CPGPrompt: translating clinical guidelines into large language model-executable decision support
CPGPrompt demonstrates generalizability across diverse clinical domains while maintaining high sensitivity for referral decisions. Its transparent, auditable framework enables the systematic identification of failure modes and provides advantages over black-box AI approaches. However, persistent challenges with subjective clinical assessments indicate a need for targeted improvements and greater clinical robustness.
Authors
- Greg S. Martin (ORCID: https://orcid.org/0000-0002-9684-7593)
- Tony J. C. Wang (ORCID: https://orcid.org/0000-0001-5809-3025)
- Yi Liu (ORCID: https://orcid.org/0000-0003-1335-7626)
- Yifan Peng (ORCID: https://orcid.org/0000-0003-0667-2599)
- Justin Rousseau
- Yanshan Wang
- Chunhua Weng
- Ruiqi Deng
- Gongbo Zhang
Institutions
- University of Pittsburgh (US)
- Cornell University (US)
- Southwestern Medical Center (US)
- Weill Cornell Medicine (US)
- Columbia University (US)
- The University of Texas Southwestern Medical Center (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2026-02-03
- DOI
- https://doi.org/10.1093/jamia/ocag026
- Primary Topic
- Clinical practice guidelines implementation
- Type
- article
- Field-Weighted Citation Impact
- 0.00