JMIR Medical Education最新文献

{"title":"Attitudes Toward Digital Planetary Health Before and After a Lecture Series on Environmental Awareness and Future Visions: Repeated Cross-Sectional Survey Study Regarding Twin Transformation.","authors":"Julia Nitsche, Theresa Sophie Busse, Sonja Schmalen, Ina Otte, Jan Peter Ehlers","doi":"10.2196/89259","DOIUrl":"10.2196/89259","url":null,"abstract":"<p><strong>Background: </strong>The focus on sustainability in university teaching and education about the climate catastrophe is constantly increasing and is essential for creating change. The chances offered by digital technological innovations are decisive in spotlighting planetary health education. Alongside welfare economies and social movements, they are among the areas with great potential to drive sustainable development.</p><p><strong>Objective: </strong>This study aimed to evaluate attitudes toward digital planetary health before and after a fully digital planetary health lecture series. This included assessing environmental health awareness, climate-related health risks, and perceptions of the need to integrate digital and planetary health education into university curricula.</p><p><strong>Methods: </strong>A repeated, pseudonymous, nonexperimental, cross-sectional online survey was conducted before (T1) and after (T2) a fully digital lecture series on digital planetary health during the 2022-2023 winter term. Because participant matching across time points was unsuccessful, descriptive analyses were conducted at the group level.</p><p><strong>Results: </strong>A total of 180 participants completed the T1 survey, and 79 participants completed the T2 survey. The mean age in the T1 survey was 27.92 (SD 10.95) years, with a minimum age of 18 years and a maximum age of 77 years. The mean age in T2 was 29.22 (SD 12.78) years, with a minimum age of 18 years and a maximum age of 78 years. In the T2 survey, 70.9% (56/79) of the participants rated it as \"(very) important\" (mean 5.38, SD 1.15) to incorporate climate-related health impacts and digital health issues into their studies. In the T2 survey, 51.9% (41/79) of the participants stated that the range of educational events on digital health at universities was inadequate. Qualitative responses highlighted perceived benefits of digitalization for collaboration, knowledge dissemination, and health care access, while concerns regarding resource consumption and ethical challenges were also described.</p><p><strong>Conclusions: </strong>Participants who attended the lecture series perceived digital planetary health as highly relevant to university education. The findings provide exploratory insights into attitudes toward the integration of planetary health and digital health topics into higher education curricula.</p>","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":"12 ","pages":"e89259"},"PeriodicalIF":13.9,"publicationDate":"2026-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13436795/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148674345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating Large Language Model-Based Automated Scoring in a Voice-Based Virtual Standardized Patient Platform for Medical Students: A Cross-Sectional Agreement Study.","authors":"Xiaoxing Gao, Xiaoming Huang, Rongrong Hu, Li Zhang, Huiting Liu, Bingqing Zhang, Chong Wei, Wei Qiu, Mengyu Zhang, Xuefeng Sun","doi":"10.2196/95578","DOIUrl":"10.2196/95578","url":null,"abstract":"<p><strong>Background: </strong>Large language model (LLM)-powered virtual standardized patients (VSPs) enable scalable clinical skills practice, but the validity of AI-generated scores relative to faculty ratings remains unclear.</p><p><strong>Objective: </strong>To assess agreement between LLM-generated and faculty ratings of history-taking and communication performance, and to examine the influence of rater and case heterogeneity.</p><p><strong>Methods: </strong>In this cross-sectional study, 92 fourth-year medical students completed one of three 15-minute voice-based VSP cases (fever, diarrhea, cough). Ten blinded faculty raters scored performance (0-100 total; 0-50 domains). AI scores were generated by DeepSeek-V3 using a calibrated prompt. Agreement was evaluated using mixed-effects models, intraclass correlation coefficients (ICC[2,1]), Spearman correlations, mean absolute error (MAE), Bland-Altman analysis, and variance partition coefficients (VPC).</p><p><strong>Results: </strong>Median total scores were similar for AI and faculty (93.0 [IQR 6.0] vs 94.0 [IQR 4.0]). Rater variability accounted for 37% of residual variance in faculty total scores (VPC = 0.37). AI total scores were positively associated with faculty total scores (β = 0.37, 95% CI 0.26-0.48, P<.001; Spearman ρ = 0.50, 95% CI 0.34-0.65). Absolute agreement was moderate (ICC[2,1] = 0.51, 95% CI 0.34-0.65), with MAE of 3.11 points. Mixed-effects Bland-Altman analysis showed a non-significant mean bias (1.26 points) and 95% limits of agreement from -4.95 to 7.48 (width = 12.43 points), with proportional bias (β_mean = -0.55, P<.001). Agreement was stronger for information gathering (β = 0.46, ρ = 0.49, ICC = 0.54, VPC = 0.23) than for communication (β = 0.27, ρ = 0.28, ICC = 0.29, VPC = 0.52). A sensitivity analysis in the lowest quartile showed attenuated but consistent agreement (ICC = 0.38).</p><p><strong>Conclusions: </strong>LLM-based scoring in a VSP showed moderate agreement with faculty ratings, performing better for information gathering than for communication. Due to rater and case heterogeneity, ceiling effects, and proportional bias, it is suitable for formative use and enhanced sampling in programmatic assessment, but not for independent high-stakes summative decisions.