e.g. mhealth
Search Results (1 to 10 of 28 Results)
Download search results: CSV END BibTex RIS
Skip search results from other journals and go to results- 8 JMIR Medical Informatics
- 8 Journal of Medical Internet Research
- 3 JMIR AI
- 3 JMIR Formative Research
- 2 JMIR mHealth and uHealth
- 1 JMIR Cancer
- 1 JMIR Data
- 1 JMIR Public Health and Surveillance
- 1 JMIR Research Protocols
- 0 Medicine 2.0
- 0 Interactive Journal of Medical Research
- 0 iProceedings
- 0 JMIR Human Factors
- 0 JMIR Serious Games
- 0 JMIR Mental Health
- 0 JMIR Rehabilitation and Assistive Technologies
- 0 JMIR Preprints
- 0 JMIR Bioinformatics and Biotechnology
- 0 JMIR Medical Education
- 0 JMIR Challenges
- 0 JMIR Diabetes
- 0 JMIR Biomedical Engineering
- 0 JMIR Cardio
- 0 Journal of Participatory Medicine
- 0 JMIR Dermatology
- 0 JMIR Pediatrics and Parenting
- 0 JMIR Aging
- 0 JMIR Perioperative Medicine
- 0 JMIR Nursing
- 0 JMIRx Med
- 0 JMIRx Bio
- 0 JMIR Infodemiology
- 0 Transfer Hub (manuscript eXchange)
- 0 JMIR Neurotechnology
- 0 Asian/Pacific Island Nursing Journal
- 0 Online Journal of Public Health Informatics
- 0 JMIR XR and Spatial Computing (JMXR)
These preprocessing steps ensured the creation of a high-quality robust dataset for training deep learning models to predict clinical deterioration from chest radiographs.
For the prediction task, computer vision deep learning models were trained and optimized with the dataset created from the cohort. Five publicly available computer vision models were compared for our task: (1) VGG16 [24], (2) Dense Net121 [25], (3) Vision Transformer [26], (4) Res Net50 [27], and (5) Inception V3 [28].
JMIR AI 2025;4:e67144
Download Citation: END BibTex RIS
The AI Reviewer: Evaluating AI’s Role in Citation Screening for Streamlined Systematic Reviews
We conducted a pilot feasibility study evaluating 5 distinct LLMs in an existing systematic review dataset.
We compared 5 commonly used LLMs to screen citations from a previously published systematic review on trauma hemorrhage, originally screened by two human reviewers [5]. Of the 1186 total citations, 21 (1.8%) were included for full-text review and 1165 (98.2%) were excluded. We randomly selected 100 excluded citations using Microsoft Excel.
JMIR Form Res 2025;9:e58366
Download Citation: END BibTex RIS
Using Wear Time for the Analysis of Consumer-Grade Wearables’ Data: Case Study Using Fitbit Data
Dataset details.
The details of this study protocol can be found in Carlozzi et al [18]. Briefly, caregivers for persons with Huntington disease (HD), spinal cord injury (SCI), and hematopoietic cell transplantation (HCT) from different clinics at the University of Michigan were recruited between November 2020 and June 2021. This study’s objective was to evaluate a just-in-time adaptive intervention to promote caregivers’ self-care.
JMIR Mhealth Uhealth 2025;13:e46149
Download Citation: END BibTex RIS
As there is currently no Chinese dataset for sentence-level classification in the medical abstract field, in this step, we used Open AI’s text generation model, GPT-3.5, to generate 3 types of small synthetic datasets, which only contain around 15,000 sentences each yet still perform well on classification tasks. The first one is the translated Pub Med dataset, which is translated into Chinese from the Pub Med 200k RCT dataset by Deep L [28], and we choose 15,000 sentences with clear labels as dataset #1.
JMIR Form Res 2025;9:e54803
Download Citation: END BibTex RIS
The workflow of the proposed Med Scale NER prompt framework is illustrated in Figure 1 and consists of three main stages: dataset preparation and annotation, design and implementation of the Med Scale NER framework, and in-depth evaluation and comparison. The process begins with the collection of high-quality Chinese journal papers focused on medical scales.
J Med Internet Res 2025;27:e67033
Download Citation: END BibTex RIS
A trial’s original dataset, with N number of patients, was first reduced by r. The variable r signifies the fraction of the last patients who were deliberately removed from the input dataset. This results in a reduced dataset with “(1-r) N” patients. In practice, the reduced dataset represents a poorly accruing clinical trial that needs to be rescued. The shaded area outlines the typical steps taken by a practitioner during the implementation process.
J Med Internet Res 2025;27:e66821
Download Citation: END BibTex RIS
The selected number of topics (T) were extracted from a collective dataset (C). Probability (Pi) of inclusion of individual posts (Ci) from the dataset can be represented as:
Our topic models generated a topic matrix and the likelihood of individual topic strength. The bag of words constructed within the matrix can be designated as n-grams. In our case, a bigram model was selected due to its popularity in strengthening topic cohesion and topic relevance.
J Med Internet Res 2025;27:e58656
Download Citation: END BibTex RIS
Mental health term categories: recall, F1-score, total mentions in the dataset, and most common misclassification (in descending order of recall). Categories with
a Recall indicates the proportion of terms in a clinician-coded category that were classified by the model as belonging to that category.
b ADHD: attention deficit hyperactive disorder.
c OCD: obsessive compulsive disorder.
dpsych ADE: psychiatric adverse drugs events.
JMIR Med Inform 2025;13:e65454
Download Citation: END BibTex RIS
If this action date does not appear in the dataset of ARRIVED appointments, then the count of unresolved cases is increased by 1. Resolution complexity is then computed as the ratio of unresolved counts to the total count of AIDs within the NONARRIVED group. Location complexity is calculated as the number of arrived dates in ARRIVED involving 2 or most different locations divided by the total number of arrived dates in ARRIVED.
JMIR Cancer 2025;11:e57715
Download Citation: END BibTex RIS
For this, we used a simple questionnaire to request information from departments on the location of the dataset, the individual data fields collected, the purpose of the data, and how and where it is stored (Multimedia Appendix 1).
This study did not access any individual patient data, and as such, ethical approval was not required. The study was undertaken under a Service Evaluation agreement with the Lancashire Teaching Hospitals NHS Foundation Trust (Service Evaluation Ref: 427).
JMIR Med Inform 2024;12:e60017
Download Citation: END BibTex RIS