Predicting KRT or Death in Critically Ill Patients with Rhabdomyolysis Using Machine Learning
Kidney360 · 2026-10 · 7 (10) · 2263-2273
DOI: 10.34067/kid.0000001292 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Kidney360, online erschienen am 23.07.2026. Verfasst von Joey Mercier und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Internal Medicine, Northern Ontario School of Medicine University, Sudbury, Ontario, Canada. Hauptthemen laut MEDLINE: Rhabdomyolysis, Critical Illness, Machine Learning, Hospital Mortality. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Key Points A machine learning model predicted in-hospital death or dialysis in patients in intensive care rhabdomyolysis. External validation was associated with improved discrimination and decision-analytic utility versus McMahon score. A web-based calculator enables risk-stratified triage using routinely available clinical data.
Background
Rhabdomyolysis is associated with outcomes ranging from muscle injury to AKI, KRT, and death. Early identification of patients at highest risk of severe outcomes may help inform triage, monitoring, and nephrology consultation. The aim of this study was to develop and externally validate a machine learning model to predict in-hospital death or KRT in patients with rhabdomyolysis.
Methods
We analyzed two independent US intensive care unit databases: the Philips eICU Collaborative Research Database (eICU) and the Medical Information Mart for Intensive Care IV (MIMIC). Adults with creatine kinase (CK) > 5000 IU/L within 72 hours of admission and length of stay greater than 1 day were included. Patients receiving KRT before admission or with CK elevation due to myocardial infarction were excluded. The eICU cohort was randomly divided into training and internal test sets to develop a random forest model predicting a composite outcome of in-hospital death or KRT. External validation was performed in the MIMIC cohort. Model performance was compared with the McMahon score.
Results
A total of 753 admissions in eICU and 768 in MIMIC were included (30% female, mean age 50 years). The composite outcome occurred in 17% and 10%, respectively. The final model incorporated 15 routinely available variables. In external validation, the model demonstrated an area under the receiver operating characteristic curve of 0.89, sensitivity of 80%, specificity of 84%, and positive likelihood ratio of 5.01. The model showed better discrimination and greater decision-analytic benefit than the McMahon score. CK alone showed poor discrimination for the composite outcome.
Conclusions
A machine learning model using routinely available clinical data predicted in-hospital death or acute KRT in critically ill patients with rhabdomyolysis and outperformed an established risk score in two intensive care unit cohorts. These findings support further prospective validation before clinical implementation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Internal Medicine, Northern Ontario School of Medicine University, Sudbury, Ontario, Canada.
- Sault Area Hospital, Sault Ste. Marie, Ontario, Canada.
- Department of Internal Medicine, University of Manitoba, Winnipeg, Manitoba, Canada.
- St Boniface Hospital, Winnipeg, Manitoba, Canada.
ORCID-Profile: Joey Mercier, Jim Boseovski
Zitieren
APA
Mercier, J., Sharma, A., & Boseovski, J. (2026). Predicting KRT or Death in Critically Ill Patients with Rhabdomyolysis Using Machine Learning. Kidney360, 7(10), 2263-2273. https://doi.org/10.34067/kid.0000001292
Vancouver
Mercier J, Sharma A, Boseovski J. Predicting KRT or Death in Critically Ill Patients with Rhabdomyolysis Using Machine Learning. Kidney360. 2026;7(10):2263-2273. doi:10.34067/kid.0000001292
BibTeX
@article{Mercier2026,
author = {Mercier, Joey and Sharma, Aditya and Boseovski, Jim},
title = {Predicting KRT or Death in Critically Ill Patients with Rhabdomyolysis Using Machine Learning},
journal = {Kidney360},
year = {2026},
volume = {7},
number = {10},
pages = {2263--2273},
doi = {10.34067/kid.0000001292}
}
EUVIMED