CoChat

A Systematic Review of ChatGPT and Other Conversational Large Language Models in Healthcare

Open access
Wang, Leyao, Wan, Zhiyu, Ni, Congning, Song, Qingyuan, Li, Yang, Clayton, Ellen Wright, Malin, Bradley A., Yin, Zhijun · 2024 · medRxiv
PreprintCited by 41

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Abstract

Background: The launch of the Chat Generative Pre-trained Transformer (ChatGPT) in November 2022 has attracted public attention and academic interest to large language models (LLMs), facilitating the emergence of many other innovative LLMs. These LLMs have been applied in various fields, including healthcare. Numerous studies have since been conducted regarding how to employ state-of-the-art LLMs in health-related scenarios to assist patients, doctors, and public health administrators. Objective: This review aims to summarize the applications and concerns of applying conversational LLMs in healthcare and provide an agenda for future research on LLMs in healthcare. Methods: We utilized PubMed, ACM, and IEEE digital libraries as primary sources for this review. We followed the guidance of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRIMSA) to screen and select peer-reviewed research articles that (1) were related to both healthcare applications and conversational LLMs and (2) were published before September 1 st , 2023, the date when we started paper collection and screening. We investigated these papers and classified them according to their applications and concerns. Results: Our search initially identified 820 papers according to targeted keywords, out of which 65 papers met our criteria and were included in the review. The most popular conversational LLM was ChatGPT from OpenAI (60), followed by Bard from Google (1), Large Language Model Meta AI (LLaMA) from Meta (1), and other LLMs (5). These papers were classified into four categories in terms of their applications: 1) summarization, 2) medical knowledge inquiry, 3) prediction, and 4) administration, and four categories of concerns: 1) reliability, 2) bias, 3) privacy, and 4) public acceptability. There are 49 (75%) research papers using LLMs for summarization and/or medical knowledge inquiry, and 58 (89%) research papers expressing concerns about reliability and/or bias. We found that conversational LLMs exhibit promising results in summarization and providing medical knowledge to patients with a relatively high accuracy. However, conversational LLMs like ChatGPT are not able to provide reliable answers to complex health-related tasks that require specialized domain expertise. Additionally, no experiments in our reviewed papers have been conducted to thoughtfully examine how conversational LLMs lead to bias or privacy issues in healthcare research. Conclusions: Future studies should focus on improving the reliability of LLM applications in complex health-related tasks, as well as investigating the mechanisms of how LLM applications brought bias and privacy issues. Considering the vast accessibility of LLMs, legal, social, and technical efforts are all needed to address concerns about LLMs to promote, improve, and regularize the application of LLMs in healthcare.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1101/2024.04.26.24306390