</p><p><strong>Clinicaltrial: </strong></p>","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":" ","pages":""},"PeriodicalIF":13.9,"publicationDate":"2026-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148631905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Performance of ChatGPT on Nursing Licensure Examinations in the United States and China: Cross-Sectional Study.","authors":"Zelin Wu, Wenyi Gan, Zhaowen Xue, Zhengxin Ni, Xiaofei Zheng, Yiyi Zhang","doi":"10.2196/105550","DOIUrl":"10.2196/105550","url":null,"abstract":"","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":"12 ","pages":"e105550"},"PeriodicalIF":13.9,"publicationDate":"2026-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13399401/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148585245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Augmented Reality in Surgical Training: Systematic Review of Its Impact on Technical Performance in Surgical Trainees.","authors":"Mahmoud El Ashry, Ahmed El Ashry, Hamza Khalique, Yahye Abdalle, Thomas Yeung","doi":"10.2196/106576","DOIUrl":"10.2196/106576","url":null,"abstract":"","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":"12 ","pages":"e106576"},"PeriodicalIF":13.9,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13394845/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148580584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance of GPT-4o and Claude in Medical Ethics Scenarios: Comparative Study.","authors":"Karishma R Desai, Anna L Gorsky, Nicole A Zelenski","doi":"10.2196/70199","DOIUrl":"10.2196/70199","url":null,"abstract":"<p><strong>Background: </strong>The emergence of AI technology has sparked curiosity regarding the capabilities of large language models (LLMs) in the field of medicine. Minimal research exists regarding the proficiency of various AI models in ethics scenarios, specifically in specialty-based scenarios.</p><p><strong>Objective: </strong>This study aimed to compare the performance of GPT-4o and Claude Sonnet 4 on ethics questions with that of medical students and orthopedic residents.</p><p><strong>Methods: </strong>A total of 200 ethical or legal scenario questions were randomly selected from question banks targeted for third- and fourth-year medical students (UWorld, AMBOSS) and orthopedic residents (OrthoBullets). Questions at the medical student level were exclusively text-based, while resident-level questions included text-based questions accompanied by images. Each question was entered identically into each AI model 3 separate times. If answers varied between trials, the answer provided most frequently by the model was used as the selected answer.</p><p><strong>Results: </strong>GPT-4o correctly answered 140 (70%) of 200 questions, which was similar to the average human test taker score of 71% (~142/200 questions). Claude correctly answered 180 (89%) questions, a score greater than that of human test takers and significantly better than GPT-4o (P<.001). Claude scored significantly higher than GPT-4o in almost all question categories. GPT-4o provided different responses to identically worded trials for 27 (21%) of 130 general questions and 3 (4%) of 70 orthopedic questions (P=.002), while Claude did not have a significant difference in variability between these 2 groups (general: 16/130, 12% vs orthopedic: 3/70, 4%; P=.06). GPT-4o selected the incorrect response for 60 (30%) total questions and chose the incorrect response most commonly selected by humans significantly more frequently on UWorld interpersonal-specific questions (30/40, 75%) than on UWorld all social sciences (27/40, 68%; P=.03). Claude showed no significant difference in the rate of most common incorrect response selection between question categories.</p><p><strong>Conclusions: </strong>These results suggest that GPT-4o can potentially answer both general and specialty-specific ethical questions with similar proficiency to sample groups of both medical students and orthopedic residents, while Claude AI performs significantly better than both humans and GPT-4o. Variables such as AI model framework and training data may drive the observed difference in performance, but the exact cause cannot be definitively isolated without intentional testing. Therefore, further research is needed to ensure safety by minimizing output variability before integrating AI as a patient-facing resource.</p>","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":"12 ","pages":"e70199"},"PeriodicalIF":13.9,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13396000/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148580572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Benefits of Chain-of-Thought Prompting for Clinical Record Rubric Evaluation in Undergraduate Medical Education: Experimental Evaluation Study With Medical Faculty.","authors":"Alberto Nogales, Sophia Denizon, Alonso Mateos Rodriguez, Javier Cervera Cordero, Gonzalo Pandelet Barainca, Enrique Aranguren Moliner, Emilio Cervera Barba","doi":"10.2196/88652","DOIUrl":"10.2196/88652","url":null,"abstract":"<p><strong>Background: </strong>Large language models in artificial intelligence have been among the tools with a significant and real impact on people's daily lives. In this regard, they serve as an aid in specific fields, such as education, helping educators with cumbersome tasks such as periodic evaluations.