OpenEvidence: Enhancing Medical Student Clinical Rotations With AI but With Limitations
Open accessAbstract
The integration of artificial intelligence (AI) into healthcare has introduced tools that improve medical education and clinical practice. OpenEvidence is an example, providing real-time synthesis and access to medical literature, particularly for medical students during clinical rotations. By enabling efficient searches for clinical guidelines, diagnostic criteria, and therapeutic approaches, it streamlines decision-making and study preparation. Its ability to present recent publications and highlight less commonly discussed treatments supports evidence-based learning. Despite these strengths, OpenEvidence has limitations. It struggles with targeted searches for specific articles, authors, or journals and operates through an opaque curation process. Compared to ChatGPT, which offers conversational interactivity, and UpToDate, known for its comprehensive, CME-accredited content, OpenEvidence lacks certain advanced features. However, its user-friendly design and focus on clinical evidence make it a valuable, accessible alternative. This editorial critically examines OpenEvidence's capabilities and limitations, comparing it with established tools. It emphasizes the need for greater transparency, broader evidence integration, and enhanced functionality to maximize its impact. Addressing these challenges could improve OpenEvidence's utility, supporting a more effective, evidence-based approach to medical education and clinical practice.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 medical education settings, OpenEvidence and similar platforms have been reported to assist students integrate guideline-based reasoning and efficiently locate relevant literature during clinical rotations.
“In medical education settings, OpenEvidence and similar platforms have been reported to assist students integrate guideline-based reasoning and efficiently locate relevant literature during clinical rotations (Patel et al. 2025).”
From Evidence on Demand: OpenEvidence versus Established LLMs on the Orthopaedic In-Training Examination (2026) · cites this paper as Patel et al. 2025
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Ethical Issues of Artificial Intelligence in Medicine and Healthcare
Farhud, D. D., & Zokaei, S. (2021) · Iranian Journal of Public Health · doi:10.18502/ijph.v50i11.7600 · Cited by 416 · see citing works
Xu, H., & Shuttleworth, K. M. J. (2024) · Intelligent Medicine · doi:10.1016/j.imed.2023.08.001 · Cited by 196 · see citing works
Flagged first, then by citations
Research works printed but not linked: 13
- [1]Leveraging physiology and artificial intelligence to deliver advancements in health care Physiol Rev Zhang A Wu Z Wu E Wu M Snyder MP Zou J Wu JC 2423 2450 103 2023 https://doi.org/10.1152/physrev.00033.2022 37104717 PMC10390055 · DOI
- [3]A double-blind study of adjuvant buspirone hydrochloride in clomipramine-treated patients with obsessive-compulsive disorder J Clin Psychopharmacol Pigott TA L'Heureux F Hill JL Bihari K Bernstein SE Murphy DL 11 18 12 1992 1552034
- [4]Subantimicrobial dose doxycycline in the treatment of recurrent oral aphthous ulceration: a pilot study J Oral Pathol Med Preshaw PM Grainger P Bradshaw MH Mohammad AR Powala CV Nolan A 236 240 36 2007 17391302
- [5]Erdheim-Chester disease: a comprehensive review of the literature Orphanet J Rare Dis Mazor RD Manevich-Mazor M Shoenfeld Y 137 8 2013 https://doi.org/10.1186/1750-1172-8-137 24011030 PMC3849848 · DOI
- [6]Pathognomonic neuroradiological signs in Wilson's disease - truth or myth? Parkinsonism Relat Disord Rędzia-Ogrodnik B Członkowska A Antos A 105247 107 2023 https://doi.org/10.1016/j.parkreldis.2022.105247 36543734 · DOI
- [7]Burnout in medical school: a medical student's perspective Acad Radiol Morcos G Awan OA 1223 1225 30 2023 https://doi.org/10.1016/j.acra.2022.11.023 36586757 PMC9799176 · DOI
- [9]Buspirone augmentation of fluoxetine in obsessive-compulsive disorder Am J Psychiatry Markovitz PJ Stagno SJ Calabrese JR 798 800 147 1990 https://doi.org/10.1176/ajp.147.6.798 2188516 · DOI
- [11]Critical analysis of the AI impact on the patient-physician relationship: a multi-stakeholder qualitative study Digit Health Čartolovni A Malešević A Poslon L 9 2023 https://doi.org/10.1177/20552076231220833 PMC10734361 38130798 · DOI
- [12]Exploring the impact Front Educ Bettayeb AM Abu Talib M Sobhe Altayasinah AZ 1379796 9 2024 https://doi.org/10.3389/feduc.2024.1379796 · DOI
- [13]Artificial intelligence and human trust in healthcare: focus on clinicians J Med Internet Res Asan O Bayrak AE Choudhury A 0 22 2020 https://doi.org/10.2196/15154 PMC7334754 32558657 · DOI · Paper page
- [14]Depiction of diaphragmatic muscle slips on supine plain radiographs: a sign of pneumoperitoneum Radiology Cho KC Baker SR 431 433 203 1997 https://doi.org/10.1148/radiology.203.2.9114100 9114100 · DOI
- [17]Technology can augment, but not replace, critical human skills needed for patient care Acad Med Alrassi J Katsufrakis PJ Chandran L 37 43 96 2021 https://doi.org/10.1097/acm.0000000000003733 32910005 · DOI · Paper page
- [18]The imperative for regulatory oversight of large language models (or generative AI) in healthcare NPJ Digit Med Meskó B Topol EJ 120 6 2023 https://doi.org/10.1038/s41746-023-00873-0 37414860 PMC10326069 · DOI · Paper page
Cited by
Sorted by citations
Avrumova, F., Cesar, M. D., Loggia, G., Strebel, K., Altorfer, F. C., Castro, R. I., Zhu, J., Abjornson, C., Bono, C. M., & Lebl, D. R. (2026) · The Spine Journal · doi:10.1016/j.spinee.2026.08.002
Evidence on Demand: OpenEvidence versus Established LLMs on the Orthopaedic In-Training Examination
Khan, A. A., Lalvani, S. S., Pourarbab, S., Hyeamang, L. J., Lew, R. M., Hussain, Z. B., Nicholson, G. P., & Garrigues, G. E. (2026) · Journal of Orthopaedic Experience & Innovation · doi:10.60118/001c.162882
- Authors
- Patel, N., Grewal, H., Buddhavarapu, V., & Dhillon, G.
- Affiliations
- Florida State University (US)
- Corresponding author
- Patel, Niket
- Venue
- Cureus
- Published
- 2025-01-03
- Volume
- 17
- Issue
- 1
- Pages
- e76867-e76867
- ISSN
- 2168-8184 (ISSN-L)
- PMC
- PMC11787857
- OpenAlex
- W4406046625
- Cited by
- 14
- References
- 2
- Citations by year
- 2026: 10 · 2025: 4
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- Locations
- Cureus (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › General Health Professions › Health Sciences Research and Education
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Innovations in Medical Education
- Keywords
- OpenEvidence, artificial intelligence in medical education, clinical rotations, medical students, evidence-based medicine, clinical decision support, medical literature searching, clinical guidelines, UpToDate, ChatGPT
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
