Search Articles

View query in Help articles search

Search Results (1 to 10 of 57 Results)

Download search results: CSV END BibTex RIS

CSV download: Download all 57 search results (up to 5,000 articles maximum)

The Right to Explanation in AI: In a Lonely Place

The Right to Explanation in AI: In a Lonely Place

This has brought about a variety of methods used to explain automation, resulting in further ambiguities in what constitutes an explanation [34]. Surprisingly, the elements of a good explanation are not well defined. Instead, many guidelines exist outlining what an explanation should contain. As a result of this varying guidance, there are different ways to categorize explanations.

Alycia Noë, Sarah Bouhouita-Guermech, Ma'n H Zawati

J Med Internet Res 2025;27:e64482


Design of an Automated Mobile Phone-Based Reminder and Incentive System: Application in a Quasi-Randomized Controlled Trial to Improve the Timeliness of Childhood Vaccinations in Tanzania

Design of an Automated Mobile Phone-Based Reminder and Incentive System: Application in a Quasi-Randomized Controlled Trial to Improve the Timeliness of Childhood Vaccinations in Tanzania

Iterative adaptations to m Paris in response to stochastic environmental and technical implementation barriers resulted in the formation of a robust m Health system that is locally hosted in a low-resource setting, but readily extensible to other geographic and topical contexts, including high-resource settings. m Paris’ open-source nature, auditability, and ability to autonomously execute algorithms in the face of diverse challenges suggest favorable prospects for the automation of critical health communication

Marco van Zwetselaar, Jan Ostermann, Melkiory Beti, Joy Noel Baumgartner, Sayoki Mfinanga, Esther Ngadaya, Lavanya Vasudevan, Nathan Thielman

JMIR Form Res 2025;9:e65150


“Digital Clinicians” Performing Obesity Medication Self-Injection Education: Feasibility Randomized Controlled Trial

“Digital Clinicians” Performing Obesity Medication Self-Injection Education: Feasibility Randomized Controlled Trial

Automation may offer benefits in standardization, efficiency, effectiveness, cost, confidentiality, and access. Social desirability response bias is associated with higher levels of treatment nonadherence [25] and reduces the accuracy of clinical history taking [26] in human-human interactions. In educational settings, certain interactions, such as quizzing, enhance information retention but may be more socially appropriate from a “digital clinician” than from a health care professional.

Sean Coleman, Caitríona Lynch, Hemendra Worlikar, Emily Kelly, Kate Loveys, Andrew J Simpkin, Jane C Walsh, Elizabeth Broadbent, Francis M Finucane, Derek O' Keeffe

JMIR Diabetes 2025;10:e63503


Leveraging AI to Optimize Maintenance of Health Evidence and Offer a One-Stop Shop for Quality-Appraised Evidence Syntheses on the Effectiveness of Public Health Interventions: Quality Improvement Project

Leveraging AI to Optimize Maintenance of Health Evidence and Offer a One-Stop Shop for Quality-Appraised Evidence Syntheses on the Effectiveness of Public Health Interventions: Quality Improvement Project

AI commonly refers to the interdisciplinary study and development of models engineered to perform varied levels of automation that would typically require human intelligence [16,17]. Machine learning is a subset of AI that involves algorithms that autonomously learn patterns from the data they are trained on without being explicitly programmed [16].

Kristin Rogers, Alanna Miller, Ashley Girgis, Emily C Clark, Sarah E Neil-Sztramko, Maureen Dobbins

J Med Internet Res 2025;27:e69700


Advancing Clinical Chatbot Validation Using AI-Powered Evaluation With a New 3-Bot Evaluation System: Instrument Validation Study

Advancing Clinical Chatbot Validation Using AI-Powered Evaluation With a New 3-Bot Evaluation System: Instrument Validation Study

Artificial intelligence (AI) automation in low- to mid-level tasks like patient education and initial therapy screening emerges as a strategic response to mitigate this shortage, reallocating medical staff to higher-priority tasks [2,3]. The advent of advanced multimodal large language models (LLMs) such as GPT-4 introduces a paradigm shift, promising scalable, cost-effective chatbot solutions, which are particularly helpful for tasks that require the provider to interact with the patient [4].

Seungheon Choo, Suyoung Yoo, Kumiko Endo, Bao Truong, Meong Hi Son

JMIR Nursing 2025;8:e63058


Automated Process for Monitoring of Amiodarone Treatment: Development and Evaluation

Automated Process for Monitoring of Amiodarone Treatment: Development and Evaluation

In this study, we present a model for the automation of repetitive follow-up of patients with amiodarone treatment. First, we constructed an automated solution including the whole surveillance process, using a robotic process automation (RPA) software tool. We then compared the RPA to standard manual amiodarone follow-up as presently practiced.

Birgitta I Johansson, Jonas Landahl, Karin Tammelin, Erik Aerts, Christina E Lundberg, Martin Adiels, Martin Lindgren, Annika Rosengren, Nikolaos Papachrysos, Helena Filipsson Nyström, Helen Sjöland

J Med Internet Res 2025;27:e65473


The Effects of Presenting AI Uncertainty Information on Pharmacists’ Trust in Automated Pill Recognition Technology: Exploratory Mixed Subjects Study

The Effects of Presenting AI Uncertainty Information on Pharmacists’ Trust in Automated Pill Recognition Technology: Exploratory Mixed Subjects Study

Trust in automation, defined as “the attitude that an agent will help achieve an individual’s goals in situations characterized by uncertainty and vulnerability” [26], is one of the most crucial factors determining the use of automation [27,28]. There is a growing body of research examining people’s trust in autonomous and robotic technologies in various domains, including transportation [29-31], health care [32,33], education [34], and defense [35,36].

Jin Yong Kim, Vincent D Marshall, Brigid Rowell, Qiyuan Chen, Yifan Zheng, John D Lee, Raed Al Kontar, Corey Lester, Xi Jessie Yang

JMIR Hum Factors 2025;12:e60273