CoChat
Sign Up
Cited by 135Artificial Intelligence in Healthcare and EducationArtificial Intelligence in HealthcareArtificial Intelligence Applications

Impact of large language model (ChatGPT) in healthcare: an umbrella review and evidence synthesis

Open access
Iqbal, Usman, Tanweer, Afifa, Rahmanti, Annisa Ristya, Greenfield, David, Lee, Leon Tsung-Ju, Li, Yu-Chuan Jack·2025·Journal of Biomedical Science
DOI 10.1186/s12929-025-01131-zPMC PMC12057020
Open this paper in CoChat — free accountOpen PDF

Abstract

Background: The emergence of Artificial Intelligence (AI), particularly Chat Generative Pre-Trained Transformer (ChatGPT), a Large Language Model (LLM), in healthcare promises to reshape patient care, clinical decision-making, and medical education. This review aims to synthesise research findings to consolidate the implications of ChatGPT integration in healthcare and identify research gaps. Main body: The umbrella review was conducted following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The Cochrane Library, PubMed, Scopus, Web of Science, and Google Scholar were searched from inception until February 2024. Due to the heterogeneity of the included studies, no quantitative analysis was performed. Instead, information was extracted, summarised, synthesised, and presented in a narrative form. Two reviewers undertook title, abstract, and full text screening independently. The methodological quality and overall rating of the included reviews were assessed using the A Measurement Tool to Assess systematic Reviews (AMSTAR-2) checklist. The review examined 17 studies, comprising 15 systematic reviews and 2 meta-analyses, on ChatGPT in healthcare, revealing diverse focuses. The AMSTAR-2 assessment identified 5 moderate and 12 low-quality reviews, with deficiencies like study design justification and funding source reporting. The most reported theme that emerged was ChatGPT's use in disease diagnosis or clinical decision-making. While 82.4% of studies focused on its general usage, 17.6% explored unique topics like its role in medical examinations and conducting systematic reviews. Among these, 52.9% targeted general healthcare, with 41.2% focusing on specific domains like radiology, neurosurgery, gastroenterology, public health dentistry, and ophthalmology. ChatGPT’s use for manuscript review or writing was mentioned in 17.6% of reviews. Promising applications include enhancing patient care and clinical decision-making, though ethical, legal, and accuracy concerns require cautious integration. Conclusion: We summarise the identified areas in reviews regarding ChatGPT's transformative impact in healthcare, highlighting patient care, decision-making, and medical education. Emphasising the importance of ethical regulations and the involvement of policymakers, we urge further investigation to ensure the reliability of ChatGPT and to promote trust in healthcare and research.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s12929-025-01131-z

Cites

9 of 9 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Inconsistent evaluation standards obstruct generalisability and regulatory oversight.

    “Methodological reviews11,35 identified an additional challenge: inconsistent evaluation standards obstruct generalisability and regulatory oversight.”

    From Generative Artificial Intelligence in Healthcare: Automation Bias, Deskilling, and Cognitive Implications – A Systematic Review (2026) · cites this paper as [35]

    The Discussion (page unavailable) says that reconciling methodological inconsistencies across studies was challenging and that addressing the review’s limitations would improve the applicability of its findings. The Conclusions call for robust regulations, but the paper does not say that inconsistent evaluation standards obstruct regulatory oversight; it also does not directly establish an effect on generalisability. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • Frameworks developed in studies enhance methodological theory by incorporating AI ethics, transparency, and bias mitigation into evidence appraisal models like PRISMA-AI and CLASMOD-AI.

    “Moreover, frameworks developed in studies4,11,35 enhance methodological theory by incorporating AI ethics, transparency, and bias mitigation into evidence appraisal models like PRISMA-AI and CLASMOD-AI.”

    From Generative Artificial Intelligence in Healthcare: Automation Bias, Deskilling, and Cognitive Implications – A Systematic Review (2026) · cites this paper as [35]

    The Methods and Results describe using PRISMA guidelines and AMSTAR-2 to conduct and appraise the review. The Discussion calls for ethical frameworks, transparent data policies, and measures to address bias in healthcare AI, but our copy does not say these were incorporated into evidence-appraisal models or mention PRISMA-AI or CLASMOD-AI (searched those model names and the claimed methodological framework). (LLM, conf=0.76)

