The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index; 13 of the 23 sources its claims cite were checked for support.
Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial
Open accessPublished version of a preprint
Abstract
A nonrandomized controlled trial with fourth-year medical students showed that engaging with AI-simulated patients using LLMs and automated feedback resulted in significantly higher scores on the pre-CC OSCE medical interview compared with the control group (mean 28.1 vs 27.1, P=.01).
Overview
CoChat Summary
TL;DR
In a nonrandomized controlled trial at Okayama University, fourth-year medical students who practiced medical interviews with GPT-4 Turbo AI-simulated patients plus feedback scored significantly higher on pre-CC OSCE medical interview scores than historical controls. The authors conclude the AI training was safe and educationally effective but limited for nonverbal communication and should be used as a supplementary tool to traditional simulation education.
Key findings
- The AI group (n=35) scored higher than the control group (n=110) on pre-CC OSCE medical interviews: total score mean 28.1, SD 1.6 vs 27.1, SD 2.2; P=.01; summary evaluation 4.8, SD 0.7 vs 4.5, SD 0.7; P=.007. The calculated effect size was 0.48.
- SBT-QA10 scores were relatively high across items (median 4–5) with no significant pre-to-post changes. A trend of inverse correlation appeared between SBT-QA10 and pre-CC OSCE scores; the item “I felt part of the team” was significant pre (β –1.8, SE 0.77; P=.047; R²=0.41) and post (β –3.2, SE 0.54; P<.001; R²=0.81), while total SBT-QA10 scores showed negative but nonsignificant coefficients (–2.0 to –2.1).
- Postcase questionnaires showed median reproducibility of the AI-simulated patient ranging from 7 to 9 and emotional interaction from 7 to 8. For the first case instance (n=32), 75% (n=24) rated difficulty as “appropriate,” 19% (n=6) “difficult,” 3% (n=2) each “easy” and “very easy,” and 0% “very difficult.” No significant safety concerns were observed.
- The authors report an MCID reference value of 26.9; the control group’s average was approximately equal to this, while the intervention group significantly exceeded it.
Methods
- Nonrandomized controlled trial with fourth-year medical students in Japan. The intervention group comprised 35 students in 2023 who consented and completed at least one AI-simulated patient practice; the control group comprised 110 students from 2022 who received only traditional education. Practice period was 1 month, followed by the pre-CC OSCE.
- The AI platform used GPT-4 Turbo integrated with “miibo” and LINE, with text-based chat and possible voice input. Prompts covered basic structure, case information, and feedback; emotional parameters were set from 1 to 10 for 8 emotions. Cases were based on 8 primary symptoms.
- Analysis used Prism 9; Mann-Whitney U, Fisher exact, Student t, Wilcoxon, and multiple regression. Primary outcome was pre-CC OSCE medical interview scores (summary and total); secondary outcomes included SBT-QA10 and postcase questionnaires. Cohen d was calculated for effect size.
Limitations
- Stated in the paper: the study was nonrandomized and voluntary, used different academic years, had a limited sample size, and only some consenting students actually participated. Assessment was indirect and short-term via pre-CC OSCE rather than real clinical settings; the text-based platform restricts nonverbal communication; LLM fabrications and opaque technology require caution and monitoring; SBT-QA10 is based on Western cultures and may need different interpretation; subgroup findings may be influenced by extreme values and lost significance when the comparison group changed.
- Evident from the text: the historical control group from 2022 may introduce cohort or secular confounding despite similar GPA, age, and sex; only 35 of 87 consenting students participated in the AI group; the SBT-QA10 was partially modified rather than used directly; and the pre-CC OSCE passing score was not disclosed.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
10 Valid · 2 Not valid · 8 Not checked · 53 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, the pre-CC OSCE has shown a significant correlation with performance during clinical clerkships in Japanese medical student cohorts [15].”
§ Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial > Introduction
What the sources say
- Supportedcites [15] source
The Correlations of OSCE and CBT scores with CC scores section reports that total OSCE scores were significantly correlated with clinical clerkship scores (P<0.001). The Study population section establishes that these Japanese medical students took the OSCE before their clerkships. The study was conducted at one institution. (LLM, conf=0.94)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“As previously reported, medical students do not resist the use of AI in medical education [21], which was evident in this study.”
§ Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial > Discussion
What the sources say
- Partly supportedcites [21] sourceExperimental — accuracy not yet measured
The Results (page unavailable) say that students thought generative AI could assist their learning, which supports a positive attitude toward its use. The paper does not establish that medical students generally do not resist AI in medical education; that broader claim goes beyond the reported views. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“This cultural difference may have influenced the results significantly [25,26].”
§ Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial > Discussion > Association Between Pre-CC OSCE Scores and AI Educational Interventions
What the sources say
- Not checked — no full text of the sourcecites [25] source
- Partly supportedcites [26] sourceExperimental — accuracy not yet measured
The passage on cultural orientation and immigration status (section labeled Abstract; page unavailable) identifies cultural differences as one explanatory factor in the Asian–white academic-effort gap. It attributes 20–30% of the jointly explained gap to cultural orientation, but does not establish that a cultural difference significantly influenced the citing paper’s unspecified results. (LLM, conf=0.80)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“People from Asian cultures have been reported to be stricter in self-evaluations.”
§ Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial > Discussion > Association Between Pre-CC OSCE Scores and AI Educational Interventions
What the sources say
- Not checked — no full text of the sourcecites [25] source
- Partly supportedcites [26] sourceExperimental — accuracy not yet measured
The passage discussing psychological costs (labeled Abstract; page unavailable) says Asian-American youth hold extraordinarily high expectations for themselves and may feel unsatisfied even when they excel. The Fig. 7 passage reports that they rate their positive feelings toward themselves lower than white peers. These findings are consistent with harsher self-assessment, but the paper does not directly measure strictness in self-evaluation or establish the claim for people from Asian cultures generally. (LLM, conf=0.82)
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Specifically, Japanese medical students often feel a strong inclination to meet others’ expectations when explaining the research, leading them to provide consent [30].”
§ Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial > Discussion > Limitations
What the sources say
- Partly supportedcites [30] sourceExperimental — accuracy not yet measured
The Discussion’s literature review of Japanese culture (page not provided) describes social pressure to cooperate and conform to group decisions. It does not address Japanese medical students, explanations of research, or whether a desire to meet others’ expectations leads students to consent. (LLM, conf=0.82)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
31 more claims · 1 with their cited sources checked
Create a free account to see all 73 claims and to verify the 1 reference still open.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“LLM-generated simulations demonstrate clinically relevant psychiatric exchanges [23-25] and generate automated feedback aligned with expert judgment [26], offering a cost-efficient and scalable alternative to real patients for clinical training.”
From Enhancing Psychiatry Training Using an Agentic AI Simulated Consultation Tool: Prospective Cohort Study (2026) · cites this paper as [25]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Prior studies have demonstrated the technical feasibility of text-based VSPs and AI-assisted automated scoring systems.”
From Development and Validation of CPX-MATE: An End-to-End Medical Education Platform Integrating Voice-Based Virtual Patient Simulation and Automated Real-time Evaluation (2026) · cites this paper as [9]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“75%(n=24) of the responses indicated it was “appropriate,” 19%(n=6) found it “difficult,” 3%(n=2) each considered it “easy” and “very easy,” and 0% (n=0) found it “very difficult” in the first instance of the case (n=32).”
§ Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial > Results
Reported 32 · recomputed 34
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial > Methods > Statistical Analysis
“total score evaluation, scored from 1 to 31 points”
§ Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial > Results
“maximum 31 points, minimum 0 points graded”
Citations
Cites
The assessment of clinical skills/competence/performance
Miller, G. E. (1990) · Academic Medicine · doi:10.1097/00001888-199009000-00045 · Cited by 4,883
Hattie, J. (2008) · doi:10.4324/9780203887332 · Cited by 3,051
Emotion: A Psychoevolutionary Synthesis
Camras, L., & Plutchik, R. (1980) · The American Journal of Psychology · doi:10.2307/1422394 · Cited by 2,487 · cited 1×
“The emotional parameters were set from 1 to 10 for 8 emotions—joy, sadness, anticipation, surprise, fear, disgust, trust, and anger—based on Ekman et al’s [16] theory and Plutchik’s [17] work.”
MethodGilson, A., Safranek, C. W., Huang, T., Socrates, V., Chi, L., Taylor, R. A., & Chartash, D. (2023) · JMIR Medical Education · doi:10.2196/45312 · Cited by 2,078 · cited 1×
“One study demonstrated that LLMs can accurately answer questions of the United States Medical Licensing Examination (USMLE), demonstrating their use in medical education and assessment [10].”
BackgroundPan-cultural elements in facial displays of emotion
Ekman, P., Sorenson, E. R., & Friesen, W. V. (1969) · Science · doi:10.1126/science.164.3875.86 · Cited by 1,775 · cited 1×
“The emotional parameters were set from 1 to 10 for 8 emotions—joy, sadness, anticipation, surprise, fear, disgust, trust, and anger—based on Ekman et al’s [16] theory and Plutchik’s [17] work.”
MethodTopping, K. J. (1996) · Higher Education · doi:10.1007/bf00138870 · Cited by 1,166
Eysenbach, G. (2023) · JMIR Medical Education · doi:10.2196/46885 · Cited by 840 · cited 1×
“Although concerns about fabrication by LLMs have been raised in various contexts [27], their occurrence in this study was limited, and no expressions deviating from the case settings were observed.”
