Science· 2026Q1
Sequential diagnosis with language models
- 27citations
- Q1SCImago
- 2026year
Short summary
An AI system simulating physicians achieved 83.2% accuracy on clinical cases and 80.3% on emergency department cases, significantly outperforming generalist physicians (36.1% and 46.8%, respectively) in a sequential diagnostic benchmark.
AI-generated from the title and abstract; the full text is not read.
Key points
- Developed an AI system and benchmark for sequential diagnosis, simulating iterative clinical reasoning.
- AI system achieved 83.2% accuracy on NEJM clinicopathological conference cases.
- AI system achieved 80.3% accuracy on MIMIC-IV-ED emergency department admissions.
- AI system significantly outperformed generalist physicians (36.1% and 46.8% accuracy, respectively).
AI-generated from the title and abstract; the full text is not read.
Abstract
We explored the capabilities of frontier language models in sequential diagnosis, a diagnostic paradigm that captures the iterative nature of clinical reasoning. Given a brief clinical presentation, clinicians selectively acquired information to reach a diagnosis, enabling assessment of diagnostic accuracy and workup cost. We developed an interactive benchmark and an artificial intelligence (AI) system that simulates a panel of physicians, continually revising the differential diagnosis and selecting cost-effective tests. Using this benchmark, the system achieved 83.2% accuracy on New England Journal of Medicine clinicopathological conference cases and 80.3% on MIMIC-IV-ED emergency department admissions, outperforming generalist physicians (36.1 and 46.8%, respectively). Although these findings were obtained in a controlled benchmark setting, they highlight the promise of language models for supporting more accurate, lower-cost diagnoses.
The authors' abstract, as published at the source. Science, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Health Informatics
Health InformaticsMedicine