What question did this study set out to answer?

The aim is to create a simple and transparent model to predict ICU mortality using readily available data.

May 20, 2026

C55-27 A Simple AI Model Predicts ICU Mortality From Routinely Collected Data in a Large Multi-Center Cohort

Key Points

The aim is to create a simple and transparent model to predict ICU mortality using readily available data.
Retrospective cohort study utilizing the eICU Collaborative Research Database
Logistic regression model trained on 80% of data with evaluation on 20%
Model performance assessed with metrics including AUC, precision, recall, and calibration scores.
Model performance on evaluation set achieved AUC of 0.806 and log loss of 0.243
At 0.20 probability threshold, precision was 0.409, recall 0.416, and specificity 0.940
Despite high missingness for some variables, findings remained robust.

Abstract

Abstract Rationale Simple, transparent risk models can help intensive care unit (ICU) teams triage care and communicate prognosis. We aimed to develop and evaluate a parsimonious mortality-prediction model using variables available in the first hours of ICU care. Methods We performed a retrospective cohort study using the publicly available eICU Collaborative Research Database (eICU-CRD). Adult ICU stays with an in-hospital mortality label were included. Candidate predictors were age, sex, Acute Physiology and Chronic Health Evaluation IVa (APACHE-IVa) score, lactate, hemoglobin, 6-hour urine output, and a binary indicator for missing urine output. Data were partitioned 80%/20% into training and evaluation sets using a deterministic hash of the patient/stay identifier to prevent patient leakage. A logistic-regression model (BigQuery ML) was trained and evaluated for discrimination (area under the receiver operating characteristic curve AUC) and log loss; operating-point performance across thresholds (precision, recall, F1, specificity, accuracy, negative predictive value NPV); and calibration (Brier score, Hosmer–Lemeshow χ², and a post-/hoc recalibration fit yielding intercept and slope). Results The cohort contained 349,391 ICU stays with 31,741 deaths (9.1%). On the 20% heldout evaluation set, overall performance was AUC 0.806 and log loss 0.243. Calibration was favorable by Brier score (0.0677) and recalibration parameters (intercept −0.0218, slope 1.0418), although the Hosmer–Lemeshow test was significant (χ² 714.8; p 0.001), which is common in very large samples. At the F1-optimal probability threshold of 0.20, precision was 0.409, recall 0.416, F1 0.412, specificity 0.940, accuracy 0.892, and NPV 0.941; at the default 0.50 threshold, precision was 0.672 and recall 0.155. Findings were robust despite high missingness in lactate (∼62%) and 6-hour urine output (∼52%), managed via first-available values and a missingness indicator. Conclusion A simple, explainable 7-variable logistic-regression model built from routinely collected ICU data achieved good discrimination and near-ideal average calibration in a large multicenter cohort. Such parsimonious models may support early triage and communication while remaining interpretable. Planned work includes temporal and external validation, decision-curve analysis, and prospective evaluation of clinical utility. References (optional—counts toward 400 words): Pollard TJ, Johnson AEW, Raffa JD, Celi LA, Mark RG, Badawi O. The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Scientific Data. 2018;5:180178. doi:10.1038/sdata.2018.178. This abstract is funded by: None

Mark Helpful

Bookmark

Relay