A deep learning model for clinical outcome prediction using longitudinal inpatient electronic health records
JAMIA Open · 06.03.2025 · 8 (2)
DOI: 10.1093/jamiaopen/ooaf026 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 10.04.2025. Verfasst von Ruichen Rong und 13 weiteren Autor:innen. Beteiligte Einrichtung: Quantitative Biomedical Research Center, Peter O'Donnell Jr. School of Public Health, The University of Texas Southwestern Medical Center, Dallas, TX…. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIAID NIH HHS, NLM NIH HHS, NIDCR NIH HHS.
Abstract (Originalsprache)
Objectives
Recent advances in deep learning show significant potential in analyzing continuous monitoring electronic health records (EHR) data for clinical outcome prediction. We aim to develop a Transformer-based, Encounter-level Clinical Outcome (TECO) model to predict mortality in the intensive care unit (ICU) using inpatient EHR data. Materials and Methods The TECO model was developed using multiple baseline and time-dependent clinical variables from 2579 hospitalized COVID-19 patients to predict ICU mortality and was validated externally in an acute respiratory distress syndrome cohort (n = 2799) and a sepsis cohort (n = 6622) from the Medical Information Mart for Intensive Care IV (MIMIC-IV). Model performance was evaluated based on the area under the receiver operating characteristic (AUC) and compared with Epic Deterioration Index (EDI), random forest (RF), and extreme gradient boosting (XGBoost).
Results
In the COVID-19 development dataset, TECO achieved higher AUC (0.89-0.97) across various time intervals compared to EDI (0.86-0.95), RF (0.87-0.96), and XGBoost (0.88-0.96). In the 2 MIMIC testing datasets (EDI not available), TECO yielded higher AUC (0.65-0.77) than RF (0.59-0.75) and XGBoost (0.59-0.74). In addition, TECO was able to identify clinically interpretable features that were correlated with the outcome.
Discussion
The TECO model outperformed proprietary metrics and conventional machine learning models in predicting ICU mortality among patients with COVID-19, widespread inflammation, respiratory illness, and other organ failures.
Conclusion
The TECO model demonstrates a strong capability for predicting ICU mortality using continuous monitoring data. While further validation is needed, TECO has the potential to serve as a powerful early warning tool across various diseases in inpatient settings.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Quantitative Biomedical Research Center, Peter O'Donnell Jr. School of Public Health, The University of Texas Southwestern Medical Center, Dallas, TX 75390, United States.
- Department of Biostatistics and Data Science, School of Public Health, University of Texas Health Science Center at Houston, Houston, TX 77030, United States.
- Texas Health Resources, Arlington, TX 76011, United States.
- Program in Computational Biology and Biomedical Informatics, Yale University, New Haven, CT 06511, United States.
- Department of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT 06511, United States.
- Department of Internal Medicine, The University of Texas Southwestern Medical Center, Dallas, TX 75390, United States.
ORCID-Profile: Zifan Gu, Ann Marie Navar, Guanghua Xiao, Donghan M Yang
Förderung
- NIAID NIH HHS
- NLM NIH HHS
- NIDCR NIH HHS
- NIGMS NIH HHS
- NCI NIH HHS
- National Institutes of Health
- Cancer Prevention and Research Institute of Texas
- Texas Health Resources Clinical Scholars Program
Zitieren
APA
Rong, R., Gu, Z., Lai, H., Nelson, T. L., Keller, T., Walker, C., Jin, K. W., Chen, C., Navar, A. M., Velasco, F., Peterson, E. D., Xiao, G., Yang, D. M., & Xie, Y. (2025). A deep learning model for clinical outcome prediction using longitudinal inpatient electronic health records. JAMIA Open, 8(2). https://doi.org/10.1093/jamiaopen/ooaf026
Vancouver
Rong R, Gu Z, Lai H, Nelson TL, Keller T, Walker C, et al. A deep learning model for clinical outcome prediction using longitudinal inpatient electronic health records. JAMIA Open. 2025;8(2). doi:10.1093/jamiaopen/ooaf026
BibTeX
@article{Rong2025,
author = {Rong, Ruichen and Gu, Zifan and Lai, Hongyin and Nelson, Tanna L and Keller, Tony and Walker, Clark and Jin, Kevin W and Chen, Catherine and Navar, Ann Marie and Velasco, Ferdinand and Peterson, Eric D and Xiao, Guanghua and Yang, Donghan M and Xie, Yang},
title = {A deep learning model for clinical outcome prediction using longitudinal inpatient electronic health records},
journal = {JAMIA Open},
year = {2025},
volume = {8},
number = {2},
doi = {10.1093/jamiaopen/ooaf026}
}
EUVIMED