DETERIO-LLM: enhancing traditional deterioration risk scores with clinical context and advanced reasoning
JAMIA Open · 07.07.2026 · 9 (4)
DOI: 10.1093/jamiaopen/ooag123 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 16.07.2026. Verfasst von Ghodsieh Ghanbari und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, University of California San Diego (UCSD) School of Medicine, La Jolla, CA 92093, United States. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NLM NIH HHS, NIGMS NIH HHS, National Library of Medicine.
Abstract (Originalsprache)
Objectives
Accurate and timely prediction of physiological deterioration in hospitalized patients is essential, but existing deep learning models, which rely solely on structured electronic health record (EHR) data, generate high false-positive rates by missing crucial contextual information in clinical notes. We present DETERIO-LLM, a hybrid prediction model that selectively integrates large language models (LLMs) with a deep learning model (DETERIO) to reclassify borderline-risk alerts using narrative clinical notes. Materials and Methods This retrospective study used a cohort of 1000 inpatients (4.6% deterioration prevalence). DETERIO-LLM selectively analyzed narrative notes for alerts in the uncertainty range (scores 2.5-3.5). Performance was evaluated using sensitivity, positive predictive value (PPV), and F1 score, benchmarked against comparators including the best-established ML model, eCART.
Results
DETERIO-LLM significantly improved predictive precision over all comparators. At its optimal threshold, the model achieved a PPV of 30.6% and an F1 score of 37.3%, outperforming eCART. This selective integration reduced false-positive alerts by 46.5% within the uncertainty range while maintaining comparable sensitivity.
Discussion
This study demonstrates a practical, interpretable method for integrating LLM-derived contextual knowledge into existing structured EHR prediction workflows. By focusing LLM analysis on high-uncertainty alerts, DETERIO-LLM substantially improves clinical utility through a marked reduction in false-positive cases, which is critical for mitigating alert fatigue.
Conclusion
Selective LLM integration with structured EHR models offers a viable, interpretable path to improving early warning systems in clinical care by leveraging narrative context to reduce alert fatigue while enhancing predictive performance.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Informatics, University of California San Diego (UCSD) School of Medicine, La Jolla, CA 92093, United States.
- Division of Gastroenterology & Hepatology, Mayo Clinic, Rochester, MN 55905, United States.
- Department of Emergency Medicine, University of California San Diego School of Medicine, La Jolla, CA 92093, United States.
ORCID-Profile: Shamim Nemati
Förderung
- NLM NIH HHS
- NIGMS NIH HHS
- National Library of Medicine
- National Institute of General Medical Sciences
Zitieren
APA
Ghanbari, G., Ahn, J. C., Kim, E., Laverde, R., Pope, Z., & Nemati, S. (2026). DETERIO-LLM: enhancing traditional deterioration risk scores with clinical context and advanced reasoning. JAMIA Open, 9(4). https://doi.org/10.1093/jamiaopen/ooag123
Vancouver
Ghanbari G, Ahn JC, Kim E, Laverde R, Pope Z, Nemati S. DETERIO-LLM: enhancing traditional deterioration risk scores with clinical context and advanced reasoning. JAMIA Open. 2026;9(4). doi:10.1093/jamiaopen/ooag123
BibTeX
@article{Ghanbari2026,
author = {Ghanbari, Ghodsieh and Ahn, Joseph C and Kim, Eileen and Laverde, Ruth and Pope, Zach and Nemati, Shamim},
title = {DETERIO-LLM: enhancing traditional deterioration risk scores with clinical context and advanced reasoning},
journal = {JAMIA Open},
year = {2026},
volume = {9},
number = {4},
doi = {10.1093/jamiaopen/ooag123}
}
EUVIMED