Prediction of in-hospital mortality at a 72-hour intensive care landmark in patients with sepsis and pre-existing hypertension: development and external validation
- 1Shandong Provincial Public Health Clinical Center: Shandong Provincial Chest Hospital
Abstract
BackgroundIn patients with sepsis and pre-existing hypertension, admission findings may not adequately describe the subsequent course of circulatory support and organ dysfunction. We developed and externally validated a model to reassess in-hospital mortality risk after the first 72 hours of intensive care.
MethodsThis retrospective study used MIMIC-IV for development and eICU-CRD for external validation. Patients had received vasoactive agents and remained in the ICU for at least 72 hours. Static variables were combined with features from six consecutive 12-hour windows. Imputation, feature selection, model fitting, and calibration were performed within training folds during five-fold cross-validation. The final XGBoost model was applied externally without refitting. Evaluation included discrimination, calibration, decision curves, and risk stratification, with an exploratory comparison of static-only and static-plus-dynamic feature sets.
ResultsThe development and external cohorts included 1019 and 1747 patients, with 338 (33.2%) and 516 (29.5%) deaths, respectively. Internal area under the receiver operating characteristic curve (AUC) was 0.752 (95% CI 0.720-0.784). External AUC was 0.713 (95% CI 0.687-0.739), average precision was 0.536, the Brier score was 0.185, and the calibration slope was 0.744. Mortality increased across external risk tertiles from 13.7% to 47.3%. In an exploratory feature-set comparison, the static-plus-dynamic feature set showed a 0.071 higher internal AUC than the static feature set (95% CI 0.042-0.109).
ConclusionsInformation accumulated during the first 72 hours supported subsequent mortality risk stratification in this selected population. The model retained moderate discrimination externally, supporting further evaluation as an adjunct to clinical reassessment. Local calibration and the clinical consequences of acting on model predictions require evaluation before routine use.
Related
- Development and multi-database validation of machine learning models for 28-day mortality prediction in ICU patients with COPD and pulmonary hypertension.
- Development and validation of an interpretable machine learning model for early prediction of mortality in ICU patients with chronic obstructive pulmonary disease and heart failure
- An interpretable machine learning model for predicting intensive care unit mortality risk in elderly patients with concomitant cardiogenic shock and sepsis: Development and external validation using two large critical care databases
- Admission-time prediction of 7-day mortality in clinician-attributed hypertensive intracerebral hemorrhage: development and external validation against the ICH score
- Development and Validation of a Prediction Model for Pulmonary Arterial Hypertension in Diabetic Patients: A Retrospective Study of 57,375 Patients.
BibTeX
@misc{chen2026prediction,
title = {{Prediction of in-hospital mortality at a 72-hour intensive care landmark in patients with sepsis and pre-existing hypertension: development and external validation}},
author = {Y. Chen and Y. Cai and H. Bian and M. Fu},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.02.26364566},
url = {https://www.medrxiv.org/content/10.64898/2026.10.02.26364566v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Prediction of in-hospital mortality at a 72-hour intensive care landmark in patients with sepsis and pre-existing hypertension: development and external validation
AU - Y. Chen
AU - Y. Cai
AU - H. Bian
AU - M. Fu
PY - 2026
DA - 2026/10/02
PB - medRxiv
DO - 10.64898/2026.10.02.26364566
UR - https://www.medrxiv.org/content/10.64898/2026.10.02.26364566v1
AB - BackgroundIn patients with sepsis and pre-existing hypertension, admission findings may not adequately describe the subsequent course of circulatory support and organ dysfunction. We developed and externally validated a model to reassess in-hospital mortality risk after the first 72 hours of intensive care. MethodsThis retrospective study used MIMIC-IV for development and eICU-CRD for external validation. Patients had received vasoactive agents and remained in the ICU for at least 72 hours. Static variables were combined with features from six consecutive 12-hour windows. Imputation, feature selection, model fitting, and calibration were performed within training folds during five-fold cross-validation. The final XGBoost model was applied externally without refitting. Evaluation included discrimination, calibration, decision curves, and risk stratification, with an exploratory comparison of static-only and static-plus-dynamic feature sets. ResultsThe development and external cohorts included 1019 and 1747 patients, with 338 (33.2%) and 516 (29.5%) deaths, respectively. Internal area under the receiver operating characteristic curve (AUC) was 0.752 (95% CI 0.720-0.784). External AUC was 0.713 (95% CI 0.687-0.739), average precision was 0.536, the Brier score was 0.185, and the calibration slope was 0.744. Mortality increased across external risk tertiles from 13.7% to 47.3%. In an exploratory feature-set comparison, the static-plus-dynamic feature set showed a 0.071 higher internal AUC than the static feature set (95% CI 0.042-0.109). ConclusionsInformation accumulated during the first 72 hours supported subsequent mortality risk stratification in this selected population. The model retained moderate discrimination externally, supporting further evaluation as an adjunct to clinical reassessment. Local calibration and the clinical consequences of acting on model predictions require evaluation before routine use.
ER -