavioral models. %M 28784592 %R 10.2196/resprot.6452 %U http://www.researchprotocols.org/2017/8/e156/ %U https://doi.org/10.2196/resprot.6452 %U http://www.ncbi.nlm.nih.gov/pubmed/28784592 %0 Journal Article %@ 2291-5222 %I JMIR Publications Inc. %V 4 %N 1 %P e14 %T Guidelines and Recommendations for Developing Interactive eHealth Apps for Complex Messaging in Health Promotion %A Heffernan,Kayla Joanne %A Chang,Shanton %A Maclean,Skye Tamara %A Callegari,Emma Teresa %A Garland,Suzanne Marie %A Reavley,Nicola Jane %A Varigos,George Andrew %A Wark,John Dennis %+ Department of Computing and Information Systems, Melbourne School of Engineering, The University of Melbourne, Doug McDonell Building, The University of Melbourne, Parkville, 3010, Australia, 61 383441500, shanton.chang@unimelb.edu.au %K mhealth %K complex messaging %K vitamin D %K eHealth smartphone apps %K interactive %D 2016 %7 09.02.2016 %9 Original Paper %J JMIR mHealth uHealth %G English %X Background: The now ubiquitous catchphrase, “There’s an app for that,” rings true owing to the growing number of mobile phone apps. In excess of 97,000 eHealth apps are available in major app stores. Yet the effectiveness of these apps varies greatly. While a minority of apps are developed grounded in theory and in conjunction with health care experts, the vast majority are not. This is concerning given the Hippocratic notion of “do no harm.” There is currently no unified formal theory for developing interactive eHealth apps, and development is especially difficult when complex messaging is required, such as in health promotion and prevention. Objective: This paper aims to provide insight into the creation of interactive eHealth apps for complex messaging, by leveraging the Safe-D case study, which involved complex messaging required to guide safe but sufficient UV exposure for vitamin D synthesis in users. We aim to create recommendations for developing interactive eHealth apps for complex messages based on the lessons learned during Safe-D app development. Methods: For this case study we developed an Apple and Android app, both named Safe-D, to safely improve vitamin D status in young women through encouraging safe ultraviolet radiation exposure. The app was developed through participatory action research involving medical and human computer interaction researchers, subject matter expert clinicians, external developers, and target users. The recommendations for development were created from analysis of the development process. Results: By working with clinicians and implementing disparate design examples from the literature, we developed the Safe-D app. From this development process, recommendations for developing interactive eHealth apps for complex messaging were created: (1) involve a multidisciplinary team in the development process, (2) manage complex messages to engage users, and (3) design for interactivity (tailor recommendations, remove barriers to use, design for simplicity). Conclusions: This research has provided principles for developing interactive eHealth apps for complex messaging as guidelines by aggregating existing design concepts and expanding these concepts and new learnings from our development process. A set of guidelines to develop interactive eHealth apps generally, and specifically those for complex messaging, was previously missing from the literature; this research has contributed these principles. Safe-D delivers complex messaging simply, to aid education, and explicitly, considering user safety. %M 26860623 %R 10.2196/mhealth.4423 %U http://mhealth.jmir.org/2016/1/e14/ %U https://doi.org/10.2196/mhealth.4423 %U http://www.ncbi.nlm.nih.gov/pubmed/26860623 %0 Journal Article %@ 1438-8871 %I JMIR Publications Inc. %V 18 %N 1 %P e24 %T Adapting Behavioral Interventions for Social Media Delivery %A Pagoto,Sherry %A Waring,Molly E %A May,Christine N %A Ding,Eric Y %A Kunz,Werner H %A Hayes,Rashelle %A Oleski,Jessica L %+ Department of Medicine, Division of Preventive and Behavioral Medicine, University of Massachusetts Medical School, S7-751, 55 Lake Ave N, Worcester, MA, 01655, United States, 1 508 856 2092, Sherry.Pagoto@umassmed.edu %K social media %K behavioral interventions %K health behavior %K online social networks %D 2016 %7 29.01.2016 %9 Tutorial %J J Med Internet Res %G English %X Patients are increasingly using online social networks (ie, social media) to connect with other patients and health care professionals—a trend called peer-to-peer health care. Because online social networks provide a means for health care professionals to communicate with patients, and for patients to communicate with each