What question did this study set out to answer?

The aim is to create a model that detects hemorrhage in ICU patients using physiological data.

February 16, 2026Open Access

Development and evaluation of a prediction model for adult ICU hemorrhage using only continuous cardiorespiratory data

Key Points

The aim is to create a model that detects hemorrhage in ICU patients using physiological data.
Collected continuous cardiorespiratory and transfusion data from four ICU cohorts.
Defined hemorrhage as three or more transfusions within 24 hours.
Trained a penalized logistic regression model to predict hemorrhage within 8 hours.
Evaluated model performance across multiple ICU cohorts.
The model achieved an AUC of 0.706 in the development cohort and 0.712 in evaluation cohorts.
Predicted risk increased significantly before clinical recognition of bleeding.
Performance varied by age, race, and gender, with lower accuracy in older adults and females.
The hemorrhage score outperformed the shock index in predictive ability.

Abstract

Abstract Objective: Develop and evaluate whether a model trained to detect the physiological signature of hemorrhage in ICU patients generalizes to other cohorts.Approach: We collected cardiorespiratory monitoring data and packed red blood cell administration data from consecutive adult admissions in one development and three evaluation ICU cohorts. We defined hemorrhage as three or more transfusions within 24 hours. We trained a penalized logistic regression model to predict hemorrhage within 8 hours and externally evaluated the predictions.Main results: The evaluation ICU cohorts comprised more than 6M q15-minute observations. The cross-validated AUC in the development cohort was 0.706 (141 event admissions, 95% CI: 0.656 - 0.757) and 0.712 (968 event admissions, 95% CI: 0.693 – 0.726) for 17,591 medical and surgical ICU patients in the combination of 3 evaluation cohorts. The calibration slope of the hemorrhage model was close to unity (1.041, 95%CI: 0.956 – 1.127). Predicted risk increased significantly in the 8 hours preceding clinical recognition of bleeding. There was no evidence of model performance drifting over time. There was evidence for lower performance for patients over 75 (20% lower than patients 18 to 44), among patients at Pitt (24% lower than MIMIC III), Black patients (11% lower than White patients), and females (12% lower than males). The shock index also had reduced performance at Pitt, for female patients, and for patients over 75, though not for Black patients. The hemorrhage score had a higher net benefit than the shock index. Significance: Patients in intensive care units have an increased risk for bleeding due to their chronic and acute illness, and earlier bleeding identification leads to better outcomes. A risk model for hemorrhage based only on continuous cardiorespiratory data has clinically relevant predictive performance that generalizes across three cohorts with different monitoring devices and electronic health record systems.

Ask AI

Helpful

Bookmark

View Full Paper