The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Enhancing self-directed learning with custom GPT AI facilitation among medical students: A randomized controlled trial
Abstract
Objective This study aims to assess the impact of LearnGuide, a specialized ChatGPT tool designed to support self-directed learning among medical students.Materials and methods In this 14-week randomized controlled trial (ClinicalTrials.gov NCT06276049), 103 medical students were assigned to either an intervention group, which received 12 weeks of problem-based training with LearnGuide support, or a control group, which received identical training without AI assistance. Primary and secondary outcomes, including Self-Directed Learning Scale scores at 6 and 12 weeks, Cornell Critical Thinking Test Level Z scores, and Global Flow Scores, were evaluated with a 14-week follow-up. Mann-Whitney U tests were used for statistical comparisons between the groups.Results At 6 weeks, the intervention group showed a marginally higher median Self-Directed Learning Scale score, which further improved by 12 weeks (4.15 [95% CI, 0.82 to 7.48]; p = 0.01) and was sustained at the 14-week follow-up. Additionally, this group demonstrated notable improvements in the Cornell Critical Thinking Test Score at 12 weeks (7.11 [95% CI, 4.50 to 9.72]; p < 0.001), which persisted into the 14-week follow-up. The group also experienced enhancements in the Global Flow Score from 6 weeks, maintaining superiority over the control group through 12 weeks.Conclusions LearnGuide significantly enhanced self-directed learning, critical thinking, and flow experiences in medical students, highlighting the crucial role of AI tools in advancing medical education.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“The Cornell Critical Thinking Test Level Z was one of the few standardized assessments employed, serving as a benchmark to quantify CT skills [59,70].”
From A Systematic Literature Review on the Pedagogical Implications and Impact of GenAI on Students' Critical Thinking (2026) · cites this paper as [59]
In the citing paper
“These interventions embedded GenAI within learning platforms to generate real-time hints, guiding questions, automated scoring, or corrective feedback in response to student inputs [32,47,49,59].”
From A Systematic Literature Review on the Pedagogical Implications and Impact of GenAI on Students' Critical Thinking (2026) · cites this paper as [59]
In the citing paper
“In project-based contexts, GenAI was embedded across multiple stages of project development, including idea generation, planning, analysis, and drafting [50,59].”
From A Systematic Literature Review on the Pedagogical Implications and Impact of GenAI on Students' Critical Thinking (2026) · cites this paper as [59]
In the citing paper
“Other tools such as Gemini, Ernie Bot, and multi-tool workflows were less common [61,70], and a few studies developed custom GPT-based systems ( [50,59,84,89,90]).”
From A Systematic Literature Review on the Pedagogical Implications and Impact of GenAI on Students' Critical Thinking (2026) · cites this paper as [59]
In the citing paper
“For example, Shalong et al. [59] employed the Cornell Critical Thinking Test Level Z to measure changes over six, 12, and 14 weeks, reporting significant improvements on both SDL and CT scores of approximately 13%, which was sustained at follow-up.”
From A Systematic Literature Review on the Pedagogical Implications and Impact of GenAI on Students' Critical Thinking (2026) · cites this paper as [59]
Citations
Cites
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
Taylor, D. C. M., & Hamdy, H. (2013) · Medical Teacher · doi:10.3109/0142159x.2013.828153 · Cited by 1,176 · cited 1×
“Self-directed learning (SDL) is delineated by the capacity and motivation of learners to establish and pursue their individual learning objectives, as well as to evaluate their progress and outcomes [1].”
Bond, M., Buntins, K., Bedenlier, S., Zawacki-Richter, O., & Kerres, M. (2020) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-019-0176-8 · Cited by 1,097 · cited 2×
“However, by 12 weeks, the intervention group exhibited a significant improvement (33.5 [29.0-39.5] vs. 27.0 [22.5-29.0]; 7.11 [95% CI, 4.50 to 9.72]; p < 0.001), which remained significant at the 14-week follow-up (6.00 [95% CI, 3.97 to 8.02]; p < 0.001).”
InfluentialCognitive Load Theory: Implications for medical education: AMEE Guide No. 86
Young, J. Q., Van Merrienboer, J., Durning, S., & Ten Cate, O. (2014) · Medical Teacher · doi:10.3109/0142159x.2014.889290 · Cited by 935 · cited 2×
“On the other hand, excessively high intrinsic cognitive load can cause frustration and diminish motivation, whereas insufficiently challenging tasks may not fully engage the learner ’ s capabilities [23].”
InfluentialFlow, performance and moderators of challenge-skill balance
Engeser, S., & Rheinberg, F. (2008) · Motivation and Emotion · doi:10.1007/s11031-008-9102-4 · Cited by 860 · cited 1×
“The Global Flow Score (GFS) is calculated by averaging the scores of the ten items on the Flow State Scale [18].”
Ethical Considerations of Using ChatGPT in Health Care
Wang, C., Liu, S., Yang, H., Guo, J., Wu, Y., & Liu, J. (2023) · Journal of Medical Internet Research · doi:10.2196/48009 · Cited by 541 · cited 1×
“However, the extensive use of ChatGPT in learning has raised concerns among some educators that its use could lead to overreliance [13,14], potentially hindering the development of essential learning skills.”
