Explainable AI-driven heterogeneity using coagulation–inflammatory markers improves prognosis prediction, risk stratification, and anticoagulant treatment effects for sepsis

Sepsis, a leading cause of hospital mortality, is characterized by substantial heterogeneity, hindering the development of effective and interpretable prognostic and stratification methods. To address this challenge, we developed an explainable prognostic model (SepsisFormer, a transformer-based deep neural network with an enhanced domain-adaptive generator) and an automated risk stratification tool (SMART, a scorecard consistent with medical knowledge). In a multicenter 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 or severe levels or CIS2 derive more significant benefits from anticoagulant treatment. In conclusion, explainable artificial intelligence can potentially improve sepsis outcomes by uncovering patient heterogeneity.