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 16 references

Research works printed but not linked: 68

  1. 10.1038/s41591-023-02448-8 · DOI · Paper page
  2. 10.2196/47564 · DOI · Paper page
  3. 10.3390/ijerph20043378 · DOI · Paper page
  4. 10.3390/biomedicines11061623 · DOI
  5. 10.1016/j.sapharm.2023.03.006 · DOI
  6. 10.1038/s41746-023-00873-0 · DOI · Paper page
  7. 10.1371/journal.pmed.1000097 · DOI · Paper page
  8. 10.1097/MD.0000000000034068 · DOI · Paper page
  9. 10.7759/cureus.36830 · DOI
  10. 10.2196/48568 · DOI · Paper page
  11. 10.7759/cureus.38784 · DOI · Paper page
  12. 10.1007/s10916-023-01925-4 · DOI · Paper page
  13. 10.7759/cureus.40546 · DOI
  14. 10.1067/j.cpradiol.2023.04.001 · DOI · Paper page
  15. 10.1038/s41586-023-06160-y · DOI · Paper page
  16. 10.7759/cureus.36408 · DOI
  17. 10.1136/bmjhci-2023-100775 · DOI · Paper page
  18. 10.7759/cureus.37368 · doi:10.7759/cureus.37368
  19. 10.7759/cureus.37589 · DOI · Paper page
  20. 10.7759/cureus.40135 · DOI · Paper page
  21. 10.7759/cureus.41916 · DOI
  22. 10.7759/cureus.38249 · DOI · Paper page
  23. 10.1038/s41598-023-31412-2 · DOI · Paper page
  24. 10.7189/jogh.13.03037 · DOI
  25. 10.7759/cureus.42214 · DOI
  26. 10.1097/IOP.0000000000002418 · DOI · Paper page
  27. 10.1253/circj.CJ-23-0308 · DOI · Paper page
  28. 10.7759/cureus.40351 · DOI
  29. 10.3390/diagnostics13111950 · DOI · Paper page
  30. 10.3350/cmh.2023.0089 · DOI · Paper page
  31. 10.1177/08465371231171125 · DOI · Paper page
  32. 10.7759/cureus.40822 · DOI · Paper page
  33. 10.7759/cureus.36590 · doi:10.7759/cureus.36590
  34. 10.1007/s00405-023-08051-4 · DOI · Paper page
  35. 10.7759/cureus.35237 · DOI · Paper page
  36. 10.1177/20552076231184091 · DOI
  37. 10.1371/journal.pdig.0000198 · DOI · Paper page
  38. 10.3389/fonc.2023.1219326 · DOI · Paper page
  39. 10.1016/j.xops.2023.100324 · DOI · Paper page
  40. 10.2196/46599 · DOI · Paper page
  41. 10.7759/cureus.40895 · DOI · Paper page
  42. 10.1016/j.jaip.2023.05.042 · DOI
  43. 10.2196/48966 · DOI · Paper page
  44. 10.1093/eurjcn/zvad038 · DOI · Paper page
  45. 10.1145/3594806.3596520 · DOI
  46. 10.7759/cureus.38166 · DOI · Paper page
  47. 10.1093/jamia/ocad072 · DOI · Paper page
  48. 10.1515/cclm-2023-0355 · DOI · Paper page
  49. 10.1371/journal.pdig.0000168 · DOI · Paper page
  50. 10.18653/v1/2023.clinicalnlp-1.10 · DOI
  51. 10.1186/s12859-023-05411-z · DOI
  52. 10.4103/tjem.tjem_79_23 · DOI · Paper page
  53. 10.7759/cureus.37938 · DOI · Paper page
  54. 10.1038/s41523-023-00557-8 · DOI · Paper page
  55. 10.7759/cureus.38683 · doi:10.7759/cureus.38683
  56. 10.1148/radiol.230424 · DOI · Paper page
  57. 10.7759/cureus.36272 · DOI · Paper page
  58. 10.1145/3582515.3609536 · DOI · Paper page
  59. 10.3390/biom13020387 · DOI
  60. 10.1109/ACCESS.2023.3300381 · DOI · Paper page
  61. 10.1056/NEJMsr1809937 · DOI · Paper page
  62. 10.1136/bmj.h1139 · DOI · Paper page
  63. 10.1038/s41551-021-00751-8 · DOI · Paper page
  64. 10.48550/arXiv.1911.07135 · DOI · Paper page
  65. 10.1371/journal.pone.0028071 · DOI · Paper page
  66. 10.1080/15265161.2023.2233357 · DOI · Paper page
  67. 10.1016/S2589-7500(23)00225-X · DOI · Paper page
  68. 10.1101/2023.08.28.23294730 · DOI · Paper page

Cited by

See all 41

Metadata

Authors
Wang, L., Wan, Z., Ni, C., Song, Q., Li, Y., Clayton, E. W., Malin, B. A., & Yin, Z.
Venue
medRxiv
Publisher
openRxiv
Published
2024-04-27
OpenAlex
W4395688696
Cited by
41
References
16
Type
posted content
Language
en
Open access
green

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: A Systematic Review of ChatGPT and Other Conversational Large Language Models in Healthcare. https://app.cochat.ai/papers/10.1101/2024.04.26.24306390
The paper
Wang, L., Wan, Z., Ni, C., Song, Q., Li, Y., Clayton, E. W., Malin, B. A., & Yin, Z. (2024). A Systematic Review of ChatGPT and Other Conversational Large Language Models in Healthcare. medRxiv. https://doi.org/10.1101/2024.04.26.24306390

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.