Search Articles

View query in Help articles search

Search Results (1 to 10 of 1579 Results)

Download search results: CSV END BibTex RIS


Acoustic Features for Identifying Suicide Risk in Crisis Hotline Callers: Machine Learning Approach

Acoustic Features for Identifying Suicide Risk in Crisis Hotline Callers: Machine Learning Approach

Now these acoustic changes can be well captured using acoustic speech features [11]. Moreover, with the development of artificial intelligence technologies such as machine learning, it is possible to analyze highly complex patterns in acoustic features [12]. Using artificial intelligence to automatically analyze features can help us move from a clinical practice model that relies solely on clinician judgment to an evidence-based medicine model based on data measurements [13].

Zhengyuan Su, Huadong Jiang, Ying Yang, Xiangqing Hou, Yanli Su, Li Yang

J Med Internet Res 2025;27:e67772

Approach to Design and Evaluate Digital Tools to Enhance Young Adult Participation in Clinical Trials: Co-Design and Controlled Intercept Study

Approach to Design and Evaluate Digital Tools to Enhance Young Adult Participation in Clinical Trials: Co-Design and Controlled Intercept Study

Follow-up initial usability testing with focus groups that evaluated the digital tools suggested that mobile apps and websites can be designed to increase interest in participating in clinical trials. A total of 351 respondents participated in the intercept study. The sample was 63.9% (223/351) female.

Tim Mackey, Raphael E Cuomo, Qing Xu, Tiana J McMann, Zhuoran Li, Mingxiang Cai, Christine Wenzel, Joshua S Yang

J Med Internet Res 2025;27:e70852

Identifying Intersecting Factors Associated With Suicidal Thoughts and Behaviors Among Transgender and Gender Diverse Adults: Preliminary Conditional Inference Tree Analysis

Identifying Intersecting Factors Associated With Suicidal Thoughts and Behaviors Among Transgender and Gender Diverse Adults: Preliminary Conditional Inference Tree Analysis

Importantly, conditional inference trees can highlight potential statistical predictors for between-group differences (eg, poverty as an additional intersectional factor for younger individuals experiencing SI). This is advantageous for intersectionality research, because our goal is not only to uncover subgroups that explain the heterogeneity in STBs but also to understand the factors associated with the heterogeneity.

Amelia M Stanton, Lauren A Trichtinger, Norik Kirakosian, Simon M Li, Katherine E Kabel, Kiyan Irani, Alexandra H Bettis, Conall O’Cleirigh, Richard T Liu, Qimin Liu

J Med Internet Res 2025;27:e65452

Sociodemographic Differences in Logins and Engagement With the Electronic Health Coach Messaging Feature of a Mobile App to Support Opioid and Stimulant Use Recovery: Results From a 1-Month Observational Study

Sociodemographic Differences in Logins and Engagement With the Electronic Health Coach Messaging Feature of a Mobile App to Support Opioid and Stimulant Use Recovery: Results From a 1-Month Observational Study

Yet, existing findings suggest uptake and engagement with m Health apps can vary dramatically [5,15]. Moreover, data on the efficacy, acceptability, and utilization of distinct app features is often lacking, thereby limiting our ability to understand what works for whom, when, and under what settings; importantly, this also limits our understanding of which groups of individuals are missed by unique m Health strategies [16-18].

Lindsey M Filiatreau, Hannah Szlyk, Alex T Ramsey, Erin Kasson, Xiao Li, Zhuoran Zhang, Patricia Cavazos-Rehg

JMIR Mhealth Uhealth 2025;13:e54753

Evolutionary Trend of Dental Health Care Information on Chinese Social Media Platforms During 2018-2022: Retrospective Observational Study

Evolutionary Trend of Dental Health Care Information on Chinese Social Media Platforms During 2018-2022: Retrospective Observational Study

Another burgeoning branch, sentiment analysis tools, can be used for public opinion analysis, such as epidemic trends [20], willingness for vaccination [10], and even presidential elections [21]. Since the emergence of Chat Generative Pretrained Transformer (Chat GPT), it has also been applied to social media research, such as popular hashtag generation algorithms [22] and the construction of lexica for online pharmacovigilance [23].

Zhiyu Zhu, Zhiyun Ye, Qian Wang, Ruomei Li, Hairui Li, Weiming Guo, Zhenxia Li, Lunguo Xia, Bing Fang

JMIR Infodemiology 2025;5:e55065

Effectiveness of Telemedicine-Delivered Carbohydrate-Counting Interventions in Patients With Type 1 Diabetes: Systematic Review and Meta-Analysis

Effectiveness of Telemedicine-Delivered Carbohydrate-Counting Interventions in Patients With Type 1 Diabetes: Systematic Review and Meta-Analysis

TM can be classified based on the communication method (text, video, or audio), communication time (synchronous or asynchronous), the purpose of the consultation (initial consultation or follow-up consultation), and participants in the remote consultation (patient-to-doctor, caregiver-to-doctor, doctor-to-doctor, or health care worker-to-doctor) [14]. In chronic disease management, particularly diabetes, the integration of TM technology with medical professionals has yielded remarkable results [15].

Yang Li, Yue Yang, Xiaoqin Liu, Xinting Zhang, Fei Li

J Med Internet Res 2025;27:e59579

Factors Influencing Information Distortion in Electronic Nursing Records: Qualitative Study

Factors Influencing Information Distortion in Electronic Nursing Records: Qualitative Study

Specific work habits can contribute to information distortion. Many nurses use the copy-and-paste function to enhance work efficiency. Some nurses prefer to copy records from the previous shifts then adjust them after completing their nursing activities. However, this habit can lead to forgetting to make the necessary adjustments, resulting in identical records across shifts. Additionally, when nurses do not take the time to review their records, errors may go unnoticed.

Jianan Wang, Yihong Xu, Zhichao Yang, Jie Zhang, Xiaoxiao Zhang, Wen Li, Yushu Sun, Hongying Pan

J Med Internet Res 2025;27:e66959

Digital Decision Support for Perioperative Care of Patients With Type 2 Diabetes: A Call to Action

Digital Decision Support for Perioperative Care of Patients With Type 2 Diabetes: A Call to Action

It can result in severe metabolic and organ dysfunction, exacerbate organ damage, trigger various disorders, increase infection risk, and even lead to postoperative death [5]. Although optimal glycemic control significantly improves postoperative outcomes in patients with diabetes, particularly in mitigating the risk of infection [6], there have long been obstacles regarding achieving the ideal method for managing blood glucose levels.

Jianwen Cai, Peiyi Li, Weimin Li, Xuechao Hao, Sheyu Li, Tao Zhu

JMIR Diabetes 2025;10:e70475

Investigating Clinicians’ Intentions and Influencing Factors for Using an Intelligence-Enabled Diagnostic Clinical Decision Support System in Health Care Systems: Cross-Sectional Survey

Investigating Clinicians’ Intentions and Influencing Factors for Using an Intelligence-Enabled Diagnostic Clinical Decision Support System in Health Care Systems: Cross-Sectional Survey

Therefore, the TTF model can serve as a precursor factor influencing perceived ease of use. Based on this rationale, this study selected the core variable of “perceived ease of use” from the TAM. Given the complexity and constant evolution of AI, it has yet to become a cornerstone of the health care system or medical education.

Rui Zheng, Xiao Jiang, Li Shen, Tianrui He, Mengting Ji, Xingyi Li, Guangjun Yu

J Med Internet Res 2025;27:e62732