Advanced Meta-Ensemble Machine Learning Models for Early and Accurate Sepsis Prediction to Improve Patient Outcomes

TL;DR

This study develops advanced machine learning meta-ensemble models that significantly improve early sepsis prediction accuracy over traditional screening tools, potentially enhancing patient outcomes.

Contribution

The paper introduces a novel meta-ensemble approach combining Random Forest, XGBoost, and Decision Tree models for superior sepsis prediction accuracy.

Findings

Meta-ensemble achieved AUC-ROC of 0.96

Random Forest scored 0.95 AUC-ROC

Ensemble outperforms individual models

Abstract

Sepsis, a critical condition from the body's response to infection, poses a major global health crisis affecting all age groups. Timely detection and intervention are crucial for reducing healthcare expenses and improving patient outcomes. This paper examines the limitations of traditional sepsis screening tools like Systemic Inflammatory Response Syndrome, Modified Early Warning Score, and Quick Sequential Organ Failure Assessment, highlighting the need for advanced approaches. We propose using machine learning techniques - Random Forest, Extreme Gradient Boosting, and Decision Tree models - to predict sepsis onset. Our study evaluates these models individually and in a combined meta-ensemble approach using key metrics such as Accuracy, Precision, Recall, F1 score, and Area Under the Receiver Operating Characteristic Curve. Results show that the meta-ensemble model outperforms individual models, achieving an AUC-ROC score of 0.96, indicating superior predictive accuracy for early sepsis detection. The Random Forest model also performs well with an AUC-ROC score of 0.95, while Extreme Gradient Boosting and Decision Tree models score 0.94 and 0.90, respectively.