CoChat
Sign Up
Cited by 56Artificial Intelligence in Healthcare and EducationInformation Retrieval and Search BehaviorMeta-analysis and systematic reviews

Examining the Validity of ChatGPT in Identifying Relevant Nephrology Literature: Findings and Implications

Open access
Suppadungsuk, Supawadee, Thongprayoon, Charat, Krisanapan, Pajaree, Tangpanithandee, Supawit, Garcia Valencia, Oscar, Miao, Jing, Mekraksakit, Poemlarp, Kashani, Kianoush +1 more·2023·Journal of Clinical Medicine
DOI 10.3390/jcm12175550PMC PMC10488525
Open this paper in CoChat — free accountOpen PDF

Abstract

Literature reviews are valuable for summarizing and evaluating the available evidence in various medical fields, including nephrology. However, identifying and exploring the potential sources requires focus and time devoted to literature searching for clinicians and researchers. ChatGPT is a novel artificial intelligence (AI) large language model (LLM) renowned for its exceptional ability to generate human-like responses across various tasks. However, whether ChatGPT can effectively assist medical professionals in identifying relevant literature is unclear. Therefore, this study aimed to assess the effectiveness of ChatGPT in identifying references to literature reviews in nephrology. We keyed the prompt “Please provide the references in Vancouver style and their links in recent literature on… name of the topic” into ChatGPT-3.5 (03/23 Version). We selected all the results provided by ChatGPT and assessed them for existence, relevance, and author/link correctness. We recorded each resource’s citations, authors, title, journal name, publication year, digital object identifier (DOI), and link. The relevance and correctness of each resource were verified by searching on Google Scholar. Of the total 610 references in the nephrology literature, only 378 (62%) of the references provided by ChatGPT existed, while 31% were fabricated, and 7% of citations were incomplete references. Notably, only 122 (20%) of references were authentic. Additionally, 256 (68%) of the links in the references were found to be incorrect, and the DOI was inaccurate in 206 (54%) of the references. Moreover, among those with a link provided, the link was correct in only 20% of cases, and 3% of the references were irrelevant. Notably, an analysis of specific topics in electrolyte, hemodialysis, and kidney stones found that >60% of the references were inaccurate or misleading, with less reliable authorship and links provided by ChatGPT. Based on our findings, the use of ChatGPT as a sole resource for identifying references to literature reviews in nephrology is not recommended. Future studies could explore ways to improve AI language models’ performance in identifying relevant nephrology literature.

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 · 10.3390/jcm12175550

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.

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?

  • When ChatGPT and other AI chatbots were challenged to authenticate their outputs with references, they generated multiple citations with detailed bibliographic data that seemed authentic, but most were fabricated, contained at least one falsified citation datum, or were completely erroneous when verified through medical literature resources.

    “Even when ChatGPT and other AI chatbots were challenged to authenticate their outputs with references [13,14], they generated multiple citations with detailed bibliographic data that seemed perfectly authentic, but most were actually fabricated, contained at least one falsified citation data, or were completely erroneous when verified through medical literature resources [13-16].”

    From Reference Hallucination Score for Medical Artificial Intelligence Chatbots: Development and Usability Study (2024) · cites this paper as [14]

    Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

    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.

