A FHIR-Powered Python Implementation of the SENECA Algorithm for Sepsis Subtyping

Sepsis is a heterogeneous syndrome with high morbidity and mortality. Despite extensive clinical trials, therapeutic progress remains limited, in part due to the absence of actionable sepsis subtypes.This study aimed to evaluate the feasibility of using HL7 Fast Healthcare Interoperability Resources (FHIR) for prerandomization sepsis subtyping to support clinical trial enrichment across multiple health systems.Data from 765 encounters at two academic medical centers were analyzed. FHIR-based resources were extracted from both research data warehouses (RDWs) and electronic health records (EHRs). A Python implementation of the Sepsis Endotyping in Emergency Care (SENECA) sepsis subtyping algorithm was developed to query and assemble FHIR resources for subtype classification.Open-source Python code for the SENECA algorithm is provided on GitHub. Experiments demonstrated: (1) successful sepsis subtyping across both health systems; (2) concordance between the original R implementation and the new Python implementation; and (3) discrepancies when comparing RDW-derived versus EHR-integrated FHIR APIs, primarily due to query and filtering limitations. Missing data were common and influenced by both clinical practice and FHIR API constraints. We provide five recommendations to address these challenges.FHIR can support multi-institutional sepsis subtyping and trial enrichment, though technical and governance challenges remain.