other, an opportunity exists to use social media as a modality to deliver behavioral interventions. Social media-delivered behavioral interventions have the potential to reduce the expense of behavioral interventions by eliminating visits, as well as increase our access to patients by becoming embedded in their social media feeds. Trials of online social network-delivered behavioral interventions have shown promise, but much is unknown about intervention development and methodology. In this paper, we discuss the process by which investigators can translate behavioral interventions for social media delivery. We present a model that describes the steps and decision points in this process, including the necessary training and reporting requirements. We also discuss issues pertinent to social media-delivered interventions, including cost, scalability, and privacy. Finally, we identify areas of research that are needed to optimize this emerging behavioral intervention modality. %M 26825969 %R 10.2196/jmir.5086 %U http://www.jmir.org/2016/1/e24/ %U https://doi.org/10.2196/jmir.5086 %U http://www.ncbi.nlm.nih.gov/pubmed/26825969 %0 Journal Article %@ 2291-5222 %I JMIR Publications Inc. %V 3 %N 4 %P e107 %T Developing and Pretesting a Text Messaging Program for Health Behavior Change: Recommended Steps %A Abroms,Lorien C %A Whittaker,Robyn %A Free,Caroline %A Mendel Van Alstyne,Judith %A Schindler-Ruwisch,Jennifer M %+ The Milken Institute School of Public Health, The George Washington University, 950 New Hampshire Avenue NW, 3rd Floor, Washington, DC, 20052, United States, 1 202 994 3518, lorien@gwu.edu %K mHealth %K telemedicine %K SMS %K text messaging %K behavior change %K behavior modification %D 2015 %7 21.12.2015 %9 Original Paper %J JMIR mHealth uHealth %G English %X Background: A growing body of evidence demonstrates that text messaging-based programs (short message service [SMS]) on mobile phones can help people modify health behaviors. Most of these programs have consisted of automated and sometimes interactive text messages that guide a person through the process of behavior change. Objective: This paper provides guidance on how to develop text messaging programs aimed at changing health behaviors. Methods: Based on their collective experience in designing, developing, and evaluating text messaging programs and a review of the literature, the authors drafted the guide. One author initially drafted the guide and the others provided input and review. Results: Steps for developing a text messaging program include conducting formative research for insights into the target audience and health behavior, designing the text messaging program, pretesting the text messaging program concept and messages, and revising the text messaging program. Conclusions: The steps outlined in this guide may help in the development of SMS-based behavior change programs. %M 26690917 %R 10.2196/mhealth.4917 %U http://mhealth.jmir.org/2015/4/e107/ %U https://doi.org/10.2196/mhealth.4917 %U http://www.ncbi.nlm.nih.gov/pubmed/26690917 %0 Journal Article %@ 1438-8871 %I JMIR Publications Inc. %V 17 %N 11 %P e254 %T How to Measure Costs and Benefits of eHealth Interventions: An Overview of Methods and Frameworks %A Bergmo,Trine Strand %+ Norwegian Centre for Integrated Care and Telemedicine, University Hospital of North Norway, Post Box 35, Tromsoe, 9038, Norway, 47 48003565, trine.bergmo@telemed.no %K eHealth %K telemedicine %K telehealth %K telemonitoring %K health economics %K economic evaluation %K cost-benefit analysis %K cost-effectiveness analysis %K cost-utility analysis %K quality-adjusted life years (QALYs) %D 2015 %7 09.11.2015 %9 Tutorial %J J Med Internet Res %G English %X Information on the costs and benefits of eHealth interventions is needed, not only to document value for money and to support decision making in the field, but also to form the basis for developing business models and to facilitate payment systems to support large-scale services. In the absence of solid evidence of its effects, key decision makers may doubt the effectiveness, which, in turn, limits investment in, and the long-term integration of, eHealth services. However, it is not realistic to conduct economic evaluations of all eHealth applications and services in all situations, so we need to be able to generalize from those we do conduct. This implies that we have to select the most appropriate methodology and data collection strategy in order to increase the transferability across evaluations. This paper aims to contribute to the understanding of how to apply economic evaluation methodology in the eHealth field. It provides a brief