Enhancing predictive modeling for respiratory support with LLM-driven guideline adherence
Integrating LLMs for guideline enforcement improves the interpretability and clinical alignment of counterfactual models in respiratory support decision-making. This hybrid framework not only enhances concordance with real-world practice but may also improve patient outcomes. Future work will refine contraindication detection and expand validation to prospective clinical trials.
Authors
- Shamim Nemati (ORCID: https://orcid.org/0000-0002-0520-4948)
- James S. Ford
- Atul Malhotra (ORCID: https://orcid.org/0000-0002-9509-1827)
- Xiaolei Lu (ORCID: https://orcid.org/0000-0002-0953-9219)
- Michael Miller (ORCID: https://orcid.org/0000-0003-0781-7868)
- Alex K. Pearce (ORCID: https://orcid.org/0000-0002-1226-0403)
- Thaidan Pham (ORCID: https://orcid.org/0000-0003-1153-0632)
- Preeti Gupta (ORCID: https://orcid.org/0000-0001-9972-2123)
Institutions
- UC San Diego Health System (US)
- University of California San Diego (US)
Publication Details
- Journal
- Critical Care
- Published
- 2025-11-14
- DOI
- https://doi.org/10.1186/s13054-025-05739-3
- Primary Topic
- Respiratory Support and Mechanisms
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Heart, Lung, and Blood Institute
- U.S. National Library of Medicine