Search Articles

View query in Help articles search

Search Results (1 to 10 of 76 Results)

Download search results: CSV END BibTex RIS


Large Language Model–Based Assessment of Clinical Reasoning Documentation in the Electronic Health Record Across Two Institutions: Development and Validation Study

Large Language Model–Based Assessment of Clinical Reasoning Documentation in the Electronic Health Record Across Two Institutions: Development and Validation Study

However, feedback provided to trainees can still be limited due to faculty having different standards of what constitutes high quality CR documentation and limited time for feedback in the fast-paced clinical environment [5-7]. Machine learning (ML), natural language processing (NLP), and other artificial intelligence (AI) technologies have emerged as avenues to augment feedback [8-12]. NLP has been used to automate the scoring of documentation in simulated scenarios [13-16].

Verity Schaye, David DiTullio, Benedict Vincent Guzman, Scott Vennemeyer, Hanniel Shih, Ilan Reinstein, Danielle E Weber, Abbie Goodman, Danny T Y Wu, Daniel J Sartori, Sally A Santen, Larry Gruppen, Yindalon Aphinyanaphongs, Jesse Burk-Rafel

J Med Internet Res 2025;27:e67967

Novel Evaluation Metric and Quantified Performance of ChatGPT-4 Patient Management Simulations for Early Clinical Education: Experimental Study

Novel Evaluation Metric and Quantified Performance of ChatGPT-4 Patient Management Simulations for Early Clinical Education: Experimental Study

Delayed feedback keeps novice learners from overrelying on immediate feedback cues to make decisions and promotes active learning in simulations [29]. However, Mayer suggests immediate feedback may be better for some tasks such as solo novice learning or guided reasoning with an expert, but the Society for Simulation in Healthcare guidelines suggest that delayed debrief is most appropriate, and we accordingly chose delayed feedback for our metric [30].

Riley Scherr, Aidin Spina, Allen Dao, Saman Andalib, Faris F Halaseh, Sarah Blair, Warren Wiechmann, Ronald Rivera

JMIR Form Res 2025;9:e66478

Identifying Patient-Reported Care Experiences in Free-Text Survey Comments: Topic Modeling Study

Identifying Patient-Reported Care Experiences in Free-Text Survey Comments: Topic Modeling Study

In addition to the rating scales, patient experience surveys often include free-text comment responses where patients can share additional feedback and context on their experiences with health care services. These free-text comments can provide additional insight into patient experiences and how health care can be improved.

Brian Steele, Paul Fairie, Kyle Kemp, Adam G D'Souza, Matthias Wilms, Maria Jose Santana

JMIR Med Inform 2025;13:e63466

Smartphone-Based Intervention Targeting Norms and Risk Perception Among University Students with Unhealthy Alcohol Use: Secondary Mediation Analysis of a Randomized Controlled Trial

Smartphone-Based Intervention Targeting Norms and Risk Perception Among University Students with Unhealthy Alcohol Use: Secondary Mediation Analysis of a Randomized Controlled Trial

Many of the digital interventions for unhealthy alcohol use that have been found effective were based on personalized normative feedback (PNF) and personalized feedback on risks for health (PFR) [11-13]. PNF is based on social norms theory, which posits that an individual’s behavior is influenced by their perceptions and beliefs about what is considered normal behavior among other people [2,14-16]. Thus, an individual’s alcohol consumption is impacted by their perceptions of other people’s drinking habits.

Joseph Studer, John A Cunningham, Elodie Schmutz, Jacques Gaume, Angéline Adam, Jean-Bernard Daeppen, Nicolas Bertholet

J Med Internet Res 2025;27:e55541

Collaborative Development of Feedback Concept Maps for Virtual Patient–Based Clinical Reasoning Education: Mixed Methods Study

Collaborative Development of Feedback Concept Maps for Virtual Patient–Based Clinical Reasoning Education: Mixed Methods Study

A study by Morse and Jutras [18] showed that working with concept maps had an effect on the students’ problem-solving performance only when feedback was provided. However, in order to provide students with feedback on their concept map, some form of “expert concept map” is needed to compare students’ results with [19], which can then be provided in real time in digital environments. Such “expert concept maps” can be created by a single teacher or by a panel of professionals or experts [19-21].