Investigating the impact of user trust on the adoption and use of ChatGPT: Survey analysis
Choudhury, A., & Shamszare, H. (2023) · Journal of Medical Internet Research · doi:10.2196/47184 · Cited by 470 · cited 1×
“However, the extensive use of ChatGPT in learning has raised concerns among some educators that its use could lead to overreliance [13,14], potentially hindering the development of essential learning skills.”
Online education in the post-COVID era
Lockee, B. B. (2021) · Nature Electronics · doi:10.1038/s41928-020-00534-0 · Cited by 430 · cited 1×
“Throughout the COVID-19 pandemic, the educational landscape experienced a significant shift from traditional in-person instruction to online learning platforms [2].”
Cheung, B. H. H., Lau, G. K. K., Wong, G. T. C., Lee, E. Y. P., Kulkarni, D., Seow, C. S., Wong, R., & Co, M. T.-H. (2023) · PLOS ONE · doi:10.1371/journal.pone.0290691 · Cited by 195
ChatGPT—A Challenging Tool for the University Professors in Their Teaching Practice
Kiryakova, G., & Angelova, N. (2023) · Education Sciences · doi:10.3390/educsci13101056 · Cited by 171 · cited 1×
“Its increasing popularity among medical educators and students has led to improvements in the creation of multiple-choice questions [7], teaching evaluations [8], and”
Cited by
Xia, Q., Liu, Q., Tlili, A., & Chiu, T. K. F. (2025) · Computers & Education · doi:10.1016/j.compedu.2025.105465 · Cited by 88
Izquierdo-Condoy, J. S., Arias-Intriago, M., Tello-De-la-Torre, A., Busch, F., & Ortiz-Prado, E. (2025) · Journal of Medical Internet Research · doi:10.2196/76340 · Cited by 87
“Shalong et al [30] demonstrated that LearnGuide, a ChatGPT-based facilitator, improved scores on the Cornell Critical Thinking Test (+7.11; P <.001), self-directed learning (+4.15; P =.01), and cognitive flow in problem-based learning environments.”
InfluentialArtificial Intelligence in Health Professions Education assessment: AMEE Guide No. 178
Masters, K., MacNeil, H., Benjamin, J., Carver, T., Nemethy, K., Valanci-Aroesty, S., Taylor, D. C. M., Thoma, B., & Thesen, T. (2025) · Medical Teacher · doi:10.1080/0142159x.2024.2445037 · Cited by 80
“In addition, they reduce extraneous load by providing solutions to complex and unfamiliar concepts tailored to the learner’s knowledge base [57].”
Wei, H., Dai, Y., Yuan, K., Li, K. Y., Hung, K. F., Hu, E. M., Lee, A. H. C., Chang, J. W. W., Zhang, C., & Li, X. (2025) · International Dental Journal · doi:10.1016/j.identj.2025.100858 · Cited by 80
“Regarding the application scenarios of AI technology in PBL/CBL, 4 out of the 6 included studies used ITSs including COMET, 30 CC-Crusier, 32 LearnGuide 34 and ChatGPT.”
InfluentialOmar, M., Nadkarni, G. N., Klang, E., & Glicksberg, B. S. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000662 · Cited by 71
Metadata
- Authors
- Shalong, W., Yi, Z., Bin, Z., Ganglei, L., Jinyu, Z., Yanwen, Z., Zequn, Z., Lianwen, Y., & Feng, R.
- Affiliations
- Department of General Surgery, The Second Xiangya Hospital of Central South University
- Hunan University of Finance and Economics (CN)
- Changsha Central Hospital (CN)
- Second Xiangya Hospital of Central South University (CN)
- Corresponding author
- Feng, Ren
- Venue
- Medical Teacher
- Publisher
- Informa UK Limited
- Published
- 2024-10-19
- Volume
- 47
- Issue
- 7
- Pages
- 1126-1133
- ISSN
- 0142-159X (ISSN-L)
- 1466-187X
- OpenAlex
- W4403561329
- Cited by
- 45
- References
- 31
- Citations by year
- 2026: 27 · 2025: 17 · 2024: 1
- FWCI
- 4.26
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Medical Teacher (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Ministry of Education’s Humanities and Social Sciences Young Researcher Fund Project
- Degree & Postgraduate Education Reform Project of Central South University
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Social Sciences › Education › Innovations in Medical Education
- Social Sciences › Education › Artificial Intelligence in Education
- Keywords
- self-directed learning, ChatGPT, AI-assisted learning, medical students, problem-based learning, critical thinking, flow experience, medical education
- MeSH terms
- Self-Directed Learning as Topic, Adult, Education, Medical, Undergraduate, Female, Humans, Male, Students, Medical, Problem-Based Learning, Young Adult
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.
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 self-directed learning with custom GPT AI facilitation among medical students: A randomized controlled trial. https://app.cochat.ai/papers/10.1080/0142159x.2024.2413023
- The paper
- Shalong, W., Yi, Z., Bin, Z., Ganglei, L., Jinyu, Z., Yanwen, Z., Zequn, Z., Lianwen, Y., & Feng, R. (2025). Enhancing self-directed learning with custom GPT AI facilitation among medical students: A randomized controlled trial. Medical Teacher. https://doi.org/10.1080/0142159x.2024.2413023
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.