Explainable AI unravels sepsis heterogeneity via coagulation-inflammation profiles for prognosis and stratification

Abstract

Abstract Sepsis is a leading cause of hospital mortality, and its significant heterogeneity complicates prognosis and stratification. To address this challenge, we developed an explainable artificial intelligence prognostic model (SepsisFormer, a transformer-based neural network) and an automated risk-stratification tool (SMART) for sepsis. In a multi-center retrospective study of 12,408 sepsis patients, SepsisFormer achieved high predictive accuracy (AUC: 0.9301, sensitivity: 0.9346, and specificity: 0.8312). SMART (AUC: 0.7360) surpassed most established scoring systems. Seven coagulation-inflammatory routine laboratory measurements and patient age were identified to classify patients’ four risk levels (mild, moderate, severe, dangerous) and two subphenotypes (CIS1 and CIS2), each with distinct clinical characteristics and mortality rates. Notably, patients with moderate/severe levels or CIS2 derive more significant benefits from anticoagulant treatment. Our work, therefore, offers a set of simple, real-time executable tools for sepsis heterogeneity, demonstrating the potential to enhance sepsis clinical practice globally, particularly in resource-constrained healthcare settings.