Early prediction of central line associated bloodstream infection using machine learning

Abstract

•CLABSIs are a major source of hospital-acquired infections and can add $46,000 in costs per patient.•Three machine learning models to predict CLABSI were compared using EHR data.•The XGBoost model obtained an AUROC of 0.762 for CLABSI risk prediction. BackgroundCentral line-associated bloodstream infections (CLABSIs) are associated with significant morbidity, mortality, and increased healthcare costs. Despite the high prevalence of CLABSIs in the U.S., there are currently no tools to stratify a patient's risk of developing an infection as the result of central line placement. To this end, we have developed and validated a machine learning algorithm (MLA) that can predict a patient's likelihood of developing CLABSI using only electronic health record data in order to provide clinical decision support.MethodsWe created three machine learning models to retrospectively analyze electronic health record data from 27,619 patient encounters. The models were trained and validated using an 80:20 split for the train and test data. Patients designated as having a central line procedure based on International Statistical Classification of Diseases and Related Health Problems 10 codes were included.ResultsXGBoost was the highest performing MLA out of the three models, obtaining an AUROC of 0.762 for CLABSI risk prediction at 48 hours after the recorded time for central line placement.ConclusionsOur results demonstrate that MLAs may be effective clinical decision support tools for assessment of CLABSI risk and should be explored further for this purpose. Central line-associated bloodstream infections (CLABSIs) are associated with significant morbidity, mortality, and increased healthcare costs. Despite the high prevalence of CLABSIs in the U.S., there are currently no tools to stratify a patient's risk of developing an infection as the result of central line placement. To this end, we have developed and validated a machine learning algorithm (MLA) that can predict a patient's likelihood of developing CLABSI using only electronic health record data in order to provide clinical decision support. We created three machine learning models to retrospectively analyze electronic health record data from 27,619 patient encounters. The models were trained and validated using an 80:20 split for the train and test data. Patients designated as having a central line procedure based on International Statistical Classification of Diseases and Related Health Problems 10 codes were included. XGBoost was the highest performing MLA out of the three models, obtaining an AUROC of 0.762 for CLABSI risk prediction at 48 hours after the recorded time for central line placement. Our results demonstrate that MLAs may be effective clinical decision support tools for assessment of CLABSI risk and should be explored further for this purpose.

Topics & Concepts