Large language model‐based identification of venous thromboembolism diagnostic delays
We developed the first LLM-based electronic-trigger to identify VTE diagnostic delays, with higher performance than existing non-LLM electronic-triggers. LLM-based approaches can facilitate diagnostic performance feedback and are scalable to other conditions and institutions.
Authors
- Daniel J. Sartori (ORCID: https://orcid.org/0000-0003-3138-7183)
- Benedict Guzman (ORCID: https://orcid.org/0000-0002-2791-1491)
- Bijal Rajput (ORCID: https://orcid.org/0000-0002-6862-6734)
- Jesse Burk‐Rafel (ORCID: https://orcid.org/0000-0003-3785-2154)
- Ilan Reinstein (ORCID: https://orcid.org/0000-0001-7360-4436)
- Verity E. Schaye (ORCID: https://orcid.org/0000-0003-0816-4037)
- Kiran Malhotra (ORCID: https://orcid.org/0009-0004-6934-0553)
- Lexi Signoriello
Institutions
- NYU Langone Health (US)
- Health Innovations (United States) (US)
- New York University (US)
Publication Details
- Journal
- Journal of Hospital Medicine
- Published
- 2025-10-07
- DOI
- https://doi.org/10.1002/jhm.70194
- Primary Topic
- Clinical Reasoning and Diagnostic Skills
- Type
- article
- Field-Weighted Citation Impact
- 0.00