BackgroundEducational strategies in curriculum development: the SPICES model
HARDEN, R. M., SOWDEN, S., & DUNN, W. R. (1984) · Medical Education · doi:10.1111/j.1365-2923.1984.tb01024.x · Cited by 772
Engineering Education in the Era of ChatGPT: Promise and Pitfalls of Generative AI for Education
Qadir, J. (2023) · 2023 IEEE Global Engineering Education Conference (EDUCON) · doi:10.1109/educon54358.2023.10125121 · Cited by 707
The use of simulated patients in medical education: AMEE Guide No 42
Cleland, J. A., Abe, K., & Rethans, J.-J. (2009) · Medical Teacher · doi:10.1080/01421590903002821 · Cited by 509 · cited 2×
“The standard practice method involves learning medical interviewing in lectures, followed by practice sessions under the supervision of instructors and simulated patients [4].”
Method
Research works printed but not linked: 3
- Abe, K, 2007, Med Educ (Japan), 38, 301
- Hinkle, DE, 2003, Applied Statistics for the Behavioral Sciences. 5th ed
- Cohen, J, 1988, Statistical Power Analysis for the Behavioral Sciences. 2nd Edition
Cited by
Tekïn, M., Yurdal, M. O., Toraman, Ç., Korkmaz, G., & Uysal, İ. (2025) · BMC Medical Education · doi:10.1186/s12909-025-07241-4 · Cited by 65
“However, its performance in auditory and multimodal tasks highlighted limitations, consistent with findings from Chan & Tsi [1] and Yama-moto et al. [25].”
Zeng, J., Qi, W., Shen, S., Liu, X., Li, S., Wang, B., Dong, C., Zhu, X., Shi, Y., Lou, X., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/79091 · Cited by 76
“…or abdominal pain or cough or heartburn or fatigue or fever or dizziness or shortness of breath General medicine Interviewing skills Yamamoto et al [48] Patient with cardiac conditions Cardiology and emergency medicine Empathic expression Aster et al [49] Patient with rheumatic disease…”
Roveta, A., Castello, L. M., Massarino, C., Francese, A., Ugo, F., & Maconi, A. (2025) · AI · doi:10.3390/ai6090227 · Cited by 60
“Conversational agents simulating patient interactions enhanced both clinical reasoning and OSCE performance ( p = 0.049 and p = 0.01, respectively) [21,22].”
InfluentialLee, H.-Y., Kim, J., Choi, H., Bae, H., Jeong, A., Choi, S., Kim, J.-H., & Kim, C.-E. (2025) · BMC Medical Education · doi:10.1186/s12909-025-08308-y · Cited by 36
“Second, to maximize learning outcomes, it is essential to integrate a structured debriefing session with peers or tutors following the chatbot training [40].”
Jacobs, C., Johnson, H., Tan, N., Brownlie, K., Joiner, R., & Thompson, T. (2025) · JMIR Medical Education · doi:10.2196/70766 · Cited by 20
Metadata
- Authors
- Yamamoto, A., Koda, M., Ogawa, H., Miyoshi, T., Maeda, Y., Otsuka, F., & Ino, H.
- Affiliations
- Okayama University Hospital (JP)
- Okayama University (JP)
- Corresponding author
- Yamamoto, Akira
- ORCID
- Venue
- JMIR Medical Education
- Publisher
- JMIR Publications Inc.
- Published
- 2024-09-23
- Volume
- 10
- Pages
- e58753
- ISSN
- 2369-3762 (ISSN-L)
- PMC
- PMC11459107
- OpenAlex
- W4401610634
- Cited by
- 92
- References
- 24
- Citations by year
- 2026: 61 · 2025: 30 · 2024: 1
- FWCI
- 8.56
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JMIR Medical Education (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Okayama University Scientific Achievement Repository (Okayama University) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Institutional Repositories DataBase (IRDB) (submittedVersion, cc-by)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Social Sciences › Education › Simulation-Based Education in Healthcare
- Social Sciences › Education › Innovations in Medical Education
- Keywords
- medical interviewing skills, large language models, simulation-based training, medical students, OSCE, feedback, nonverbal communication, medical education
- MeSH terms
- Simulation Training, Artificial Intelligence, Clinical Competence, Education, Medical, Undergraduate, Educational Measurement, Female, Humans, Interviews as Topic, Japan, Male, Students, Medical, Patient Simulation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial. https://app.cochat.ai/papers/10.2196/58753
- The paper
- Yamamoto, A., Koda, M., Ogawa, H., Miyoshi, T., Maeda, Y., Otsuka, F., & Ino, H. (2024). Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial. JMIR Medical Education. https://doi.org/10.2196/58753
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.