Fast and interpretable mortality risk scores for critical care patients
Journal of the American Medical Informatics Association · 2025
DOI: 10.1093/jamia/ocae318 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, 2025. Verfasst von Chloe Qinyu Zhu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Duke University, Durham, NC 27708, United States. Hauptthemen laut MEDLINE: Machine Learning, Hospital Mortality, Algorithms, Critical Care. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDA NIH HHS, NINDS NIH HHS, NIH HHS.
Abstract (Originalsprache)
Objective
Prediction of mortality in intensive care unit (ICU) patients typically relies on black box models (that are unacceptable for use in hospitals) or hand-tuned interpretable models (that might lead to the loss in performance). We aim to bridge the gap between these 2 categories by building on modern interpretable machine learning (ML) techniques to design interpretable mortality risk scores that are as accurate as black boxes. Material and Methods We developed a new algorithm, GroupFasterRisk, which has several important benefits: it uses both hard and soft direct sparsity regularization, it incorporates group sparsity to allow more cohesive models, it allows for monotonicity constraint to include domain knowledge, and it produces many equally good models, which allows domain experts to choose among them. For evaluation, we leveraged the largest existing public ICU monitoring datasets (MIMIC III and eICU).
Results
Models produced by GroupFasterRisk outperformed OASIS and SAPS II scores and performed similarly to APACHE IV/IVa while using at most a third of the parameters. For patients with sepsis/septicemia, acute myocardial infarction, heart failure, and acute kidney failure, GroupFasterRisk models outperformed OASIS and SOFA. Finally, different mortality prediction ML approaches performed better based on variables selected by GroupFasterRisk as compared to OASIS variables.
Discussion
GroupFasterRisk’s models performed better than risk scores currently used in hospitals, and on par with black box ML models, while being orders of magnitude sparser. Because GroupFasterRisk produces a variety of risk scores, it allows design flexibility—the key enabler of practical model creation.
Conclusion
GroupFasterRisk is a fast, accessible, and flexible procedure that allows learning a diverse set of sparse risk scores for mortality prediction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, Duke University, Durham, NC 27708, United States.
- Microsoft Research, New York, NY 10012, United States.
- Cornell University, Ithaca, NY 14853, United States.
Förderung
- NIDA NIH HHS
- NINDS NIH HHS
- NIH HHS
- NSF
- NHLBI NIH HHS
- NIH
- NIDA
Zitieren
APA
Zhu, C. Q., Tian, M., Semenova, L., Liu, J., Xu, J., Scarpa, J., & Rudin, C. (2025). Fast and interpretable mortality risk scores for critical care patients. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocae318
Vancouver
Zhu CQ, Tian M, Semenova L, Liu J, Xu J, Scarpa J, et al. Fast and interpretable mortality risk scores for critical care patients. Journal of the American Medical Informatics Association. 2025. doi:10.1093/jamia/ocae318
BibTeX
@article{Zhu2025,
author = {Zhu, Chloe Qinyu and Tian, Muhang and Semenova, Lesia and Liu, Jiachang and Xu, Jack and Scarpa, Joseph and Rudin, Cynthia},
title = {Fast and interpretable mortality risk scores for critical care patients},
journal = {Journal of the American Medical Informatics Association},
year = {2025},
doi = {10.1093/jamia/ocae318}
}
EUVIMED