Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
[Preprint]. 2023 Feb 1:2023.01.30.23285067.
doi: 10.1101/2023.01.30.23285067.

The Diagnostic and Triage Accuracy of the GPT-3 Artificial Intelligence Model

David M Levine  1   2 , Rudraksh Tuwani  3   4 , Benjamin Kompa  4   5 , Amita Varma  3   4 , Samuel G Finlayson  6 , Ateev Mehrotra  7 , Andrew Beam  4   5
Affiliations

The Diagnostic and Triage Accuracy of the GPT-3 Artificial Intelligence Model

David M Levine et al. medRxiv. .

Abstract

Importance: Artificial intelligence (AI) applications in health care have been effective in many areas of medicine, but they are often trained for a single task using labeled data, making deployment and generalizability challenging. Whether a general-purpose AI language model can perform diagnosis and triage is unknown.

Objective: Compare the general-purpose Generative Pre-trained Transformer 3 (GPT-3) AI model's diagnostic and triage performance to attending physicians and lay adults who use the Internet.

Design: We compared the accuracy of GPT-3's diagnostic and triage ability for 48 validated case vignettes of both common (e.g., viral illness) and severe (e.g., heart attack) conditions to lay people and practicing physicians. Finally, we examined how well calibrated GPT-3's confidence was for diagnosis and triage.

Setting and participants: The GPT-3 model, a nationally representative sample of lay people, and practicing physicians.

Exposure: Validated case vignettes (<60 words; <6th grade reading level).

Main outcomes and measures: Correct diagnosis, correct triage.

Results: Among all cases, GPT-3 replied with the correct diagnosis in its top 3 for 88% (95% CI, 75% to 94%) of cases, compared to 54% (95% CI, 53% to 55%) for lay individuals (p<0.001) and 96% (95% CI, 94% to 97%) for physicians (p=0.0354). GPT-3 triaged (71% correct; 95% CI, 57% to 82%) similarly to lay individuals (74%; 95% CI, 73% to 75%; p=0.73); both were significantly worse than physicians (91%; 95% CI, 89% to 93%; p<0.001). As measured by the Brier score, GPT-3 confidence in its top prediction was reasonably well-calibrated for diagnosis (Brier score = 0.18) and triage (Brier score = 0.22).

Conclusions and relevance: A general-purpose AI language model without any content-specific training could perform diagnosis at levels close to, but below physicians and better than lay individuals. The model was performed less well on triage, where its performance was closer to that of lay individuals.

Keywords: artificial intelligence; diagnosis; machine learning; triage.

PubMed Disclaimer

Figures

Figure 1:
Figure 1:
An illustrative example of GPT-3 prompting.
Figure 2.
Figure 2.
Diagnostic and triage accuracy of lay individuals with Internet access, GPT-3, and primary care attending physicians. Panel A: Correct diagnosis was listed among the top-3, stratified by case acuity from most acute (emergent) to least acute (self-care). Panel B: Correct dichotomized triage (same-day vs not same-day), stratified by case acuity from most acute (emergent) to least acute (self-care).
Figure 3.
Figure 3.
Calibration analysis of GPT-3 confidence scores for diagnosis and triage. Each panel shows a calibration curve displaying the relationship between GPT-3 confidence and accuracy. Each dot represents “binned” confidence scores that fall within the same range (e.g. 90-100%), while the y-axis shows the average accuracy for vignettes in that bin. In the case of good calibration, GPT-3 would get approximately 90% accuracy on vignettes that have a confidence score of approximately 90%. The Brier score is an overall summary of the calibration curve that ranges between 0 and 1, with a score of 0 implying perfect calibration. Panel A: Calibration curve and Brier score for GPT-3 diagnostic confidence. Overall, the model appears reasonably well-calibrated (Brier score=0.18). Panel B: Calibration curve and Brier score for triage prediction, again displayed evidence of reasonably good calibration (Brier score=0.22).
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Bates DW, Levine D, Syrowatka A, et al. The potential of artificial intelligence to improve patient safety: a scoping review. NPJ Digit Med. 2021;4(1):54. doi:10.1038/s41746-021-00423-6 - DOI - PMC - PubMed
    1. Kompa B, Hakim JB, Palepu A, et al. Artificial Intelligence Based on Machine Learning in Pharmacovigilance: A Scoping Review. Drug Safety. 2022;45(5):477–491. doi: 10.1007/s40264-022-01176-1 - DOI - PMC - PubMed
    1. Matheny ME, Whicher D, Thadaney Israni S. Artificial intelligence in health care: A report from the national academy of medicine. JAMA. 2020;323(6):509–510. doi:10.1001/jama.2019.21579 - DOI - PubMed
    1. Rojas-Gualdron DF. Artificial Intelligence in Health Care: The Hope, the Hype, the Promise, the Peril. National academy of medicine. Una reseña. CES Med. 2022;36(1):76–78. doi:10.21615/cesmedicina.6571 - DOI
    1. Beam AL, Kohane IS. Big data and machine learning in health care. JAMA - Journal of the American Medical Association. 2018;319(13):1317–1318. doi:10.1001/jama.2017.18391 - DOI - PubMed

Publication types