The citation lists haven’t been fetched yet

References 43 · Cited by 56

Research works printed but not linked: 28

  1. [1]Martin S. Hussain Z. Boyle J.G. A beginner’s guide to the literature search in medical education Scott. Med. J. 2017 62 58 62 10.1177/0036933017707163 28606006 · DOI
  2. [2]Kuper A. Literature and medicine: A problem of assessment Acad. Med. 2006 81 S128 S137 10.1097/00001888-200610001-00032 17001123 · DOI
  3. [3]Grewal A. Kataria H. Dhawan I. Literature search for research planning and identification of research problem Indian J. Anaesth. 2016 60 635 639 10.4103/0019-5049.190618 27729689 PMC5037943 · DOI
  4. [7]Biswas S.S. Role of Chat GPT in Public Health Ann. Biomed. Eng. 2023 51 868 869 10.1007/s10439-023-03172-7 36920578 · DOI · Paper page
  5. [8]Kung T.H. Cheatham M. Medenilla A. Sillos C. de Leon L. Elepaño C. Madriaga M. Aggabao R. Diaz-Candido G. Maningo J. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models PLoS Digit. Health 2023 2 e0000198 10.1371/journal.pdig.0000198 36812645 PMC9931230 · DOI · Paper page
  6. [11]Davenport T. Kalakota R. The potential for artificial intelligence in healthcare Future Healthc. J. 2019 6 94 98 10.7861/futurehosp.6-2-94 31363513 PMC6616181 · DOI · Paper page
  7. [13]Chavez M.R. Butler T.S. Rekawek P. Heo H. Kinzler W.L. Chat Generative Pre-trained Transformer: Why we should embrace this technology Am. J. Obstet. Gynecol. 2023 228 706 711 10.1016/j.ajog.2023.03.010 36924908 · DOI · Paper page
  8. [14]Salvagno M. Taccone F.S. Gerli A.G. Can artificial intelligence help for scientific writing? Crit. Care 2023 27 75 10.1186/s13054-023-04380-2 36841840 PMC9960412 · DOI · Paper page
  9. [15]Marchandot B. Matsushita K. Carmona A. Trimaille A. Morel O. ChatGPT: The next frontier in academic writing for cardiologists or a pandora’s box of ethical dilemmas Eur. Heart J. Open 2023 3 oead007 10.1093/ehjopen/oead007 36915398 PMC10006694 · DOI · Paper page
  10. [19]Mojadeddi Z.M. Rosenberg J. The impact of AI and ChatGPT on research reporting N. Z. Med. J. 2023 136 60 64 37167941
  11. [20]Miao J. Thongprayoon C. Cheungpasitporn W. Assessing the Accuracy of ChatGPT on Core Questions in Glomerular Disease Kidney Int. Rep. 2023 8 1657 1659 10.1016/j.ekir.2023.05.014 37547515 PMC10403654 · DOI
  12. [21]Shen Y. Heacock L. Elias J. Hentel K.D. Reig B. Shih G. Moy L. ChatGPT and Other Large Language Models Are Double-edged Swords Radiology 2023 307 e230163 10.1148/radiol.230163 36700838 · DOI · Paper page
  13. [22]Alhasan K. Raina R. Jamal A. Temsah M.H. Combining human and AI could predict nephrologies future, but should be handled with care Acta Paediatr. 2023 112 1844 1848 10.1111/apa.16867 37278392 · DOI · Paper page
  14. [23]Connor C.W. Artificial Intelligence and Machine Learning in Anesthesiology Anesthesiology 2019 131 1346 1359 10.1097/ALN.0000000000002694 30973516 PMC6778496 · DOI
  15. [24]Salas M. Petracek J. Yalamanchili P. Aimer O. Kasthuril D. Dhingra S. Junaid T. Bostic T. The Use of Artificial Intelligence in Pharmacovigilance: A Systematic Review of the Literature Pharm. Med. 2022 36 295 306 10.1007/s40290-022-00441-z 35904529 · DOI
  16. [26]Lu Y. Wu H. Qi S. Cheng K. Artificial Intelligence in Intensive Care Medicine: Toward a ChatGPT/GPT-4 Way? Ann. Biomed. Eng. 2023 51 1898 1903 10.1007/s10439-023-03234-w 37179277 PMC10182840 · DOI
  17. [27]Siddiqui T.A. Sukhia R.H. Ghandhi D. Artificial intelligence in dentistry, orthodontics and Orthognathic surgery: A literature review J. Pak. Med. Assoc. 2022 72 (Suppl. S1) S91 S96 10.47391/jpma.Aku-18 35202378 · DOI