Anja Mayer, Inga Hege, Andrzej A Kononowicz, Anja Müller, Małgorzata Sudacka

JMIR Med Educ 2025;11:e57331

A User-Centered Design Approach for a Screening App for People With Cognitive Impairment (digiDEM-SCREEN): Development and Usability Study

A User-Centered Design Approach for a Screening App for People With Cognitive Impairment (digiDEM-SCREEN): Development and Usability Study

The objective of this publication is to illustrate the iterative and agile user-centered development process consisting of 8 phases to move from a conceptual idea to an early prototype and a final prototypical implementation with continual involvement and feedback process from stakeholders and intended future users.

Michael Zeiler, Nikolas Dietzel, Fabian Haug, Julian Haug, Klaus Kammerer, Rüdiger Pryss, Peter Heuschmann, Elmar Graessel, Peter L Kolominsky-Rabas, Hans-Ulrich Prokosch

JMIR Hum Factors 2025;12:e65022

A Digital Tool for Clinical Evidence–Driven Guideline Development by Studying Properties of Trial Eligible and Ineligible Populations: Development and Usability Study

A Digital Tool for Clinical Evidence–Driven Guideline Development by Studying Properties of Trial Eligible and Ineligible Populations: Development and Usability Study

In parallel, a prototype data analysis tool was designed and demonstrated to the NICE gout GDG and other guideline developers in NICE and SIGN to seek their feedback and more detailed requirements in terms of data analysis they wished to have access to as they considered the evidence and drafted recommendations. It was agreed to capture the following two high-level output types: Index condition population analysis: A general view of the population with the underlying condition.

Shahzad Mumtaz, Megan McMinn, Christian Cole, Chuang Gao, Christopher Hall, Magalie Guignard-Duff, Huayi Huang, David A McAllister, Daniel R Morales, Emily Jefferson, Bruce Guthrie

J Med Internet Res 2025;27:e52385

Effect of a Feedback Visit and a Clinical Decision Support System Based on Antibiotic Prescription Audit in Primary Care: Multiarm Cluster-Randomized Controlled Trial

Effect of a Feedback Visit and a Clinical Decision Support System Based on Antibiotic Prescription Audit in Primary Care: Multiarm Cluster-Randomized Controlled Trial

This study aimed to evaluate the effect of a multifaceted intervention involving an HIR visit, clinical practice feedback, and the presentation of an online decision aid (the CDSS-based visit group) on antibiotic prescribing among GPs in western France. The intervention was compared with (1) a standard intervention involving a HIR visit, clinical practice feedback, and a prescribing information leaflet (the standard visit group) and (2) no intervention (the control group).

Pauline Jeanmougin, Stéphanie Larramendy, Jean-Pascal Fournier, Aurélie Gaultier, Cédric Rat

J Med Internet Res 2024;26:e60535

Electronic Feedback Alone Versus Electronic Feedback Plus in-Person Debriefing for a Serious Game Designed to Teach Novice Anesthesiology Residents to Perform General Anesthesia for Cesarean Delivery: Randomized Controlled Trial

Electronic Feedback Alone Versus Electronic Feedback Plus in-Person Debriefing for a Serious Game Designed to Teach Novice Anesthesiology Residents to Perform General Anesthesia for Cesarean Delivery: Randomized Controlled Trial

Furthermore, the debriefing component, which typically uses an electronic feedback model [12], is not even consistently described in proposed design frameworks [13,14]. Electronic automated written feedback is typically provided based on the player’s expected actions being detected as “performed,” “partially performed,” or “not performed,” by the game software. Evidence of the value of electronic feedback has been previously demonstrated in 1 randomized controlled trial [15].

Allison Lee, Stephanie Goodman, Chen Miao Chen, Ruth Landau, Madhabi Chatterji

JMIR Serious Games 2024;12:e59047

Development and Refinement of a Chatbot for Birthing Individuals and Newborn Caregivers: Mixed Methods Study

Development and Refinement of a Chatbot for Birthing Individuals and Newborn Caregivers: Mixed Methods Study

Survey feedback on outreach strategies and usability (n=100). Example of participants’ interview responses by themes. “At the beginning, when I received the first message, I wasn’t sure what to do, if should read it or not, later I decided to read it and I found it to be good, because it was good information.” [Hispanic/Latina, Other, 38 years, female, 2 children] “In the past, I was a victim of identity theft. I’m very leery about getting messages from different places ...

Jessica Nathalie Rivera Rivera, Katarina E AuBuchon, Marjanna Smith, Claire Starling, Karen G Ganacias, Aimee Danielson, Loral Patchen, Janine A Rethy, H Joseph Blumenthal, Angela D Thomas, Hannah Arem

JMIR Pediatr Parent 2024;7:e56807