Academic Journal
Scaffolded AI-Supported Problem-Based Learning for Medical Interns: Exploratory Retrospectively Registered Randomized Controlled Evaluation With a Voluntary Feasibility Follow-Up.
| Τίτλος: | Scaffolded AI-Supported Problem-Based Learning for Medical Interns: Exploratory Retrospectively Registered Randomized Controlled Evaluation With a Voluntary Feasibility Follow-Up. |
|---|---|
| Συγγραφείς: | Zhao Z; Department of Computer Science and Technology, Zhejiang University of Technology, No. 288 Liuhe Road, Xihu District, Hangzhou, Zhejiang, 310023, China, 86 158 6913 2329.; Zhejiang Institute of Artificial Intelligence, Hangzhou, Zhejiang, China., Wu B; Department of Ultrasound, Tongde Hospital Affiliated to Zhejiang Chinese Medical University, No. 234 Gucui Road, Hangzhou, Zhejiang, China., Tian S; Department of Ultrasound, Tongde Hospital Affiliated to Zhejiang Chinese Medical University, No. 234 Gucui Road, Hangzhou, Zhejiang, China., Hu H; Department of Computer Science and Technology, Zhejiang University of Technology, No. 288 Liuhe Road, Xihu District, Hangzhou, Zhejiang, 310023, China, 86 158 6913 2329., Hao P; Department of Computer Science and Technology, Zhejiang University of Technology, No. 288 Liuhe Road, Xihu District, Hangzhou, Zhejiang, 310023, China, 86 158 6913 2329. |
| Πηγή: | JMIR medical education [JMIR Med Educ] 2026 Sep 03; Vol. 12, pp. e95039. Date of Electronic Publication: 2026 Sep 03. |
| Τύπος έκδοσης: | Journal Article; Randomized Controlled Trial |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: JMIR Publications Country of Publication: Canada NLM ID: 101684518 Publication Model: Electronic Cited Medium: Internet ISSN: 2369-3762 (Electronic) Linking ISSN: 23693762 NLM ISO Abbreviation: JMIR Med Educ Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Toronto, ON : JMIR Publications, [2015]- |
| Ιατρικοί όροι (MeSH): | Problem-Based Learning*/methods , Problem-Based Learning*/standards , Internship and Residency*/methods , Artificial Intelligence*, Educational Measurement/methods ; Humans ; Feasibility Studies ; Retrospective Studies ; Follow-Up Studies ; Female ; Generative Artificial Intelligence ; Male ; Clinical Competence |
| Περίληψη: | Background: High-quality problem-based learning (PBL) during internship is resource-intensive and difficult to scale without consistent facilitation. Although generative AI is increasingly used in health professions education, many applications remain on-demand answer tools that may not reproduce core PBL processes. Objective: This study aimed to develop and evaluate the Multiagent PBL Environment for Clinical Reasoning (MAPLE-CR), an AI-supported environment that uses generative AI as a process-oriented scaffold rather than an answer-delivery aid. The system supports cognitive mechanisms through reasoning prompts, social-interactional mechanisms through simulated tutor and peer roles, and regulatory mechanisms through structured workflows and feedback loops. We separately evaluated implementation and repeated-use feasibility, including learner experience, short-term outcomes versus self-study, and preliminary framework-aligned process evidence. Methods: We conducted a 2-stage study. In an exploratory randomized evaluation (N=52; intervention: n=26; control: n=26), interns completed parallel pretests and posttests around a standardized case. The intervention group engaged in asynchronous, scaffolded PBL in MAPLE-CR, whereas controls completed case-matched self-study using materials derived from the same case and learning objectives. We summarized transcript-derived process dimensions and postsession learner experience in the intervention group. In a voluntary follow-up, 18 participants completed 1 MAPLE-CR case per week for 4 additional weeks to examine repeated use feasibility and patterns across novel cases. Results: Baseline pretest scores were comparable between groups (P=.56). The intervention group