  18. [28]Cascella M. Montomoli J. Bellini V. Bignami E. Evaluating the Feasibility of ChatGPT in Healthcare: An Analysis of Multiple Clinical and Research Scenarios J. Med. Syst. 2023 47 33 10.1007/s10916-023-01925-4 36869927 PMC9985086 · DOI · Paper page
  19. [29]Alkaissi H. McFarlane S.I. Artificial Hallucinations in ChatGPT: Implications in Scientific Writing Cureus 2023 15 e35179 10.7759/cureus.35179 36811129 PMC9939079 · DOI · Paper page
  20. [30]Meskó B. Görög M. A short guide for medical professionals in the era of artificial intelligence NPJ Digit. Med. 2020 3 126 10.1038/s41746-020-00333-z 33043150 PMC7518439 · DOI · Paper page
  21. [33]Fatani B. ChatGPT for Future Medical and Dental Research Cureus 2023 15 e37285 10.7759/cureus.37285 37168166 PMC10165936 · DOI
  22. [35]Gottlieb M. Kline J.A. Schneider A.J. Coates W.C. ChatGPT and conversational artificial intelligence: Friend, foe, or future of research? Am. J. Emerg. Med. 2023 70 81 83 10.1016/j.ajem.2023.05.018 37229893 · DOI
  23. [36]Athaluri S.A. Manthena S.V. Kesapragada V.S.R.K.M. Yarlagadda V. Dave T. Duddumpudi R.T.S. Exploring the Boundaries of Reality: Investigating the Phenomenon of Artificial Intelligence Hallucination in Scientific Writing Through ChatGPT References Cureus 2023 15 e37432 10.7759/cureus.37432 37182055 PMC10173677 · DOI · Paper page
  24. [37]Masters K. Medical Teacher’s first ChatGPT’s referencing hallucinations: Lessons for editors, reviewers, and teachers Med. Teach. 2023 45 673 675 10.1080/0142159X.2023.2208731 37183932 · DOI · Paper page
  25. [39]Alexandre Blanco-Gonzalez A.C. Seco-Gonzalez A. Conde-Torres D. Antelo-Riveiro P. Pineiro A. Garcia-Fandino R. The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies arXiv 2022 2212.08104 PMC10302890 37375838
  26. [41]Jamal A. Solaiman M. Alhasan K. Temsah M.-H. Sayed G. Integrating ChatGPT in Medical Education: Adapting Curricula to Cultivate Competent Physicians for the AI Era Cureus 2023 15 e43036 10.7759/cureus.43036 37674966 PMC10479954 · DOI
  27. [42]Temsah O. Khan S.A. Chaiah Y. Senjab A. Alhasan K. Jamal A. Aljamaan F. Malki K.H. Halwani R. Al-Tawfiq J.A. Overview of Early ChatGPT’s Presence in Medical Literature: Insights from a Hybrid Literature Review by ChatGPT and Human Experts Cureus 2023 15 e37281 10.7759/cureus.37281 37038381 PMC10082551 · DOI
  28. [44]Tustumi F. Andreollo N.A. Aguilar-Nascimento J.E. Future of the language models in healthcare: The role of chatGPT Arq. Bras. Cir. Dig. 2023 36 e1727 10.1590/0102-672020230002e1727 37162073 PMC10168663 · DOI · Paper page

Authors
Suppadungsuk, S., Thongprayoon, C., Krisanapan, P., Tangpanithandee, S., Garcia Valencia, O., Miao, J., Mekraksakit, P., Kashani, K., & Cheungpasitporn, W.
Affiliations
  • Mayo Clinic (US)
  • Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA
Corresponding author
Cheungpasitporn, Wisit
ORCID
Venue
Journal of Clinical Medicine
Publisher
MDPI AG
Published
2023-08-25
Volume
12
Issue
17
Pages
5550
ISSN
2077-0383 (ISSN-L)
DOI
10.3390/jcm12175550
PMC
PMC10488525
OpenAlex
W4386224103
Cited by
56
References
43
Citations by year
2026: 13 · 2025: 11 · 2024: 20 · 2023: 12
FWCI
2.23
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Clinical Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
Keywords
ChatGPT, large language models, literature searching, citation accuracy, AI-generated references, hemodialysis, kidney stones, electrolyte imbalance, prompt engineering

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