    Experimental — accuracy not yet measured

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

1 retracted

Flagged first, then by citations

Research works printed but not linked: 29

  1. [1]Ashraf H, Ashfaq H. The role of ChatGPT in medical research: progress and limitations. Ann Biomed Eng. 2023. 10.1007/s10439-023-03311-0. 37452215 · DOI
  2. [2]Bagde H, Dhopte A, Alam MK, Basri R. A systematic review and meta-analysis on ChatGPT and its utilization in medical and dental research. Heliyon. 2023;9(12): e23050. 10.1016/j.heliyon.2023.e23050. 38144348 PMC10746423 · DOI
  3. [3]Bečulić H, Begagić E, Skomorac R, Mašović A, Selimović E, Pojskić M. 2024. ChatGPT’s contributions to the evolution of neurosurgical practice and education: A systematic review of benefits, concerns and limitations. Medicinski Glasnik Ljekarske Komore Zenicko-Dobojskog Kantona. 10.17392/1661-23 37950660 · DOI
  4. [4]Bera K, O’Connor G, Jiang S, Tirumani SH, Ramaiya N. Analysis of ChatGPT publications in radiology: literature so far. Curr Probl Diagn Radiol. 2024;53(2):215–25. 10.1067/j.cpradiol.2023.10.013. 37891083 · DOI
  5. [5]Bugaj M, Kliestik T, Lăzăroiu G. Generative artificial intelligence-based diagnostic algorithms in disease risk detection, in personalized and targeted healthcare procedures, and in patient care safety and quality. Contemp Read Law Soc Justice. 2023;15(1):9–26. · DOI
  6. [6]Cao Y, Li S, Liu Y, Yan Z, Dai Y, Yu PS, Sun L. 2023. A comprehensive survey of AI-generated content (AIGC): a history of generative AI from GAN to ChatGPT (arXiv:2303.04226). arXiv. http://arxiv.org/abs/2303.04226 · arXiv
  7. [7]Cazzato G, Capuzzolo M, Parente P, Arezzo F, Loizzi V, Macorano E, Marzullo A, Cormio G, Ingravallo G. Chat GPT in diagnostic human pathology: will it be useful to pathologists? A preliminary review with ‘query session’ and future perspectives. AI. 2023;4(4):1010–22. 10.3390/ai4040051. · DOI
  8. [8]Choi GJ, Kang H. Introduction to umbrella reviews as a useful evidence-based practice. J Lipid Atherosclerosis. 2023;12(1):3. PMC9884555 36761061 · DOI
  9. [9]Gabashvili I. 2023. ChatGPT in dermatology: a comprehensive systematic review. medRxiv, 2023–06.
  10. [10]Garg RK, Urs VL, Agarwal AA, Chaudhary SK, Paliwal V, Kar SK. Exploring the role of ChatGPT in patient care (diagnosis and treatment) and medical research: a systematic review. Health Promot Perspect. 2023;13(3):183. 37808939 PMC10558973 · DOI
  11. [12]Harry A. The future of medicine: harnessing the power of AI for revolutionizing healthcare. Int J Multidis Sci Arts. 2023;2(1):36–47.
  12. [14]Javaid M, Haleem A, Singh RP. ChatGPT for healthcare services: an emerging stage for an innovative perspective. BenchCouncil Trans Benchmarks Standards Evaluat. 2023;3(1): 100105. · DOI · Paper page
  13. [15]Klang E, Sourosh A, Nadkarni GN, Sharif K, Lahat A. Evaluating the role of ChatGPT in gastroenterology: a comprehensive systematic review of applications, benefits, and limitations. Ther Adv Gastroenterol. 2023;16:17562848231218618. 10.1177/17562848231218618. PMC10750546 38149123 · DOI
  14. [16]Lee D, Yoon SN. Application of artificial intelligence-based technologies in the healthcare industry: opportunities and challenges. Int J Environ Res Public Health. 2021;18(1):271. 33401373 PMC7795119 · DOI · Paper page
  15. [17]Levin G, Horesh N, Brezinov Y, Meyer R. Performance of ChatGPT in medical examinations: a systematic review and a meta-analysis. Int J Obstet Gynaecol. 2024;131(3):378–80. 10.1111/1471-0528.17641. 37604703 · DOI
  16. [19]Mitsea E, Drigas A, Skianis C. Digitally assisted mindfulness in training self-regulation skills for sustainable mental health: a systematic review. Behav Sci. 2023;13(12):1008. 38131865 PMC10740653 · DOI
  17. [20]Muftić F, Kadunić M, Mušinbegović A, Abd Almisreb A. Exploring medical breakthroughs: a systematic review of ChatGPT applications in healthcare. Southeast Eur J Soft Comput. 2023;12(1):13–41.
  18. [21]Rao A, Kim J, Kamineni M, Pang M, Lie W, Succi MD. Evaluating ChatGPT as an adjunct for radiologic decision-making. medRxiv. 2023;16:2023–02. PMC10733745 37356806
  19. [22]Roman A, Al-Sharif L, Al Gharyani M. The expanding role of ChatGPT (chat-generative pre-trained transformer) in neurosurgery: a systematic review of literature and conceptual framework. Cureus. 2023. 10.7759/cureus.43502. 37719492 PMC10500385 · DOI
  20. [23]Roumeliotis KI, Tselikas ND. ChatGPT and open-AI models: a preliminary review. Future Internet. 2023;15(6):192. · DOI
  21. [27]Schopow N, Osterhoff G, Baur D. Applications of the natural language processing tool ChatGPT in clinical practice: comparative study and augmented systematic review. JMIR Med Inform. 2023;11: e48933. 38015610 PMC10716749 · DOI
  22. [29]Starcevic V, Berle D, Arnáez S. Recent insights into cyberchondria. Curr Psychiatry Rep. 2020;22(11):56. 10.1007/s11920-020-01179-8. 32852626 PMC7450158 · DOI
  23. [30]Swaminathan A, Rathnasabapathy M. Role of creativity in problem solving–a review. Rev Int Geograph Educ Online. 2021;11(8):2.
  24. [31]Temperley HC, O’Sullivan NJ, Mac Curtain BM, Corr A, Meaney JF, Kelly ME, Brennan I. Current applications and future potential of C hat GPT in radiology: a systematic review. J Med Imaging Radiat Oncol. 2024;1754–9485:13621. 10.1111/1754-9485.13621. 38243605 · DOI
  25. [32]Tiwari A, Kumar A, Jain S, Dhull KS, Sajjanar A, Puthenkandathil R, Paiwal K, Singh R. Implications of ChatGPT in public health dentistry: a systematic review. Cureus. 2023. 10.7759/cureus.40367. 37456464 PMC10340128 · DOI
  26. [33]Iqbal U, Lee LT, Rahmanti AR, Celi LA, Li YJ. Can large language models provide secondary reliable opinion on treatment options for dermatological diseases? J Am Med Inform Assoc. 2024;31(6):1341–7. 10.1093/jamia/ocae067.PMID:38578616;PMCID:PMC11105123. 38578616 PMC11105123 · DOI
  27. [34]Wang C, Liu S, Yang H, Guo J, Wu Y, Liu J. Ethical considerations of using ChatGPT in health care. J Med Int Res. 2023;25: e48009. PMC10457697 37566454
  28. [35]Wong M, Lim ZW, Pushpanathan K, Cheung CY, Wang YX, Chen D, Tham YC. Review of emerging trends and projection of future developments in large language models research in ophthalmology. Br J Ophthalmol. 2023. 10.1136/bjo-2023-324734. 38164563 · DOI
  29. [38]Zack T, Lehman E, Suzgun M, et al. Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study. Lancet Digit Health. 2024;6(1):e12–22. 10.1016/S2589-7500(23)00225-X[publishedOnlineFirst:2023/12/21]. 38123252 · DOI

