VAP Risk Index: Early prediction and hospital phenotyping of ventilator-associated pneumonia using machine learning

Background: Ventilator-associated pneumonia (VAP) is a leading cause of morbidity and mortality in intensive care units (ICUs). Early identification of patients at risk of VAP enables early intervention, which in turn improves patient outcomes. We developed a predictive model for individualized risk assessment utilizing machine learning to identify patients at risk of developing VAP. Methods: : The Philips eRI database, a multi-institution electronic medical record (EMR), was used for model development. For adult (≥18y) patients, we propose a set of criteria using indications of the start of a new antibiotic treatment temporally contiguous to a microbiological test to mark suspected infection events, of which those with a positive culture are labeled as presumed VAP if 1) the event occurs at least 48 hours after intubation, and 2) there are no indications of community-acquired pneumonia (CAP) or other hospital-acquired infections (HAI) in the patient charts. The resulting VAP and no-VAP (control) cases were then used to build an ensemble of decision trees to predict the risk of VAP in the next 24hrs using data on patient’s demographics, vitals, labs, and ventilator settings. Results: : The resulting model predicts the development of VAP with an AUC of 76% and AUPRC of 75% at a lead time of 24h in advance. Additionally, we group hospitals that are similar in healthcare processes into distinct clusters and characterize VAP prediction for the identified hospital clusters. We show inter-hospital (teaching status and healthcare processes) and cohort-specific (age groups, gender, early vs late VAP, ICU mortality status) differences in VAP prediction and associated symptomologies. Conclusions: : Our proposed VAP criteria provide a temporal context for the infection event and enable studying the disease course. Using the proposed criteria, we curated a patient cohort and used it to build a model to predict an impending VAP event before any clinical suspicions. We present a clustering approach to tailor the VAP prediction model for different hospital types based on their EMR data characteristics. The developed VAP prediction model provides instantaneous risk score that allows early interventions and confirmatory diagnostic actions.