Academic Journal
Turning AI hallucinations into scaffolds for morphologic reasoning: A pilot randomized trial of prompt-guided virtual microscopy learning during a focused histology module.
| Τίτλος: | Turning AI hallucinations into scaffolds for morphologic reasoning: A pilot randomized trial of prompt-guided virtual microscopy learning during a focused histology module. |
|---|---|
| Συγγραφείς: | Peng Y; School of Public Health, Shenyang Medical College, Shenyang, People's Republic of China.; Shenyang Key Laboratory of Chronic Disease Assessment and Nutritional Intervention for Heart and Brain, Shenyang Medical College, Shenyang, People's Republic of China., Ma M; School of Public Health, Shenyang Medical College, Shenyang, People's Republic of China.; Shenyang Key Laboratory of Chronic Disease Assessment and Nutritional Intervention for Heart and Brain, Shenyang Medical College, Shenyang, People's Republic of China., Yang Y; Shenyang Medical College, Shenyang, People's Republic of China., Wu J; Shenyang Key Laboratory of Chronic Disease Assessment and Nutritional Intervention for Heart and Brain, Shenyang Medical College, Shenyang, People's Republic of China.; Shenyang Medical College, Shenyang, People's Republic of China., Peng Y; Shenyang Key Laboratory of Chronic Disease Assessment and Nutritional Intervention for Heart and Brain, Shenyang Medical College, Shenyang, People's Republic of China.; School of Basic Medicine, Shenyang Medical College, Shenyang, People's Republic of China. |
| Πηγή: | Anatomical sciences education [Anat Sci Educ] 2026 Oct; Vol. 19 (10), pp. 1670-1681. Date of Electronic Publication: 2026 Jun 30. |
| Τύπος έκδοσης: | Journal Article; Randomized Controlled Trial |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: John Wiley & Sons, Inc Country of Publication: United States NLM ID: 101392205 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1935-9780 (Electronic) Linking ISSN: 19359772 NLM ISO Abbreviation: Anat Sci Educ Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Hoboken, N.J. : John Wiley & Sons, Inc. |
| Ιατρικοί όροι (MeSH): | Microscopy*/methods , Education, Medical, Undergraduate*/methods , Histology*/education , Computer-Assisted Instruction*/methods , Artificial Intelligence*, Students, Medical/psychology ; Students, Medical/statistics & numerical data ; Educational Measurement/statistics & numerical data ; Humans ; Pilot Projects ; Female ; Male ; Young Adult ; Curriculum ; Learning ; User-Computer Interface ; Adult ; Workflow |
| Περίληψη: | AI is a medical education tool, yet its potential to foster morphologic reasoning remains underexplored. Histology students often struggle to move beyond pattern recognition toward evidence-based justification. This pilot trial evaluated a prompt-guided "Prompt Loop" workflow for improving morphologic reasoning and verification-oriented appraisal. A parallel-design randomized controlled trial was conducted with 55 first-year medical students. Participants were assigned to Standard Virtual Microscopy (VM) learning (n = 28) or VM Prompt Loop (n = 27). The intervention used a multimodal AI assistant (GPT-4o) within a four-stage cycle-Observation, Reasoning, Verification, and Consolidation-designed to treat AI inaccuracies as verification scaffolds. Outcomes included a supervised VM morphologic reasoning assessment (Identification vs. Reasoning) and a domain-level perception questionnaire. The VM Prompt Loop group achieved higher total scores (78.0 ± 13.5 vs. 67.1 ± 12.0; p = 0.003; Cohen's d = 0.85). This gain was mainly driven by the morphologic reasoning (38.4 ± 10.2 vs. 31.0 ± 8.2; p = 0.005; d = 0.80), whereas identification scores showed no significant difference (p = 0.073). Survey data revealed higher ratings for verification and inquiry behaviors (p < 0.001). Process documentation showed high fidelity, with 93% of Prompt Loop students submitting required AI-interaction screenshots and a mean of 2.1 ± 1.5 error-correction entries. A prompt-guided AI workflow improved morphologic reasoning in histology. When AI outputs were treated as provisional claims and routed through a structured verification process, the Prompt Loop may provide a practical model for supporting verification-oriented morphologic reasoning in histology. (© 2026 American Association for Anatomy.) |
| References: | Cheng X, Chan LK, Li H, Yang X. Histology and embryology education in China: the current situation and changes over the past 20 years. Anat Sci Educ. 2020;13:759–768. Hortsch M, Koney NK‐K, Oommen AM, Yohannan DG, Li Y, de Melo Leite ACR, et al. Virtual microscopy goes global: the images are virtual and the problems are real. 2023. p. 79–124. Francis DV, Charles AS, Jacob TM, Ruban A, Premkumar PS, Rabi S. Virtual microscopy as a teaching–learning tool for histology in a competency‐based medical curriculum. Med J Armed Forces India. 2023;79:S156–S164. Lee B, Hsieh S, Chang Y, Tseng F, Lin Y, Chen Y, et al. A web‐based virtual microscopy platform for improving academic performance in histology and pathology laboratory courses: a pilot study. Anat Sci Educ. 2020;13:743–758. Maity S, Nauhria S, Nayak N, Nauhria S, Coffin T, Wray J, et al. Virtual versus light microscopy usage among students: a systematic review and meta‐analytic evidence in medical education. Diagnostics. 