achieved higher posttest scores than controls (Hodges-Lehmann median difference 8.25 points, 95% CI 6.60-11.60; Cliff δ=0.506, 95% CI 0.21-0.76; P=.001) and greater score gains (median difference 6.60 points, 95% CI 1.60-14.95; P=.01). On a 0 to 5 scale, mean scores were highest for knowledge accuracy (4.4) and clinical reasoning (CR, 3.7), whereas active participation averaged 2.1, and interaction-oriented dimensions were more variable. Means for 12 positively worded questionnaire items ranged from 4.19 to 4.62, supporting high satisfaction, involvement, perceived support, and self-efficacy; open-ended responses contextualized perceived strengths and improvement needs. In the voluntary follow-up (n=18), weekly cross-case use was feasible; median within-session gains ranged from 13.4 to 20.0 points across 5 attempts, with marked increases in CR and aggregate scores from attempts 1 to 2 but statistically uncertain later trajectories. Conclusions: MAPLE-CR was feasible and showed high learner acceptability. Its use was associated with larger short-term CR knowledge gains than case-matched self-study, while transcript analyses provided preliminary framework-aligned process evidence. However, the post hoc sensitivity analysis did not establish prospective power sufficiency, and the confidence interval could not exclude smaller educationally meaningful effects. These findings suggest that AI-supported, process-oriented PBL may provide a scalable formative supplement for CR practice when facilitator capacity and small-group scheduling are constrained, but the study did not isolate specific scaffolding effects. Further research should confirm these findings using larger, prospectively powered trials with stronger active comparators and longer-term outcome measures. (© Zhengqi Zhao, Baijing Wu, Shuyuan Tian, Haigen Hu, Pengyi Hao. Originally published in JMIR Medical Education (https://mededu.jmir.org).) |
| References: | Med Educ. 2025 Oct;59(10):1079-1093. (PMID: 40156179) NPJ Digit Med. 2026 Jan 9;9(1):29. (PMID: 41513946) JMIR Med Educ. 2024 Sep 23;10:e58753. (PMID: 39312284) JMIR Med Educ. 2024 Aug 16;10:e59213. (PMID: 39150749) Int J Med Inform. 2025 Nov;203:106006. (PMID: 40479778) Med Educ. 1979 Jan;13(1):41-54. (PMID: 763183) Medicine (Baltimore). 2024 Jul 5;103(27):e38813. (PMID: 38968472) Int J Med Inform. 2025 Mar;195:105761. (PMID: 39689449) JMIR Med Educ. 2025 Dec 12;11:e81271. (PMID: 41385781) NPJ Digit Med. 2025 Nov 4;8(1):627. (PMID: 41188616) J Med Ethics. 2010 Oct;36(10):614-9. (PMID: 20797979) Nature. 2024 Jun;630(8017):625-630. (PMID: 38898292) Sci Rep. 2023 Sep 14;13(1):15220. (PMID: 37709817) Educ Psychol. 2013 Oct;48(4):243-270. (PMID: 24273351) BMC Med Educ. 2026 Jan 23;26(1):291. (PMID: 41578287) Med Teach. 2002 Mar;24(2):173-80. (PMID: 12098437) Med Educ. 2024 Nov;58(11):1315-1323. (PMID: 38563548) Sci Rep. 2025 Aug 19;15(1):30440. (PMID: 40830409) Med Teach. 2013 Oct;35(10):e1511-30. (PMID: 23941678) Med Educ. 2026 Aug;60(8):894-907. (PMID: 41308655) Med Educ. 2011 Aug;45(8):792-806. (PMID: 21752076) Med Teach. 2025 Jul;47(7):1126-1133. (PMID: 39425996) J Med Internet Res. 2025 Nov 3;27:e76340. (PMID: 41183320) Med Teach. 2005 Jan;27(1):10-28. (PMID: 16147767) Int J Med Inform. 2026 May;211:106340. (PMID: 41678976) Korean J Med Educ. 2022 Jun;34(2):131-143. (PMID: 35676880) BMC Med Educ. 2025 Jan 11;25(1):50. (PMID: 39799356) Med Educ. 2023 Oct;57(10):882-885. (PMID: 37183307) BMC Med Educ. 2023 May 1;23(1):290. (PMID: 37127593) |
| Contributed Indexing: | Keywords: artificial intelligence; clinical reasoning; educational technology; large language models; problem-based learning; randomized controlled trial; scaffolding |
| Entry Date(s): | Date Created: 20260903 Date Completed: 20260903 Latest Revision: 20260921 |
| Update Code: | 20260921 |
| PubMed Central ID: | PMC13541230 |
| DOI: | 10.2196/95039 |
| PMID: | 42691464 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!