overview of basic health economics principles and frameworks and discusses some methodological issues and challenges in conducting cost-effectiveness analysis of eHealth interventions. Issues regarding the identification, measurement, and valuation of costs and benefits are outlined. Furthermore, this work describes the established techniques of combining costs and benefits, presents the decision rules for identifying the preferred option, and outlines approaches to data collection strategies. Issues related to transferability and complexity are also discussed. %M 26552360 %R 10.2196/jmir.4521 %U http://www.jmir.org/2015/11/e254/ %U https://doi.org/10.2196/jmir.4521 %U http://www.ncbi.nlm.nih.gov/pubmed/26552360 %0 Journal Article %@ 2291-5222 %I JMIR Publications Inc. %V 3 %N 1 %P e22 %T Translating Behavioral Interventions Onto mHealth Platforms: Developing Text Message Interventions for Smoking and Alcohol %A Bock,Beth C %A Rosen,Rochelle K %A Barnett,Nancy P %A Thind,Herpreet %A Walaska,Kristen %A Foster,Robert %A Deutsch,Christopher %A Traficante,Regina %+ Centers for Behavioral and Preventive Medicine, Alpert Medical School, Brown University, 164 Summit Avenue, Coro West, Suite 1b, Providence, RI, 02903, United States, 1 4017938020, Bbock@lifespan.org %K mHealth %K text message %K smoking cessation %K alcohol %K qualitative methods %D 2015 %7 24.02.2015 %9 Tutorial %J JMIR mHealth uHealth %G English %X The development of mHealth applications is often driven by the investigators and developers with relatively little input from the targeted population. User input is commonly limited to “like/dislike” post- intervention consumer satisfaction ratings or device or application specific user analytics such as usability. However, to produce successful mHealth applications with lasting effects on health behaviors it is crucial to obtain user input from the start of each project and throughout development. The aim of this tutorial is to illustrate how qualitative methods in an iterative process of development have been used in two separate behavior change interventions (targeting smoking and alcohol) delivered through mobile technologies (ie, text messaging). A series of focus groups were conducted to assist in translating a face-to-face smoking cessation intervention onto a text message (short message service, SMS) delivered format. Both focus groups and an advisory panel were used to shape the delivery and content of a text message delivered intervention for alcohol risk reduction. An in vivo method of constructing message content was used to develop text message content that was consistent with the notion of texting as “fingered speech”. Formative research conducted with the target population using a participatory framework led to important changes in our approach to intervention structure, content development, and delivery. Using qualitative methods and an iterative approach that blends consumer-driven and investigator-driven aims can produce paradigm-shifting, novel intervention applications that maximize the likelihood of use by the target audience and their potential impact on health behaviors. %M 25714907 %R 10.2196/mhealth.3779 %U http://mhealth.jmir.org/2015/1/e22/ %U https://doi.org/10.2196/mhealth.3779 %U http://www.ncbi.nlm.nih.gov/pubmed/25714907 %0 Journal Article %@ 1438-8871 %I JMIR Publications Inc. %V 17 %N 1 %P e30 %T The Person-Based Approach to Intervention Development: Application to Digital Health-Related Behavior Change Interventions %A Yardley,Lucy %A Morrison,Leanne %A Bradbury,Katherine %A Muller,Ingrid %+ Department of Psychology, Faculty of Social and Human Sciences, University of Southampton, Department of Psychology, Highfield campus, Southampton, SO17 1BJ, United Kingdom, 44 2380 594581, L.Yardley@soton.ac.uk %K person-based approach %K Internet %K qualitative research %K evaluation studies %K feasibility studies %K health promotion %K patient education %K professional education %K behavior change. %D 2015 %7 30.01.2015 %9 Viewpoint %J J Med Internet Res %G English %X This paper describes an approach that we have evolved for developing successful digital interventions to help people manage their health or illness. We refer to this as the “person-based” approach to highlight the focus on understanding and accommodating the perspectives of the people who will use the intervention. While all intervention designers seek to elicit and incorporate the views of target users in a variety of ways, the person-based approach offers a distinctive and systematic means of addressing the user experience of intended behavior change techniques in particular and can enhance