JMIR Formative Research

View query in Help articles search

Field

e.g. mhealth

Operator

Field

Criteria

e.g. John Smith or 0000-0001-6479-5330

Exact Match for Criteria

Yes No

Search Results (1 to 10 of 1778 Results)

Download search results: CSV END BibTex RIS

Sort by:

ChatGPT-Assisted Deep Learning Models for Influenza-Like Illness Prediction in Mainland China: Time Series Analysis

The TFT model was used to predict ILI positive rates, using its hybrid structure that merges recurrent neural networks with attention mechanisms to grasp both short-term and long-term patterns.

Weihong Huang, Wudi Wei, Xiaotao He, Baili Zhan, Xiaoting Xie, Meng Zhang, Shiyi Lai, Zongxiang Yuan, Jingzhen Lai, Rongfeng Chen, Junjun Jiang, Li Ye, Hao Liang

J Med Internet Res 2025;27:e74423

Download Citation: END BibTex RIS

Download PDF Download XML

A Responsible Framework for Assessing, Selecting, and Explaining Machine Learning Models in Cardiovascular Disease Outcomes Among People With Type 2 Diabetes: Methodology and Validation Study

Yang Yang, Che-Yi Liao, Esmaeil Keyvanshokooh, Hui Shao, Mary Beth Weber, Francisco J Pasquel, Gian-Gabriel P Garcia

JMIR Med Inform 2025;13:e66200

Download Citation: END BibTex RIS

Download PDF Download XML

Examining the Impact of Digital Inclusion on Depression Among Older Adults in China: Mediating Role of Noncognitive Abilities

Integrating Yang and Chu’s [28] digital literacy framework with the media intervention model of Chen et al [38], we pioneer evidence of their mediating role in holistic digital inclusion. Digital engagement enhances psychological resilience through three pathways: remodeling social interactions, optimizing learning strategies, and diversifying recreational activities.

Xinru Li, Chengyu Chen, Xiyan Li, Yuyang Li, Shujuan Xiao, Jianan Han, Yanan Wang, Chichen Zhang

J Med Internet Res 2025;27:e71441

Download Citation: END BibTex RIS

Download PDF Download XML

Associations Among Minority Stress, Allostatic Load, and Drug and Alcohol Use in Sexual Minorities: Protocol for the Queer Health Study—a Longitudinal Feasibility Evaluation

In addition, we will track how long it takes to recruit the sample and calculate the proportion of missing data, usable biomarker data, participants eligible after screening, participants consented, and participants retained at each time point. Drug and alcohol abuse consequences will be assessed via the Drug Abuse Screening Test (DAST-10) [41] and the Alcohol Use Disorders Identification Test (AUDIT) [42]. Depression will be measured by the Center for Epidemiological Studies Depression Scale [43].

Nathan Grant Smith, Tzuan A Chen, Robert-Paul Juster, Ezemenari M Obasi, Jacob S Crocker

JMIR Res Protoc 2025;14:e73070

Download Citation: END BibTex RIS

Download PDF Download XML

The Digital Library of Health Care Consultations and Simulated Health Care Student Teaching: Protocol for a Repository of Recordings to Support Communication Research

Health care consumer surveys (pre- and postconsultation): Health care consumers will be asked to complete a survey before their consultation detailing their demographics, reason for visit, and how long they have known the clinician. Post consultation, they will be asked to complete a survey detailing their consultation experience, including whether they felt respected, felt listened to, and had enough time (Multimedia Appendix 1).

Elizabeth Ann Sturgiss, Kimberley Norman, Terry Haines, Katrina Long, Suzanne Nielsen, Jenny Sim, Aron Shlonsky, Brendan Shannon, Cylie Williams

JMIR Res Protoc 2025;14:e67910

Download Citation: END BibTex RIS

Download PDF Download XML

Exploring the Potential of Electroencephalography Signal–Based Image Generation Using Diffusion Models: Integrative Framework Combining Mixed Methods and Multimodal Analysis

Later, EEG-GAN [18] introduced the first EEG-based image generation model using long short-term memory [24] to extract EEG features and guide the GAN’s image generation process. Several works based on GANs, such as Thought Viz [25], visual-guided GAN with visual-consistent term [26], Brain Media [27], and EEG2 IMAGE [16], have emerged, each focusing on improving the interaction between the EEG encoder and the GAN architecture.

Chi-Sheng Chen, Shao-Hsuan Chang, Che-Wei Liu, Tung-Ming Pan

JMIR Med Inform 2025;13:e72027

Download Citation: END BibTex RIS

Download PDF Download XML

Large Language Model–Assisted Risk-of-Bias Assessment in Randomized Controlled Trials Using the Revised Risk-of-Bias Tool: Usability Study

All reviewers completed a week-long training on systematic reviews to ensure a consistent understanding of Ro B2. Three reviewers (WZ, DX, and CB) initially conducted independent judgments of 46 RCTs using standardized criteria, recording the time taken for the judgments. All results were resolved through consensus. We randomly selected 3 evaluation results from each category to construct the prompt, which were used as benchmarks to assess the accuracy of the answers generated by the LLMs.

Jiajie Huang, Honghao Lai, Weilong Zhao, Danni Xia, Chunyang Bai, Mingyao Sun, Jianing Liu, Jiayi Liu, Bei Pan, Jinhui Tian, Long Ge

J Med Internet Res 2025;27:e70450

Download Citation: END BibTex RIS

Download PDF Download XML

Wearable Technologies for Health Promotion and Disease Prevention in Older Adults: Systematic Scoping Review and Evidence Map

Table 3 presents the key characteristics of machine learning techniques in research studies, including tree-based models (decision tree, random forest, and gradient boosting), linear models, deep learning neural networks, multilayer perceptrons, long short-term memory networks, and convolutional neural networks). K-nearest neighbors, support vector machines, and others. Machine learning techniques research work for wearable sensors. Handles high-dimensional data. Robust to noisy data.

Yue Sun, Ji Chen, Mengmeng Ji, Xiaomei Li

J Med Internet Res 2025;27:e69077

Download Citation: END BibTex RIS

Download PDF Download XML