• Publicly available EHR databases lack key sepsis biomarkers such as CRP and PCT. • Key sepsis biomarkers rarely rank highly in model-derived feature importance scores. • Adoption of explainable ML has increased by 73% per year between 2019 and 2025. To systematically review machine learning-based sepsis prediction studies, examining model explainability and the extent to which explanations reflect key sepsis biomarkers. Following the PRISMA guidelines, we reviewed the titles, abstracts, and full texts. The search was conducted in four major bibliographic databases with publication dates from January 1, 2019 to July 16, 2025. The included studies provided a clear definition of sepsis based on the Sepsis-3 criteria and involved critically ill adult human subjects. Two authors (IP and AKa) independently reviewed and assessed each study. Using statistical methods, we assessed study quality and explainability trends. A total of 37 studies were included. Our analysis revealed a notable temporal increase (≈67% greater odds per year) in the use of explainability methods in sepsis prediction models. However, key sepsis biomarkers (procalcitonin or C-reactive protein) were not among the top predictive features, highlighting a gap between the model output and known sepsis pathophysiology. Model attributions often mirror what electronic health records measure most consistently (vital signs) rather than what is most biologically specific, partly due to the high missingness and irregular sampling of CRP/PCT in public datasets. Heterogeneity in feature selection and reliance on local datasets limit generalizability, while sparse code/data sharing constrains reproducibility. This review newly quantifies the rise of explainability use in sepsis prediction and identifies a consistent gap between model explanations and key sepsis biomarkers, providing a foundation for future work to bridge data-driven insights with sepsis pathophysiology. CRD420251101470.
Papapanagiotou et al. (Thu,) studied this question.