the use of theory-based and evidence-based approaches to intervention development. There are two key elements to the person-based approach. The first is a developmental process involving qualitative research with a wide range of people from the target user populations, carried out at every stage of intervention development, from planning to feasibility testing and implementation. This process goes beyond assessing acceptability, usability, and satisfaction, allowing the intervention designers to build a deep understanding of the psychosocial context of users and their views of the behavioral elements of the intervention. Insights from this process can be used to anticipate and interpret intervention usage and outcomes, and most importantly to modify the intervention to make it more persuasive, feasible, and relevant to users. The second element of the person-based approach is to identify “guiding principles” that can inspire and inform the intervention development by highlighting the distinctive ways that the intervention will address key context-specific behavioral issues. This paper describes how to implement the person-based approach, illustrating the process with examples of the insights gained from our experience of carrying out over a thousand interviews with users, while developing public health and illness management interventions that have proven effective in trials involving tens of thousands of users. %M 25639757 %R 10.2196/jmir.4055 %U http://www.jmir.org/2015/1/e30/ %U https://doi.org/10.2196/jmir.4055 %U http://www.ncbi.nlm.nih.gov/pubmed/25639757 %0 Journal Article %@ 1438-8871 %I JMIR Publications Inc. %V 17 %N 1 %P e28 %T Developing Internet-Based Health Interventions: A Guide for Public Health Researchers and Practitioners %A Horvath,Keith J %A Ecklund,Alexandra M %A Hunt,Shanda L %A Nelson,Toben F %A Toomey,Traci L %+ Division of Epidemiology and Community Health, University of Minnesota, 1300 S. 2nd Street, Suite 300, Minneapolis, MN, 55454, United States, 1 612 626 1799, horva018@umn.edu %K Internet %K public health %K intervention %K development %D 2015 %7 23.01.2015 %9 Original Paper %J J Med Internet Res %G English %X Background: Researchers and practitioners interested in developing online health interventions most often rely on Web-based and print resources to guide them through the process of online intervention development. Although useful for understanding many aspects of best practices for website development, missing from these resources are concrete examples of experiences in online intervention development for health apps from the perspective of those conducting online health interventions. Objective: This study aims to serve as a series of case studies in the development of online health interventions to provide insights for researchers and practitioners who are considering technology-based interventional or programmatic approaches. Methods: A convenience sample of six study coordinators and five principal investigators at a large, US-based land grant university were interviewed about the process of developing online interventions in the areas of alcohol policy, adolescent health, medication adherence, and human immunodeficiency virus prevention in transgender persons and in men who have sex with men. Participants were asked questions that broadly addressed each of the four phases of the User-Centered Design Process Map from the US Department of Health and Human Services' Research-Based Web Design & Usability Guidelines. Interviews were audio recorded and transcribed. Qualitative codes were developed using line-by-line open coding for all transcripts, and all transcripts were coded independently by at least 2 authors. Differences among coders were resolved with discussion. Results: We identified the following seven themes: (1) hire a strong (or at least the right) research team, (2) take time to plan before beginning the design process, (3) recognize that vendors and researchers have differing values, objectives, and language, (4) develop a detailed contract, (5) document all decisions and development activities, (6) use a content management system, and (7) allow extra time for testing and debugging your intervention. Each of these areas is discussed in detail, with supporting quotations from principal investigators and study coordinators. Conclusions: The values held by members of each participating organization involved in the development of the online intervention or program, as well as the objectives that are trying to be met with the website, must be considered. These defined values and objectives should prompt an open and explicit discussion about