2023;13:558. Fries A, Pirotte M, Vanhee L, Bonnet P, Quatresooz P, Debruyne C, et al. Validating instructional design and predicting student performance in histology education: using machine learning via virtual microscopy. Anat Sci Educ. 2024;17:984–997. Darici D, Flägel K, Sternecker K, Missler M. Transfer of learning in histology: insights from a longitudinal study. Anat Sci Educ. 2024;17:274–286. Bellstedt M, Holtrup A, Otto N, Berndt M, Scherff AD, Papan C, et al. Gaze cueing improves pattern recognition of histology learners. Anat Sci Educ. 2024;17:1461–1472. Eng‐Tat A, Liu P, Jitesh R, Chandrika M, Satish RL, Lian WQD, et al. The challenges of histology education. Clin Anat. 2023;36:308–314. Hortsch M. Histology as a paradigm for a science‐based learning experience: visits by histology education spirits of past, present, and future. Anat Sci Educ. 2023;16:372–383. Tolsgaard MG, Pusic MV, Sebok‐Syer SS, Gin B, Svendsen MB, Syer MD, et al. The fundamentals of artificial intelligence in medical education research: AMEE Guide No. 156. Med Teach. 2023;45:565–573. Lee H. The rise of ChatGPT: exploring its potential in medical education. Anat Sci Educ. 2024;17:926–931. Gan W, Ouyang J, Li H, Xue Z, Zhang Y, Dong Q, et al. Integrating ChatGPT in orthopedic education for medical undergraduates: randomized controlled trial. J Med Internet Res. 2024;26:e57037. Preiksaitis C, Rose C. Opportunities, challenges, and future directions of generative artificial intelligence in medical education: scoping review. JMIR Med Educ. 2023;9:e48785. Totlis T, Natsis K, Filos D, Ediaroglou V, Mantzou N, Duparc F, et al. The potential role of ChatGPT and artificial intelligence in anatomy education: a conversation with ChatGPT. Surg Radiol Anat. 2023;45:1321–1329. Izquierdo‐Condoy JS, Arias‐Intriago M, Tello‐De‐la‐Torre A, Busch F, Ortiz‐Prado E. Generative artificial intelligence in medical education: enhancing critical thinking or undermining cognitive autonomy? J Med Internet Res. 2025;27:e76340. Li X, Bai H, Feng X, Liang Z, Chen S, Zhao Q. Deliberate errors vs. induced errors: how best to structure students' error generation to promote learning? Learn Instr. 2026;104:102356. Sinha T, Kapur M. When problem solving followed by instruction works: evidence for productive failure. Rev Educ Res. 2021;91:761–798. Abd‐alrazaq A, AlSaad R, Alhuwail D, Ahmed A, Healy PM, Latifi S, et al. Large language models in medical education: opportunities, challenges, and future directions. JMIR Med Educ. 2023;9:e48291. Cross J, Kayalackakom T, Robinson RE, Vaughans A, Sebastian R, Hood R, et al. Assessing ChatGPT's capability as a new age standardized patient: qualitative study. JMIR Med Educ. 2025;11:e63353. Gordon M, Daniel M, Ajiboye A, Uraiby H, Xu NY, Bartlett R, et al. A scoping review of artificial intelligence in medical education: BEME Guide No. 84. Med Teach. 2024;46:446–470. McCarrick CA, McEntee PD, Boland PA, Donnelly S, O'Meara Y, Heneghan H, et al. A randomized controlled trial of a deep language learning model‐based simulation tool for undergraduate medical students in surgery. J Surg Educ. 2025;82:103629. Wu D, Xiang Y, Wu X, Yu T, Huang X, Zou Y, et al. Artificial intelligence‐tutoring problem‐based learning in ophthalmology clerkship. Ann Transl Med. 2020;8:700. Zaidi NB, Hwang C, Scott S, Stallard S, Purkiss J, Hortsch M. Climbing Bloom's taxonomy pyramid: lessons from a graduate histology course. Anat Sci Educ. 2017;10:456. Artino AR, La Rochelle JS, Dezee KJ, Gehlbach H. Developing questionnaires for educational research: AMEE Guide No. 87. Med Teach. 2014;36:463–474. Nikiforova T, Carter A, Yecies E, Spagnoletti CL. Best practices for survey use in medical education: how to design, refine, and administer high‐quality surveys. South Med J. 2021;114:567–571. Alkhadim GS. Cronbach's alpha and semantic overlap between items: a proposed correction and tests of significance. Front Psychol. 2022;13:815490. Vokinger KN, Stekhoven DJ, Krauthammer M. Lost in anonymization—a data anonymization reference classification merging legal and technical considerations. Journal of Law, Medicine & Ethics. 2020;48:228–231. Biggs J. Enhancing teaching through constructive alignment. High Educ (Dordr). 1996;32:347–364. Masters K, Salcedo D. A checklist for reporting, reading and evaluating artificial intelligence technology enhanced learning (AITEL) research in medical education. Med Teach. 2024;46:1175–1179. |
| Grant Information: | JYTZD2023145 the Science and Technology Research Project of Department of Education of Liaoning Province; 2024JH2/102500059 ), the Science and Technology Key Research Project of Liaoning Province; CXZH2024134 Research Project on Integrated Traditional Chinese and Western Medicine for Chronic Disease Management; LJ212510164020 the Basic scientific research project of Liaoning Provincial Department of Education; 2025-BS-0864 the Doctoral Start-up Foundation of Liaoning Province, China; 2025YB02 the Undergraduate Teaching Reform Research Project of Shenyang Medical College |
| Contributed Indexing: | Keywords: artificial intelligence (AI); histology; morphologic reasoning; prompt‐guided learning; verification; virtual microscopy |
| Entry Date(s): | Date Created: 20260630 Date Completed: 20261011 Latest Revision: 20261016 |
| Update Code: | 20261017 |
| DOI: | 10.1002/ase.70297 |
| PMID: | 42376779 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1935-9780 |
|---|---|
| DOI: | 10.1002/ase.70297 |