Predicting ICU Mortality Among Septic Patients Using Machine Learning Technique

Abstract

Introduction: Sepsis leads to substantial global health burdens in terms of morbidity and mortality and is associated with numerous risk factors. It is crucial to identify sepsis at an early stage in order to limit its escalation and sequelae associated with the condition. The purpose of this research is to predict ICU mortality early and evaluate the predictive accuracy of machine learning algorithms for ICU mortality among septic patients. Methods: The study used a retrospective cohort from computerized ICU records accumulated from 280 hospitals between 2014 and 2015. Initially the sample size was 23.47K. Several machine learning models were trained, validated, and tested using five-fold cross-validation, and three sampling strategies (Under-Sampling, Over-Sampling, and Combination). Results: The under-sampled approach combined with augmentation for the Extra Trees model produced the best performance with Accuracy, Precision, Sensitivity, Specificity, F1-Score, and AUC of 90.99%, 84.16%, 94.89%, 88.48%, 89.20%, and 91.69%, respectively, with Top 30 features. For Over-Sampling, the Top 29 combined features showed the best performance with Accuracy, Precision, Sensitivity, Specificity, F1-Score, and AUC of 82.99%, 51.38%, 71.72%, 85.41%, 59.87%, and 78.56%, respectively. For Down-Sampling, the Top 31 combined features produced Accuracy, Precision, Sensitivity, Specificity, F1-Score, and AUC of 81.78%, 49.08%, 79.76%, 82.21%, 60.76%, and 80.98%, respectively. Conclusions: Machine learning models can reliably predict ICU mortality when suitable clinical predictors are utilized. The study showed that the proposed Extra Trees model can predict ICU mortality with an accuracy of 90.99% accuracy using only single-entry data. Incorporating longitudinal data could further enhance model performance.

Keywords: ICU mortality; augmentation; machine learning; over-sampling; prediction; sepsis.

Figure 1

A general architecture of random forest.

Figure 2

Feature ranked according to XGBoost feature selection algorithms.

Figure 3

ROC curves for under-sampled techniques for the ET, SVC, and RF classifier.

Figure 4

Confusion matrix for SVC classifier for top 31 features on under sampled dataset.

Figure 5

ROC curves for over-sampled techniques for ET, SVC, and RF classifier.

Figure 6

Confusion matrix for SVC classifier for top 29 features on over-sampled dataset.

Figure 7

ROC curves for combined sample techniques for the ET, SVC, and RF classifier.

Figure 8

Confusion matrix for stacking classifier for each subset.