Performance of a large language model on the reasoning tasks of a physician
Science · 30.04.2026 · 392 (6797) · 524-527
DOI: 10.1126/science.adz4433 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science, erschienen am 30.04.2026. Verfasst von Peter G Brodeur und 24 weiteren Autor:innen. Beteiligte Einrichtung: Department of Internal Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA. Hauptthemen laut MEDLINE: Clinical Decision-Making, Clinical Reasoning, Decision Support Systems, Clinical, Large Language Models. Die Arbeit wurde bisher 77-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: NCATS NIH HHS, National Institutes of Health, Gordon and Betty Moore Foundation.
Abstract (Originalsprache)
More than 65 years ago, complex clinical diagnostic reasoning cases were introduced as the gold standard for the evaluation of expert medical computing systems, a standard that has held ever since. In this study, we report the results of a physician evaluation of a large language model (LLM) on challenging clinical cases across five experiments with a baseline of hundreds of physicians. We then report a real-world study comparing human expert and artificial intelligence (AI) second opinions in randomly selected patients in the emergency room of a major tertiary academic medical center. In all experiments, the LLM outperformed physician baselines and displayed continued improvement from prior generations of AI clinical decision support. Our study suggests that LLMs have eclipsed most benchmarks of clinical reasoning, motivating the urgent need for prospective trials.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Internal Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA.
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
- Stanford Division of Computational Medicine, Stanford University, Stanford, CA, USA.
- Stanford Clinical Excellence Research Center, Stanford University, Stanford, CA, USA.
- Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA.
- Department of Internal Medicine, Cambridge Health Alliance, Cambridge, MA, USA.
ORCID-Profile: Peter G Brodeur, Thomas A Buckley, Zahir Kanjee, Ethan Goh, Evelyn Bin Ling, Priyank Jain, Stephanie Cabral, Raja-Elie Abdulnour, Adrian D Haimovich, Jason A Freed, Andrew Olson, Robert Gallo, Liam G McCoy, Haadi Mombini, Matthew Gwiazdon, Daniele Restifo, Daniel Restrepo, Eric Horvitz, Jonathan Chen, Arjun K Manrai, Adam Rodman
Förderung
- NCATS NIH HHS
- National Institutes of Health
- Gordon and Betty Moore Foundation
- Josiah Macy Jr. Foundation
- Harvard Medical School
Zitieren
APA
Brodeur, P. G., Buckley, T. A., Kanjee, Z., Goh, E., Ling, E. B., Jain, P., Cabral, S., Abdulnour, R. E., Haimovich, A. D., Freed, J. A., Olson, A., Morgan, D. J., Hom, J., Gallo, R., McCoy, L. G., Mombini, H., Lucas, C., Fotoohi, M., Gwiazdon, M., …, & Rodman, A. (2026). Performance of a large language model on the reasoning tasks of a physician. Science, 392(6797), 524-527. https://doi.org/10.1126/science.adz4433
Vancouver
Brodeur PG, Buckley TA, Kanjee Z, Goh E, Ling EB, Jain P, et al. Performance of a large language model on the reasoning tasks of a physician. Science. 2026;392(6797):524-527. doi:10.1126/science.adz4433
BibTeX
@article{Brodeur2026,
author = {Brodeur, Peter G and Buckley, Thomas A and Kanjee, Zahir and Goh, Ethan and Ling, Evelyn Bin and Jain, Priyank and Cabral, Stephanie and Abdulnour, Raja-Elie and Haimovich, Adrian D and Freed, Jason A and Olson, Andrew and Morgan, Daniel J and Hom, Jason and Gallo, Robert and McCoy, Liam G and Mombini, Haadi and Lucas, Christopher and Fotoohi, Misha and Gwiazdon, Matthew and Restifo, Daniele and Restrepo, Daniel and Horvitz, Eric and Chen, Jonathan and Manrai, Arjun K and Rodman, Adam},
title = {Performance of a large language model on the reasoning tasks of a physician},
journal = {Science},
year = {2026},
volume = {392},
number = {6797},
pages = {524--527},
doi = {10.1126/science.adz4433}
}
EUVIMED