Search Articles

View query in Help articles search

Search Results (1 to 10 of 252 Results)

Download search results: CSV END BibTex RIS


Guideline-Incorporated Large Language Model-Driven Evaluation of Medical Records Using MedCheckLLM

Guideline-Incorporated Large Language Model-Driven Evaluation of Medical Records Using MedCheckLLM

One underexplored area is their application for the reliable evaluation of medical documents. The automated evaluation of these documents has the potential to enhance patient safety. The system’s reasoning process must be (1) transparent and comprehensible to human evaluators and (2) guided by established medical guidelines proven to increase patient safety [3].

Marc Cicero Schubert, Stella Soyka, Wolfgang Wick, Varun Venkataramani

JMIR Form Res 2025;9:e53335

Application of an Innovative Methodology to Build Infrastructure for Digital Transformation of Health Systems: Developmental Program Evaluation

Application of an Innovative Methodology to Build Infrastructure for Digital Transformation of Health Systems: Developmental Program Evaluation

A developmental evaluation is utilization focused and should be designed and implemented in ways that maximize utility for the primary intended users [46]. This evaluation approach generates data and findings in near real time, thereby facilitating developmental decision-making and course corrections throughout the development process [44,47]. This evaluation was guided by the following overarching evaluation questions: What factors influenced the CO-Away digital health platform development?

M Claire Buchan, Tarun Reddy Katapally, Jasmin Bhawra

JMIR Form Res 2025;9:e53339

Automatic Human Embryo Volume Measurement in First Trimester Ultrasound From the Rotterdam Periconception Cohort: Quantitative and Qualitative Evaluation of Artificial Intelligence

Automatic Human Embryo Volume Measurement in First Trimester Ultrasound From the Rotterdam Periconception Cohort: Quantitative and Qualitative Evaluation of Artificial Intelligence

This dual evaluation highlights the novelty of our work, offering insights into the reliability and efficiency of AI-based segmentation in clinical workflows. The data used for this study was collected within the Rotterdam Periconception Cohort (Predict Study).

Wietske A P Bastiaansen, Stefan Klein, Batoul Hojeij, Eleonora Rubini, Anton H J Koning, Wiro Niessen, Régine P M Steegers-Theunissen, Melek Rousian

J Med Internet Res 2025;27:e60887

Development and Impact of a Community-Delivered, Multisectoral Lifestyle Management Service for People Living With Type 2 Diabetes (Logan Healthy Living): Protocol for a Pragmatic, Single-Arm Intervention Study

Development and Impact of a Community-Delivered, Multisectoral Lifestyle Management Service for People Living With Type 2 Diabetes (Logan Healthy Living): Protocol for a Pragmatic, Single-Arm Intervention Study

To simultaneously support reporting for the outcome-based funding model and evaluate the real-world impact of a routinely delivered community program, a comprehensive continuous evaluation protocol informed by the RE-AIM framework was developed. The purpose of this paper is to describe the development of Logan Healthy Living and the protocol for program evaluation of this allied health care service.

Sjaan R Gomersall, Denis Y Giguere, Jacqueline Cotugno, Joanna Munro, Wallis J Westbrook, Robyn Littlewood, John Cairney, Elisabeth AH Winkler, Phillip M van der Vliet, Ana D Goode, Tahlia Alsop, Genevieve Nissa Healy

JMIR Res Protoc 2025;14:e69477

ChatGPT’s Performance on Portuguese Medical Examination Questions: Comparative Analysis of ChatGPT-3.5 Turbo and ChatGPT-4o Mini

ChatGPT’s Performance on Portuguese Medical Examination Questions: Comparative Analysis of ChatGPT-3.5 Turbo and ChatGPT-4o Mini

This study has several limitations regarding the performance evaluation of Chat GPT-3.5 Turbo and Chat GPT-4o mini. The analysis was based solely on Chat GPT’s indication of the correct answer, which, while aligning with expectations for human candidates, does not consider other aspects of examination performance. Additionally, the grading did not account for the complexity or length of the questions, providing an incomplete assessment of the models’ performance.

Filipe Prazeres

JMIR Med Educ 2025;11:e65108

Large Language Models’ Accuracy in Emulating Human Experts’ Evaluation of Public Sentiments about Heated Tobacco Products on Social Media: Evaluation Study

Large Language Models’ Accuracy in Emulating Human Experts’ Evaluation of Public Sentiments about Heated Tobacco Products on Social Media: Evaluation Study

This approach stems from the time-consuming and labor-intensive nature of human sentiment evaluation, which involves recruiting, training, and coordinating multiple evaluators. This complexity arises from the fact that latent coding, including sentiment analysis, requires understanding the underlying meanings and subtleties in the text, which can substantially vary depending on the context and across coders [15].

Kwanho Kim, Soojong Kim

J Med Internet Res 2025;27:e63631

A Digital Pornography Education Prototype Co-Designed With Young People: Formative Evaluation

A Digital Pornography Education Prototype Co-Designed With Young People: Formative Evaluation

Here, we describe a formative evaluation of The Gist prototype, an evaluation designed to pretest a program with the target group before implementation [27]. This evaluation aims to assess The Gist’s usability, desirability, inclusiveness, and potential for impact, as well as identifying areas for future improvement. Development of The Gist used a human-centred and co-design methodology [4].

Jake Turvey, Michelle Raggatt, Cassandra J C Wright, Angela C Davis, Meredith J Temple-Smith, Megan S C Lim

JMIR Form Res 2025;9:e65859

A Narrative Review to Identify Promising Approaches for Digital Health Interventions to Support Emotion Regulation for Adolescents With Attention-Deficit/Hyperactivity Disorder

A Narrative Review to Identify Promising Approaches for Digital Health Interventions to Support Emotion Regulation for Adolescents With Attention-Deficit/Hyperactivity Disorder

Emotion regulation can be defined as a set of processes concerned with the identification or evaluation, inhibition, or modification of emotional reactions in the service of achieving some goal, including displaying socially appropriate behavior [6]. The process model of emotion regulation, developed and later extended by Gross [7,8], is one of the dominant models in the field.

Aja Louise Murray, Melissa Thye, Ingrid Obsuth, Shufang Cai, Michael Lui, Corina Orr, Anusha Saravanan

JMIR Ment Health 2025;12:e56066

Formative Evaluation of Suicide Prevention Websites for Men: Qualitative Study with Men at Risk of Suicide and with Potential Gatekeepers

Formative Evaluation of Suicide Prevention Websites for Men: Qualitative Study with Men at Risk of Suicide and with Potential Gatekeepers

For the evaluation of the websites for males, 24 videoconference interviews with men in 3 age groups (18 to 30 years old, 31 to 50 years old, 50 years and older; 8 participants per age group) were conducted. We included all persons who identified as men and were older than 18 years. We did not explicitly search for men with a history of suicidal behavior nor relatives of men with a history of suicidal experience and behavior given ethical considerations.

Doreen Reifegerste, Anna J M Wagner, Lisa Huber, Manuel Fastuca

JMIR Form Res 2025;9:e59829