Assessing GPT-4’s Performance in Delivering Medical Advice: Comparative Analysis With Human Experts
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Background: Accurate medical advice is paramount in ensuring optimal patient care, and misinformation can lead to misguided decisions with potentially detrimental health outcomes. The emergence of large language models (LLMs) such as OpenAI’s GPT-4 has spurred interest in their potential health care applications, particularly in automated medical consultation. Yet, rigorous investigations comparing their performance to human experts remain sparse. Objective: This study aims to compare the medical accuracy of GPT-4 with human experts in providing medical advice using real-world user-generated queries, with a specific focus on cardiology. It also sought to analyze the performance of GPT-4 and human experts in specific question categories, including drug or medication information and preliminary diagnoses. Methods: We collected 251 pairs of cardiology-specific questions from general users and answers from human experts via an internet portal. GPT-4 was tasked with generating responses to the same questions. Three independent cardiologists (SL, JHK, and JJC) evaluated the answers provided by both human experts and GPT-4. Using a computer interface, each evaluator compared the pairs and determined which answer was superior, and they quantitatively measured the clarity and complexity of the questions as well as the accuracy and appropriateness of the responses, applying a 3-tiered grading scale (low, medium, and high). Furthermore, a linguistic analysis was conducted to compare the length and vocabulary diversity of the responses using word count and type-token ratio. Results: GPT-4 and human experts displayed comparable efficacy in medical accuracy (“GPT-4 is better” at 132/251, 52.6% vs “Human expert is better” at 119/251, 47.4%). In accuracy level categorization, humans had more high-accuracy responses than GPT-4 (50/237, 21.1% vs 30/238, 12.6%) but also a greater proportion of low-accuracy responses (11/237, 4.6% vs 1/238, 0.4%; P=.001). GPT-4 responses were generally longer and used a less diverse vocabulary than those of human experts, potentially enhancing their comprehensibility for general users (sentence count: mean 10.9, SD 4.2 vs mean 5.9, SD 3.7; P<.001; type-token ratio: mean 0.69, SD 0.07 vs mean 0.79, SD 0.09; P<.001). Nevertheless, human experts outperformed GPT-4 in specific question categories, notably those related to drug or medication information and preliminary diagnoses. These findings highlight the limitations of GPT-4 in providing advice based on clinical experience. Conclusions: GPT-4 has shown promising potential in automated medical consultation, with comparable medical accuracy to human experts. However, challenges remain particularly in the realm of nuanced clinical judgment. Future improvements in LLMs may require the integration of specific clinical reasoning pathways and regulatory oversight for safe use. Further research is needed to understand the full potential of LLMs across various medical specialties and conditions.
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.
Integrity signals
Registry
Cites
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.
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
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115 · cited 1×
“5 is its success in meeting the passing threshold for the United States Medical Licensing Examination [8], demonstrating its ability to offer medical advice comparable to that of trained professionals [9].”
BackgroundKung, T. H., Cheatham, M., ChatGPT, Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., et al. (2022) · doi:10.1101/2022.12.19.22283643 · Cited by 4,115
Large Language Models Encode Clinical Knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.13138 · Cited by 4,083
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083 · cited 1×
“Therefore, it is crucial to develop auditing procedures capable of capturing the intricacies of LLM-associated risks, necessitating a balanced evaluation of the potential benefits and risks inherent in LLMs [17,18].”
BackgroundGPT-3: Its Nature, Scope, Limits, and Consequences
Floridi, L., & Chiriatti, M. (2020) · Minds and Machines · doi:10.1007/s11023-020-09548-1 · Cited by 2,519
Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine
Lee, P., Bubeck, S., & Petro, J. (2023) · New England Journal of Medicine · doi:10.1056/nejmsr2214184 · Cited by 1,738
The imperative for regulatory oversight of large language models (or generative AI) in healthcare
Meskó, B., & Topol, E. J. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00873-0 · Cited by 1,047
Large Language Models in Medical Education: Opportunities, Challenges, and Future Directions
Abd-alrazaq, A., AlSaad, R., Alhuwail, D., Ahmed, A., Healy, P. M., Latifi, S., Aziz, S., Damseh, R., Alabed Alrazak, S., & Sheikh, J. (2023) · JMIR Medical Education · doi:10.2196/48291 · Cited by 722
Role of Chat GPT in public health
Biswas, S. S. (2023) · Annals of Biomedical Engineering · doi:10.1007/s10439-023-03172-7 · Cited by 673 · cited 1×
“In the medical field, GPT has the potential to augment medical education [5], provide clinical decision support [6], and enhance public health initiatives [7].”
BackgroundPerformance of GPT-3.5 and GPT-4 on the Japanese Medical Licensing Examination: Comparison Study
Takagi, S., Watari, T., Erabi, A., & Sakaguchi, K. (2023) · JMIR Medical Education · doi:10.2196/48002 · Cited by 271 · cited 2×
“Recent studies and OpenAI’s own documentation suggest that GPT-4’s performance in non-English languages, including medical contexts, has improved compared to previous versions [11,24,25].”
BackgroundResultLarge language models (LLM) and ChatGPT: what will the impact on nuclear medicine be?
Alberts, I. L., Mercolli, L., Pyka, T., Prenosil, G., Shi, K., Rominger, A., & Afshar-Oromieh, A. (2023) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-023-06172-w · Cited by 207 · cited 1×
“As a large language model (LLM), the GPT developed by OpenAI generates human-like text [1-3], distinguishing it from other specialized deep learning models that are limited to solving specific problems within predetermined domains [4].”
MethodGenerative AI in Health Care and Liability Risks for Physicians and Safety Concerns for Patients
Duffourc, M., & Gerke, S. (2023) · JAMA · doi:10.1001/jama.2023.9630 · Cited by 132
Reddy, S. (2023) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2023.101304 · Cited by 99 · cited 1×
“Therefore, it is crucial to develop auditing procedures capable of capturing the intricacies of LLM-associated risks, necessitating a balanced evaluation of the potential benefits and risks inherent in LLMs [17,18].”
Background
Cited by
Weisman, D., Sugarman, A., Huang, Y. M., Gelberg, L., Ganz, P. A., & Comulada, W. S. (2025) · JMIR Formative Research · doi:10.2196/65670 · Cited by 37
Esmaeilzadeh, P. (2025) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-025-03182-6 · Cited by 26
Leon, M., Ruaengsri, C., Pelletier, G., Bethencourt, D., Shibata, M., Flores, M. Q., & Shudo, Y. (2024) · Journal of Clinical Medicine · doi:10.3390/jcm13216543 · Cited by 12
Metadata
- Authors
- Jo, E., Song, S., Kim, J.-H., Lim, S., Kim, J. H., Cha, J.-J., Kim, Y.-M., & Joo, H. J.
- Venue
- JMIR Medical Education
- Publisher
- JMIR Publications Inc.
- Published
- 2024-07-08
- Volume
- 10
- Pages
- e51282-e51282
- ISSN
- 2369-3762 (ISSN-L)
- OpenAlex
- W4400549596
- Cited by
- 39
- References
- 13
- FWCI
- 3.13
- 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.