Interpretable Machine Learning Model for Predicting Sepsis and Septic Shock Among Patients with Documented Fever at Emergency Department Triage Using Patients' Historical Data.

Using the AutoScore framework, we developed a novel scoring system for predicting sepsis and septic shock at the triage stage, incorporating nine variables and a maximum score of 29.

Our model incorporated nine variables including initial vital signs, age, baseline platelet count, total bilirubin, and creatinine levels.

Compared to qSOFA ≥ 2 (AUROC: 0.605) and Modified Early Warning Score ≥ 5 (AUROC: 0.678), our scoring system demonstrated superior predictive performance for septic shock.

For comparable specificity levels (ranging from 0.50 to 0.95), our scoring system achieved higher sensitivity than Modified Early Warning Score.