Cited by

Sorted by citations

Authors
Iqbal, U., Tanweer, A., Rahmanti, A. R., Greenfield, D., Lee, L. T.-J., & Li, Y.-C. J.
Affiliations
  • Bond University (AU)
  • University of Management and Technology (PK)
  • Universitas Gadjah Mada (ID)
  • UNSW Sydney (AU)
  • Taipei Medical University Hospital (TW)
  • Taipei Medical University (TW)
Corresponding author
Li, Yu-Chuan Jack
ORCID
Venue
Journal of Biomedical Science
Publisher
Springer Science and Business Media LLC
Published
2025-05-07
Volume
32
Issue
1
Pages
45-45
ISSN
  • 1021-7770 (ISSN-L)
  • 1423-0127
DOI
10.1186/s12929-025-01131-z
PMC
PMC12057020
OpenAlex
W4410178347
Cited by
135
References
9
Citations by year
2026: 98 · 2025: 37
FWCI
7.98
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Biomedical Science (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Bond University Research Portal (Bond University) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
Keywords
ChatGPT, large language models, artificial intelligence in healthcare, clinical decision-making, disease diagnosis, medical education, radiology, neurosurgery, gastroenterology, ophthalmology, dental public health, manuscript review, research gaps
MeSH terms
Large Language Models, Generative Artificial Intelligence, Artificial Intelligence, Delivery of Health Care, Humans, Language

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