CoChat

Applications and Concerns of ChatGPT and Other Conversational Large Language Models in Health Care: Systematic Review

Open access
Wang, Leyao, Wan, Zhiyu, Ni, Congning, Song, Qingyuan, Li, Yang, Clayton, Ellen, Malin, Bradley, Yin, Zhijun · 2024 · Journal of Medical Internet Research

Published version of a preprint

Cited by 165

The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.

Abstract

Background: The launch of ChatGPT (OpenAI) in November 2022 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 health care. Numerous studies have since been conducted regarding how to use state-of-the-art LLMs in health-related scenarios. Objective: This review aims to summarize applications of and concerns regarding conversational LLMs in health care and provide an agenda for future research in this field. Methods: We used PubMed, ACM, and the IEEE digital libraries as primary sources for this review. We followed the guidance of PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) to screen and select peer-reviewed research articles that (1) were related to health care applications and conversational LLMs and (2) were published before September 1, 2023, the date when we started paper collection. 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 (7.9%) papers met our criteria and were included in the review. The most popular conversational LLM was ChatGPT (60/65, 92% of papers), followed by Bard (Google LLC; 1/65, 2% of papers), LLaMA (Meta; 1/65, 2% of papers), and other LLMs (6/65, 9% papers). These papers were classified into four categories of applications: (1) summarization, (2) medical knowledge inquiry, (3) prediction (eg, diagnosis, treatment recommendation, and drug synergy), and (4) administration (eg, documentation and information collection), and four categories of concerns: (1) reliability (eg, training data quality, accuracy, interpretability, and consistency in responses), (2) bias, (3) privacy, and (4) public acceptability. There were 49 (75%) papers using LLMs for either summarization or medical knowledge inquiry, or both, and there are 58 (89%) papers expressing concerns about either reliability or bias, or both. We found that conversational LLMs exhibited promising results in summarization and providing general medical knowledge to patients with a relatively high accuracy. However, conversational LLMs such as ChatGPT are not always able to provide reliable answers to complex health-related tasks (eg, diagnosis) that require specialized domain expertise. While bias or privacy issues are often noted as concerns, no experiments in our reviewed papers thoughtfully examined how conversational LLMs lead to these issues in health care 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 bring 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 health care.

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 · 10.2196/22769

Cites

39 of 39 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

Research works printed but not linked: 67

  1. 10.1038/s41591-023-02448-8 · DOI · Paper page
  2. 10.3390/ijerph20043378 · DOI · Paper page
  3. 10.3390/biomedicines11061623 · DOI
  4. 10.2196/51580 · DOI · Paper page
  5. 10.1016/j.ijom.2023.09.005 · DOI
  6. 10.1093/jamia/ocae035 · DOI
  7. 10.1038/s41746-023-00873-0 · DOI · Paper page
  8. 10.1371/journal.pmed.1000097 · DOI · Paper page
  9. 10.7759/cureus.38249 · DOI
  10. 10.1067/j.cpradiol.2023.04.001 · DOI
  11. 10.7189/jogh.13.03037 · DOI
  12. 10.7759/cureus.36408 · DOI
  13. 10.7759/cureus.40546 · DOI
  14. 10.7759/cureus.37589 · DOI · Paper page
  15. 10.7759/cureus.37368 · doi:10.7759/cureus.37368
  16. 10.1136/bmjhci-2023-100775 · DOI
  17. 10.7759/cureus.36590 · doi:10.7759/cureus.36590
  18. 10.7759/cureus.42214 · DOI
  19. 10.7759/cureus.41916 · DOI
  20. 10.7759/cureus.40135 · DOI · Paper page
  21. 10.7759/cureus.38683 · doi:10.7759/cureus.38683
  22. 10.1515/cclm-2023-0355 · DOI
  23. 10.1038/s41586-023-06160-y · DOI · Paper page
  24. 10.18653/v1/2023.clinicalnlp-1.10 · DOI
  25. 10.2196/48568 · DOI · Paper page
  26. 10.7759/cureus.38784 · DOI
  27. 10.7759/cureus.36830 · DOI
  28. 10.1007/s10916-023-01925-4 · DOI · Paper page
  29. 10.1097/IOP.0000000000002418 · DOI
  30. 10.1016/j.xops.2023.100324 · DOI · Paper page
  31. 10.1145/3594806.3596520 · DOI
  32. 10.3389/fonc.2023.1219326 · DOI · Paper page
  33. 10.2196/48966 · DOI
  34. 10.1253/circj.cj-23-0308 · DOI
  35. 10.3390/diagnostics13111950 · DOI
  36. 10.7759/cureus.40895 · DOI · Paper page
  37. 10.1093/eurjcn/zvad038 · DOI · Paper page
  38. 10.1177/08465371231171125 · DOI · Paper page
  39. 10.3350/cmh.2023.0089 · DOI · Paper page
  40. 10.1177/20552076231184091 · DOI
  41. 10.7759/cureus.40351 · DOI
  42. 10.1016/j.jaip.2023.05.042 · DOI
  43. 10.1186/s12859-023-05411-z · DOI
  44. 10.4103/tjem.tjem_79_23 · DOI
  45. 10.1038/s41523-023-00557-8 · DOI · Paper page
  46. 10.7759/cureus.36272 · DOI
  47. 10.1148/radiol.230424 · DOI · Paper page
  48. 10.1093/jamia/ocad072 · DOI · Paper page
  49. 10.7759/cureus.37938 · DOI
  50. 10.3390/biom13020387 · DOI
  51. 10.1109/access.2023.3300381 · DOI · Paper page
  52. 10.1136/bmj.h1139 · DOI · Paper page
  53. 10.1038/s41551-021-00751-8 · DOI · Paper page
  54. 10.1109/cvpr42600.2020.00033 · DOI · Paper page
  55. 10.1080/15265161.2023.2233357 · DOI · Paper page
  56. 10.1038/s41746-023-00873-0 · DOI · Paper page
  57. 10.1371/journal.pone.0120592 · DOI
  58. 10.1016/j.ajhg.2016.12.002 · DOI
  59. 10.1186/s12920-017-0282-1 · DOI
  60. 10.1126/sciadv.abe9986 · DOI
  61. 10.1038/s41576-022-00455-y · DOI
  62. 10.1038/s41467-022-35295-1 · DOI · Paper page
  63. 10.1101/gr.277674.123 · DOI
  64. 10.1007/978-3-031-69651-0_5 · DOI
  65. 10.1109/tnnls.2021.3129592 · DOI
  66. Liu, H, arXiv
  67. Li, C, arXiv

Cited by

See all 165

Metadata

Authors
Wang, L., Wan, Z., Ni, C., Song, Q., Li, Y., Clayton, E., Malin, B., & Yin, Z.
Venue
Journal of Medical Internet Research
Published
2024-11-07
Volume
26
Pages
e22769
ISSN
1438-8871 (ISSN-L)
OpenAlex
W4403087472
Cited by
165
References
39
FWCI
4.81
Type
journal article
Language
en
Open access
gold

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

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.