Machine learning algorithms for prediction of ventilator associated pneumonia in traumatic brain injury patients from the MIMIC-III database

Abstract

BackgroundVentilator associated pneumonia (VAP) is a common complication and associated with poor prognosis of traumatic brain injury (TBI) patients. ObjectivesThis study was conducted to explore the predictive performance of different machine-learning algorithms for VAP in TBI patients. MethodsTBI patients receiving mechanical ventilation more than 48 hours from the Medical Information Mart for Intensive Care-III (MIMIC-III) database were eligible for the study. The VAP was confirmed based on the ICD-9 code. Included patients were separated to the training cohort and the validation cohort with a ratio of 7:3. Predictive models based on different machine learning algorithms were developed using 5-fold cross validation in the training cohort and then verified in the validation cohort by evaluating the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy and F score. Results786 TBI patients from the MIMIC-III were finally included with the VAP incidence of 44.0%. The random forest performed the best on predicting VAP in the training cohort with a AUC of 1.000. The XGBoost and AdaBoost were ranked the second and the third with a AUC of 0.915 and 0.789 in the training cohort. While the AdaBoost performed the best on predicting VAP in the validation cohort with a AUC of 0.706. The XGBoost and random forest were ranked the second and the third with the AUC of 0.685 and 0.683 in the validation cohort. Generally, the random forest and XGBoost were likely to be over-fitting while the AdaBoost was relatively stable in predicting the VAP. ConclusionsThe AdaBoost performed well and stably on predicting the VAP in TBI patients. Developing programs using AdaBoost in portable electronic devices may effectively assist physicians in assessing the risk of VAP in TBI.