Analyzing Electronic Medical Records to Predict Risk of DIT (Death, Intubation, or Transfer to ICU) in Pediatric Respiratory Failure or Related Conditions

Large volumes of data are generated in hospital settings, including clinical and physiological data generated during the course of patient care. Our goal, as proof of concept, was to identify early clinical factors or traits useful for predicting the outcome, of death, intubation, or transfer to ICU, for children with pediatric respiratory failure. We implemented both supervised and unsupervised methods to extend our understanding on statistical relationships in clinical and physiological data. As a supervised learning method, we use binary logistic regression to predict the risk of developing DIT outcome. Next, we implemented unsupervised k-means algorithm on principal components of clinical and physiological data to further explore the contribution of clinical and physiological data on developing DIT outcome. Our results show that early signals of DIT can be detected in physiological data, and two risk factors, blood pressure and oxygen level, are the most important determinant of developing DIT.