Early Sepsis Prediction Using Publicly Available Data: High-Performance AI/ML Models with First-Hour Clinical Information

Abstract

Objectives: Early identification of sepsis is critical, as delayed diagnosis significantly increases morbidity and mortality. We aimed to develop and validate AI/ML models for early sepsis prediction using structured electronic health record (EHR) data, waveform data, and a combination of both. Methods: We conducted a retrospective observational study using the AIM-AHEAD60 subset of the CHoRUS dataset. Adult patients (≥18 years) with a final diagnosis of sepsis were included. Structured EHR data (demographics, initial vital signs, laboratory results) and waveform data (continuous vital signs) from the first hour of hospital arrival were extracted. Three algorithms (i.e., XGBoost, LightGBM, and HistGB) were developed with a focus on maximizing the performance metric of recall. Other performance metrics were also assessed, including accuracy, precision, F1 score, and the area under the receiver operating characteristic curve (AUROC). Results: A total of 11,312 unique patients met the inclusion criteria, among whom 2245 individuals (19.85%) were diagnosed with sepsis at least once. Using structured EHR data alone, laboratory variables such as lactate and leukocyte count were most predictive. Waveform models identified respiratory rate, systolic blood pressure, and temperature trends in the first hour as key predictors. Combined models highlighted mean temperature and mean systolic blood pressure as top features. XGBoost achieved the highest AUROC (0.922) across all data configurations, with a recall above 80%, demonstrating robust performance despite substantial missing data. Conclusions: High-performing AI/ML models for early sepsis prediction can be developed from publicly available datasets using only first-hour clinical information. XGBoost models demonstrate strong potential for real-time clinical screening.

Topics & Concepts