Predicting ventilator-associated pneumonia with machine learning

Abstract

Ventilator-associated pneumonia (VAP) is the most common and fatal nosocomial infection in intensive care units (ICUs). Existing methods for identifying VAP display low accuracy, and their use may delay antimicrobial therapy. VAP diagnostics derived from machine learning (ML) methods that utilize electronic health record (EHR) data have not yet been explored. The objective of this study is to compare the performance of a variety of ML models trained to predict whether VAP will be diagnosed during the patient stay. A retrospective study examined data from 6126 adult ICU encounters lasting at least 48 hours following the initiation of mechanical ventilation. The gold standard was the presence of a diagnostic code for VAP. Five different ML models were trained to predict VAP 48 hours after initiation of mechanical ventilation. Model performance was evaluated with regard to the area under the receiver operating characteristic (AUROC) curve on a 20% hold-out test set. Feature importance was measured in terms of Shapley values. The highest performing model achieved an AUROC value of 0.854. The most important features for the best-performing model were the length of time on mechanical ventilation, the presence of antibiotics, sputum test frequency, and the most recent Glasgow Coma Scale assessment. Supervised ML using patient EHR data is promising for VAP diagnosis and warrants further validation. This tool has the potential to aid the timely diagnosis of VAP.

The Epidemiological Characteristics of Ventilator-associated Pneumonia in Neurosurgery: A Ten-year Surveillance Study in A Large Chinese Tertiary Hospital

“…The BRT algorithm was derived from an ensemble machine learning method, which was proved e ciently in dealing with non-linear relationships and interaction between covariates [37] and had been widely used for diseases risk explanation and prediction, including avian in uenza [38], Middle East respiratory syndrome coronavirus [17] and scrub typhus [39]. Machine learning has been proven increasingly integrated into clinical practice, with applications ranging from pre-clinical data processing, bedside diagnosis assistance, patient strati cation, treatment decision-making, and early warning as part of primary and secondary prevention, which has been widely used for risk factors investigation and prognostic prediction [40], including VAP diagnostics [41] and prognosis [42].…”

Predicting Falls in Long-term Care Facilities: Machine Learning Study

“…Successive iterations of trees use gradient descent on the prior trees to minimize the error of the next tree that was formed. XGBoosting has been shown to exhibit excellent performance for a wide range of classification problems in acute and chronic conditions [ 44 - 48 ]. For comparison with the structurally complex XGBoosting model, logistic regression and multilayered perceptron models were also trained and tested.…”

Artificial Intelligence in Infection Management in the ICU

“…A significant number of AI/machine learning models have been developed that try to predict the occurrence of an event in advance, commonly termed 'forecasting' . Ventilator associated pneumonia (VAP), central-line associated blood stream infections (CLABSI), as well as the risk of colonization/infection with a multidrug resistant pathogen (MDR) are just a few examples for which prediction models have been developed [5][6][7][8]. The forecasting of sepsis and/or septic shock has, however, dominated this domain, as illustrated by the no more than 15 retrospective papers and 1 prospective interventional study carried out solely in the ICU that were identified by Fleuren et al in their recent systematic review [9].…”