</p><p><strong>Objective: </strong>This study focused on analyzing the benefits of large language models, particularly the chain-of-thought (CoT) strategy, for the task of evaluating students' Spanish-language medical record writing. The aim was 2-fold: first, we attempted to save time and resources, and second, we used the reasoning of the CoT strategy to evaluate the rubrics and their interpretations.</p><p><strong>Methods: </strong>The proposed solution assessed the application of 2 models-Llama 3.1 and Claude 3.5-in combination with one-shot and CoT to evaluate how medical students write medical records in Spanish. First, machine learning metrics were applied to measure the performance of the solutions. Then, different statistical analyses were performed at the clinical record and item levels. Finally, differences between the proposed models and evaluators were studied in depth.</p><p><strong>Results: </strong>A maximum of 3807 items were evaluated. Claude obtained the best accuracy with slight differences between one-shot and CoT (86.4% and 85.0%, respectively). However, Claude with CoT outperformed the rest of the combinations on all complementary metrics, initially achieving a sensitivity of 94.2%, specificity of 59.5%, precision of 85.8%, and F1-score of 89.6%. Expert review of CoT reasoning determined that 63.8% of the discrepancies were model hits, raising Claude's final accuracy to 94.6% (SD 4.3%). In the final phase, sensitivity was 98.0% (SD 2.3%), specificity improved to 83.3% (SD 14.3%), and F1-score reached 96.2% (SD 3.3%). Sectional analysis showed greater difficulties in the \"History of present illness\" section (n=125 discordances).</p><p><strong>Conclusions: </strong>CoT demonstrated strong potential for supporting the evaluation of clinical records written in Spanish by medical students and providing feedback to them. More importantly, it showed significant promise in assisting professors by assessing the quality of their rubrics and identifying possible errors.</p>","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":"12 ","pages":"e88652"},"PeriodicalIF":13.9,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13395432/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148580628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Principles for Responsible AI in Health Professions Education, Research, and Care: Health CARE-AI (Contextual, Accountable, Responsible, and Equitable Artificial Intelligence) Framework Delphi Consensus Study.","authors":"Lyn K Sonnenberg, David Wiljer, Muhammad Mamdani, Victor Do, Brandon Tang, Babar Haroon, Bizav Jaffer, Jerry Maniate","doi":"10.2196/91626","DOIUrl":"10.2196/91626","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Artificial intelligence (AI) is rapidly integrating into health professions education and clinical practice, creating significant opportunities alongside new ethical challenges. Although current international and professional guidance establishes essential values, it offers limited direction for how clinicians, educators, learners, and institutions should act in routine educational, research, and clinical contexts. The CARE-AI (Contextual, Accountable, Responsible, and Equitable Artificial Intelligence) project responds to this practice-level gap by articulating guidance that moves beyond values toward professional accountability and equity, with explicit attention to educational, research, and clinical practice contexts.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;The study objective was to develop and validate a consensus-based, actionable framework of principles to guide responsible AI use across health professions education, research, and clinical care.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We conducted a 3-phase modified Delphi consensus study, reported in accordance with the Accurate Consensus Reporting Document. Phase 1 involved 2 international professional meetings and 3 purposively sampled focus groups (AI or technology, health professions education, and ethics or professionalism) to adapt and refine draft principles using an exploratory qualitative approach. Phase 2 used an online survey with a 5-point importance scale and prespecified consensus criteria (inclusion ≥70%: high ratings; exclusion ≥70%: low ratings). Phase 3 used include, exclude, or undecided voting on revised principles. Quantitative thresholds determined consensus. Qualitative free-text comments informed iterative refinement.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Participants represented diverse communities of practice across health professions education, clinical care, patient partners, ethics, and digital health, spanning multiple professional roles and training levels. Across all phases, 303 unique participants contributed to the study. Phase 1 focus groups (n=61) provided early insight and direction. In phase 2, the first Delphi survey round, 242 participants initiated the survey, with 120 (49.6%) participants completing it. In phase 3, the second Delphi survey round, 103 participants were invited based on expressed interest at the end of the first round; 78 participants initiated the survey and 75 completed it (75/78, 96.2% of starters). In phase 2, of the 61 statements, 58 (95%) met the inclusion criteria, and participants submitted 1887 comments (697 were content rich), prompting clearer accountability language, stronger equity commitments, and more usable wording. In phase 3, all 10 principles and their statements met the inclusion criteria. Participants contributed 224 comments (179 were content rich) that informed final refinements. Endorsement was near unanimous: 96% (72/75) agreed or strongly agreed that the framework clearly defined professionalis","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":"12 ","pages":"e91626"},"PeriodicalIF":13.9,"publicationDate":"2026-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13395757/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148562899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Psychiatry Training Using an Agentic AI Simulated Consultation Tool: Prospective Cohort Study.","authors":"Alice Rueda, Huda F Al-Shamali, Zack Cote, Niloy Roy, Reinhard Janssen-Aguilar, Jithin Joseph, Bazen Gashaw Teferra, Mohammad Amin Kamaleddin, Lisa Burback, Olga Winkler, Bill Kapralos, Andrei Torres, Divya Sharma, Sridhar Krishnan, Guillaume Dumas, Andrew Greenshaw, Alexandre Hudon, Sanjeev Sockalingam, Yanbo Zhang, Adam Dubrowski, Venkat Bhat","doi":"10.2196/88580","DOIUrl":"10.2196/88580","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Canadian psychiatry residents must demonstrate consultation competency, assessed using the standardized assessment of a clinical encounter report (STACER). However, opportunities to practice these skills and receive constructive assessment remain limited in clinical settings.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to evaluate the technical feasibility of an agentic AI system designed to support psychiatry residents' consultation competence through simulated patient encounters with a patient agent and structured feedback from a rater agent.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We conducted a two-phase technical feasibility prospective single-arm cohort study of the STACER Agentic System, a large language model-based platform integrating a patient agent and a rater agent. Phase 1 involved automated evaluation of the patient agent using a psychiatrist agent across 227 synthetic major depressive disorder cases. Performance was assessed using DeepEval metrics (correctness, clarity, medical faithfulness, turn relevance, and role adherence) with descriptive statistics and 95% CIs. Phase 2 involved a preliminary user study with 14 convenience-sampled participants: a total of 5 members of the clinical research team and 9 psychiatry residents from the University of Alberta. Participants completed simulated diagnostic interviews and case presentations. Performance was evaluated using STACER-based scoring by the rater agent and 2 psychiatrists. Interrater reliability was assessed using intraclass correlation coefficients (α=.05). Participants rated realism, behavioral consistency, psychiatric nuance, and feedback utility using Likert scales and free-text answers.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The patient agent demonstrated high behavioral (51/56, 91.07%) and symptom fidelity (105/110, 95.45%), with strong automated performance (medical faithfulness mean 0.99, 95% CI 0.99-1.00; turn relevance 0.99, 95% CI 0.986-0.992). Participants rated simulations as psychiatrically plausible and diagnostically useful, particularly for depressive symptom representation, although rapport building was moderate (mean 2.78, SD 1.56 to mean 3.00, SD 1.41, out of 5.00) due to limited nonverbal cues. The rater agent generated structured STACER-aligned feedback with high intrarater consistency, especially at the section subtotal level. Interrater reliability with psychiatrists was poor at the item level (intraclass correlation coefficient range=0.25-0.49) but improved to good-to-excellent agreement at the section level for psychiatry resident sessions (intraclass correlation coefficient range=0.89-0.93). The rater agent's scores fell between those of the 2 psychiatrists for the clinical research team and were lower than both human raters for psychiatry residents.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The STACER Agentic System demonstrates the technical feasibility of using agentic AI to simulate psychiatric consultations and deliver STACER-ali","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":"12 ","pages":"e88580"},"PeriodicalIF":13.9,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13387278/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148550667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"User Acceptance of an AI-Powered Medical History-Taking Training System Among Undergraduate Medical Students: Mixed Methods Study.","authors":"Yang Liu, Yiying Zhu, Chujun Shi, Xian Lu, Liping Wu, Minghui Yue, Xiaolin Hong, Oudong Xia, Weishan Zhang","doi":"10.2196/101425","DOIUrl":"10.2196/101425","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;AI-powered virtual patient systems provide medical students with repeatable practice environments for history-taking training. However, user acceptance of such systems and the experience dimensions associated with that acceptance lack mixed methods evidence.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to (1) examine the associations of system experience and learning experience/intrinsic motivation with overall acceptance among undergraduate medical students using an AI-powered medical history-taking training and evaluation system (AMTES), (2) explore user experience patterns through open-ended questions, and (3) integrate quantitative and qualitative findings to inform system refinement and pedagogical implementation.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A cross-sectional convergent mixed methods design was used. A total of 66 undergraduate medical students at a Chinese medical college completed a postuse questionnaire after AMTES training. The primary outcome was an overall acceptance composite combining use intention, recommendation intention, and overall satisfaction. Associations with system experience and learning experience/intrinsic motivation were examined using linear regression with heteroscedasticity-consistent SEs (type 3) and bootstrap CIs. Sensitivity analyses included covariate adjustment, single-outcome models, a fractional logit model, and content-overlap sensitivity checks for the system-experience composite. Open-ended responses were analyzed using codebook-oriented thematic analysis and integrated with quantitative findings through a joint display.