Engineering biomarker representations of vital signs data enhances deep learning mortality prediction
Journal of the American Medical Informatics Association · 01.07.2026 · 33 (7) · 1381-1386
DOI: 10.1093/jamia/ocag066 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 02.05.2026. Verfasst von Behrooz Mamandipoor und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, University of California, San Diego Health, La Jolla, CA, 92093, United States. Hauptthemen laut MEDLINE: Deep Learning, Vital Signs, Hospital Mortality. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 11 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Objectives
We evaluated bidirectional long short-term memory models for predicting inpatient mortality using different approaches to processing vital signs data collected during the initial 24 h of intensive care unit (ICU) admissions. Materials and Methods We compared 3 vital-sign representations: (1) raw data recorded every 5 min, (2) preprocessed data averaged hourly, and (3) preprocessed data using biomarker representations that extends a digital oximetry biomarker toolbox of PhysioZoo software, applied to blood pressure, heart rate, temperature, respiratory rate, and SpO2.
Results
Across 2 large ICU datasets, HiRID and eICU, models trained on the frequency-normalized representation achieved higher discrimination and lower Brier scores than those trained on raw 5-min and hourly averaged data.
Discussion
The use of biomarker representations of vital signs yielded the largest improvements in discrimination and overall probabilistic performance reflected by lower Brier scores for predicting inpatient mortality by deep learning.
Conclusion
Thus, we recommend using a similar approach to vital signs preprocessing for time-series predictive models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Biomedical Informatics, University of California, San Diego Health, La Jolla, CA, 92093, United States.
- Division of Perioperative Informatics, Department of Anesthesiology, University of California, San Diego, La Jolla, CA, 92037, United States.
Förderung
- NIH HHS
- National Institutes of Health
Zitieren
APA
Mamandipoor, B., Shen, I., Hsu, C. N., & Gabriel, R. A. (2026). Engineering biomarker representations of vital signs data enhances deep learning mortality prediction. Journal of the American Medical Informatics Association, 33(7), 1381-1386. https://doi.org/10.1093/jamia/ocag066
Vancouver
Mamandipoor B, Shen I, Hsu CN, Gabriel RA. Engineering biomarker representations of vital signs data enhances deep learning mortality prediction. Journal of the American Medical Informatics Association. 2026;33(7):1381-1386. doi:10.1093/jamia/ocag066
BibTeX
@article{Mamandipoor2026,
author = {Mamandipoor, Behrooz and Shen, Isabella and Hsu, Chun-Nan and Gabriel, Rodney A},
title = {Engineering biomarker representations of vital signs data enhances deep learning mortality prediction},
journal = {Journal of the American Medical Informatics Association},
year = {2026},
volume = {33},
number = {7},
pages = {1381--1386},
doi = {10.1093/jamia/ocag066}
}
EUVIMED