On Classifying Sepsis Heterogeneity in the ICU: Insight Using Machine Learning

Tel: 44 (0) 758 285 9501 Mesh Term s Machine Learning, Sepsis Syndrome Word Count: 2,000 AB STRACT Current machine learning models aiming to predict sepsis from Electronic Health Records (EHR) do not account for the heterogeneity of the condition, despite its e me r ging importance in prognosis and treatment. This work demonstrate s the added value of stratifying the types of organ dysfunction observed in patients who develop sepsis in the ICU in improving the ability to recognise patients at risk of sepsis from their EHR data. Using an ICU dataset of 13,728 records, we identify clinically significant sepsis subpopulations with distinct organ dysfunction patterns . Classification experiments using Random Forest, Gradient Boost Trees and Support Vector Machines, aiming to distinguish patients who develop sepsis in the ICU from those who do not, show that features selected using sepsis subpopulations as background knowledge yield a superior performance regardless of the classification model used. Our findings can steer mach ine learning efforts towards more personalised models for complex conditions including sepsis.