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Both system experience and learning experience/intrinsic motivation were positively associated with overall acceptance (standardized β=.526; P&lt;.001 and standardized β=.377; P=.002, respectively; R&lt;sup&gt;2&lt;/sup&gt;=0.662). Sensitivity analyses supported the robustness of both positive associations. Qualitative analysis showed that the most frequently nominated benefits clustered within the \"Practice Accessibility and Feedback Support\" theme, particularly self-directed practice (28/66, 42.4%) and immediate feedback (25/66, 37.9%). Refinement priorities clustered around 4 dialogue-quality and assessment dimensions, including semantic understanding, contextual consistency, conversational naturalness, and scoring logic, each cited by 21%-35% of respondents. The mixed methods joint display indicated contextual (same-source) alignment on dialogue and scoring concerns and suggested that perceived scoring-feedback discrepancies may be associated with lower student trust in the feedback function. This cross-dimensional pattern was not apparent from the quantitative model alone.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;In this exploratory cohort of undergraduate medical students, both system interaction quality and perceived learning value were positively associated with overall acceptance of AMTES, with system interaction quality showing","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":" ","pages":"e101425"},"PeriodicalIF":13.9,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13439043/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148370156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Perceptions, Attitudes, and Use of AI by Medical Students: Mixed Methods Study.","authors":"Frédéric Paris, Vincent Garrouste, Laure Abensur Vuillaume","doi":"10.2196/91345","DOIUrl":"10.2196/91345","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;AI is transforming medicine by enhancing care, reducing administrative tasks, and facilitating research. AI also raises many concerns, including a lack of clinical context awareness, data dependence, and the absence of ethical judgment. As future practitioners, medical students must be prepared for these changes. Most studies assessing students' attitudes and knowledge were conducted before AI became accessible and tailored to the needs of the population. Therefore, how medical students actually use AI remains largely unexplored.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to explore French medical students' perceptions, attitudes, and use of AI.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A mixed methods study was conducted in 2025 among French medical students in their clerkship year. An online survey included open-ended questions about the definition of AI and feelings toward AI, a Likert scale item to assess specific attitudes, and multiple-choice questions about student characteristics. Quantitative analysis was performed using Kruskal-Wallis tests, chi-square tests, and exploratory multivariable linear regression to examine associations between AI knowledge, attitudes, and student characteristics. Qualitative thematic analysis was conducted inductively on open-text responses regarding perceptions of AI, feelings, training expectations, and use.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Of the 1377 responses received, 1342 were included. Students had a median age of 23 (IQR 22-24) years and were predominantly in their fifth year. Only 5% (67/1342) provided a correct definition of AI, while 57.4% (770/1342) gave incorrect responses. Attitudes toward AI were generally positive, with a median score of 7 (IQR 5-8). Students with unknown AI definitions had significantly lower attitude scores (P=.02), although the magnitude of the difference was small (ε²=0.005). In multivariable analysis, belonging to the unknown AI definition category remained associated with a lower general attitude toward AI score compared with the incorrect category (regression coefficient β=-0.72, 95% CI -1.17 to -0.28; P=.001). Regarding education, 48.5% (651/1342) of students preferred AI training outside the formal curriculum. Qualitative analysis revealed 5 themes: representation, nuanced optimism, critical consideration, replacement, and AI use. Students describe AI as a robot, an improved search engine, or an unlimited data source. Their nuanced optimism blends enthusiasm for efficient patient care and the opportunity to focus more on the patient relationship, with concerns about dehumanization, energy costs, and skill regression. Critical consideration underscores distrust from ethical dilemmas and data security risks. Replacement concerns arise from shifting professional roles, though many believe human empathy remains irreplaceable. Regarding AI use, students highlight its potential for administrative aid, personalized training, and clinical support","PeriodicalId":36236,"journal":{"name":"JMIR Medical Education","volume":"12 ","pages":"e91345"},"PeriodicalIF":13.9,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13384426/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148537263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}