the scope of work, budget, and other needs from the perspectives of each organization. Because of the complexity of developing online interventions, researchers and practitioners should become familiar with the process and how it may differ from the development and implementation of in-person interventions or programs. To assist with this, the intervention team should consider expanding the team to include experts in computer science or learning technologies, as well as taking advantage of institutional resources that will be needed for successful completion of the project. Finally, we describe the tradeoff between funds available for online intervention or program development and the complexity of the project. %M 25650702 %R 10.2196/jmir.3770 %U http://www.jmir.org/2015/1/e28/ %U https://doi.org/10.2196/jmir.3770 %U http://www.ncbi.nlm.nih.gov/pubmed/25650702 %0 Journal Article %@ 1929-0748 %I JMIR Publications Inc. %V 3 %N 4 %P e75 %T “Real-World” Practical Evaluation Strategies: A Review of Telehealth Evaluation %A Agboola,Stephen %A Hale,Timothy M %A Masters,Caitlin %A Kvedar,Joseph %A Jethwani,Kamal %+ Partners Healthcare Center for Connected Health, Suite 300, 25 New Chardon Street, Boston, MA, 02114, United States, 1 617 643 0291, sagboola@partners.org %K telehealth %K eHealth %K evaluation %K evaluation framework %K diabetes mellitus %K technology %D 2014 %7 17.12.2014 %9 Review %J JMIR Res Protoc %G English %X Background: Currently, the increasing interest in telehealth and significant technological breakthroughs of the past decade create favorable conditions for the widespread adoption of telehealth services. Therefore, expectations are high that telehealth can help alleviate prevailing challenges in health care delivery. However, in order to translate current research to policy and facilitate adoption by patients and health care providers, there is need for compelling evidence of the effectiveness of telehealth interventions. Such evidence is gathered from rigorously designed research studies, which may not always be practical in many real-world settings. Objective: Our aim was to summarize current telehealth evaluation strategies and challenges and to outline practical approaches to conduct evaluation in real-world settings using one of our previously reported telehealth initiatives, the Diabetes Connect program, as a case study. Methods: We reviewed commonly used current evaluation frameworks and strategies, as well as best practices based on successful evaluative efforts to date to address commonly encountered challenges in telehealth evaluation. These challenges in telehealth evaluation and commonly used frameworks are described relevant to the evaluation of Diabetes Connect, a 12-month Web-based blood glucose monitoring program. Results: Designers of telehealth evaluation frameworks must give careful consideration to the elements of planning, implementation, and impact assessment of interventions. Evaluating performance at each of these phases is critical to the overall success of an intervention. Although impact assessment occurs at the end of a program, our review shows that it should begin at the point of problem definition. Critical to the success of an evaluative strategy is early planning that involves all stakeholders to identify the overall goals of the program and key measures of success at each phase of the program life cycle. This strategy should enable selection of an appropriate evaluation strategy and measures to aid in the ongoing development and implementation of telehealth and provide better evidence of program impact. Conclusions: We recommend a pragmatic, multi-method, multi-phase approach to telehealth evaluation that is flexible and can be adapted to the characteristics and challenges unique to each telehealth program. %M 25524892 %R 10.2196/resprot.3459 %U http://www.researchprotocols.org/2014/4/e75/ %U https://doi.org/10.2196/resprot.3459 %U http://www.ncbi.nlm.nih.gov/pubmed/25524892 %0 Journal Article %@ 2291-5222 %I JMIR Publications Inc. %V 2 %N 4 %P e53 %T Enabling Psychiatrists to be Mobile Phone App Developers: Insights Into App Development Methodologies %A Zhang,Melvyn WB %A Tsang,Tammy %A Cheow,Enquan %A Ho,Cyrus SH %A Yeong,Ng Beng %A Ho,Roger CM %+ National Healthcare Group, 10 Buangkok Green Medical Park, Singapore, 539747, Singapore, 65 63892000, melvynzhangweibin@gmail.com %K smartphone application %K mobile application %K creation %D 2014 %7 11.11.2014 %9 Original Paper %J JMIR mHealth uHealth %G English %X Background: The use of mobile phones, and specifically smartphones, in the last decade has become more and more prevalent. The