Interpretable machine-learning model for real-time, clustered risk factor analysis of sepsis and septic death in critical care

•Comprehensive clinical-applicable and interpretable visualization of the predictive machine learning algorithm.•The real-time analysis of risk factors enables dynamic evaluation of predicted outcomes and in-time management in clinics.•The clustered analysis enables the discrimination of heterogeneity through unsupervised fashion in complex diseases like sepsis.•Our interpretable machine-learning algorithm has the potential for effective clinical decision-making and a comprehensive understanding of complex diseases such as sepsis.