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

TL;DR

This paper demonstrates that stratifying sepsis patients by organ dysfunction patterns improves machine learning models' ability to predict sepsis in ICU settings, promoting personalized approaches.

Contribution

It introduces a method to classify sepsis heterogeneity using organ dysfunction patterns, enhancing prediction accuracy beyond existing models.

Findings

Sepsis subpopulations have distinct organ dysfunction patterns.

Feature selection based on subpopulations improves classification performance.

Machine learning models benefit from stratified sepsis data.

Abstract

Current machine learning models aiming to predict sepsis from Electronic Health Records (EHR) do not account for the heterogeneity of the condition, despite its emerging importance in prognosis and treatment. This work demonstrates 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 machine learning efforts towards more personalised models for complex conditions including sepsis.