latest mobile phones are equipped with comprehensive features that can be used in health care, such as providing rapid access to up-to-date evidence-based information, provision of instant communications, and improvements in organization. The estimated number of health care apps for mobile phones is increasing tremendously, but previous research has highlighted the lack of critical appraisal of new apps. This lack of appraisal of apps has largely been due to the lack of clinicians with technical knowledge of how to create an evidence-based app. Objective: We discuss two freely available methodologies for developing Web-based mobile phone apps: a website builder and an app builder. With these, users can program not just a Web-based app, but also integrate multimedia features within their app, without needing to know any programming language. Methods: We present techniques for creating a mobile Web-based app using two well-established online mobile app websites. We illustrate how to integrate text-based content within the app, as well as integration of interactive videos and rich site summary (RSS) feed information. We will also briefly discuss how to integrate a simple questionnaire survey into the mobile-based app. A questionnaire survey was administered to students to collate their perceptions towards the app. Results: These two methodologies for developing apps have been used to convert an online electronic psychiatry textbook into two Web-based mobile phone apps for medical students rotating through psychiatry in Singapore. Since the inception of our mobile Web-based app, a total of 21,991 unique users have used the mobile app and online portal provided by WordPress, and another 717 users have accessed the app via a Web-based link. The user perspective survey results (n=185) showed that a high proportion of students valued the textbook and objective structured clinical examination videos featured in the app. A high proportion of students concurred that a self-designed mobile phone app would be helpful for psychiatry education. Conclusions: These methodologies can enable busy clinicians to develop simple mobile Web-based apps for academic, educational, and research purposes, without any prior knowledge of programming. This will be beneficial for both clinicians and users at large, as there will then be more evidence-based mobile phone apps, or at least apps that have been appraised by a clinician. %M 25486985 %R 10.2196/mhealth.3425 %U http://mhealth.jmir.org/2014/4/e53/ %U https://doi.org/10.2196/mhealth.3425 %U http://www.ncbi.nlm.nih.gov/pubmed/25486985 %0 Journal Article %@ 1438-8871 %I Gunther Eysenbach %V 15 %N 3 %P e63 %T Storing and Using Health Data in a Virtual Private Cloud %A Regola,Nathan %A Chawla,Nitesh V %+ Interdisciplinary Center for Network Science and Applications, Department of Computer Science and Engineering, University of Notre Dame, 384 Fitzpatrick Hall, Notre Dame, IN, 46556, United States, 1 574 631 1090, nchawla@nd.edu %K medical informatics %K HIPAA %D 2013 %7 13.03.2013 %9 Original Paper %J J Med Internet Res %G English %X Electronic health records are being adopted at a rapid rate due to increased funding from the US federal government. Health data provide the opportunity to identify possible improvements in health care delivery by applying data mining and statistical methods to the data and will also enable a wide variety of new applications that will be meaningful to patients and medical professionals. Researchers are often granted access to health care data to assist in the data mining process, but HIPAA regulations mandate comprehensive safeguards to protect the data. Often universities (and presumably other research organizations) have an enterprise information technology infrastructure and a research infrastructure. Unfortunately, both of these infrastructures are generally not appropriate for sensitive research data such as HIPAA, as they require special accommodations on the part of the enterprise information technology (or increased security on the part of the research computing environment). Cloud computing, which is a concept that allows organizations to build complex infrastructures on leased resources, is rapidly evolving to the point that it is possible to build sophisticated network architectures with advanced security capabilities. We present a prototype infrastructure in Amazon’s Virtual Private Cloud to allow researchers and practitioners to utilize the data in a HIPAA-compliant environment. %M 23485880 %R 10.2196/jmir.2076 %U http://www.jmir.org/2013/3/e63/ %U https://doi.org/10.2196/jmir.2076 %U http://www.ncbi.nlm.nih.gov/pubmed/23485880