AUTHOR=Singh Pradeep , Nagori Aditya , Lodha Rakesh , Sethi Tavpritesh TITLE=Early prediction of hypothermia in pediatric intensive care units using machine learning JOURNAL=Frontiers in Physiology VOLUME=Volume 13 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.921884 DOI=10.3389/fphys.2022.921884 ISSN=1664-042X ABSTRACT=Hypothermia is a life-threatening condition where the temperature of the body drops below 35°C and is a key source of concern in Intensive Care Units. Early identification can help to nudge clinical management to initiate early interventions. Despite its importance, very few studies have focused on the early prediction of hypothermia. In this study, we aim to monitor and predict Hypothermia (30min-4hr) ahead of its onset using machine learning models developed on physiological vitals and to prospectively validate the best performing model in the pediatric ICU. We developed and evaluated ML algorithms for the early prediction of hypothermia in a pediatric ICU. Sepsis advanced forecasting engine ICU Database (SafeICU) data resource, is an in-house ICU source of data that is built in the Pediatric ICU at the AIIMS, New Delhi. The training set consisted of windows of the length of 4.2 hr with a lead time of 30min-4hr from the onset of hypothermia. A set of 3835 hand-engineered time-series features were calculated to capture physiological features from the time series. Features selection using the Boruta algorithm was performed to select the most important predictors of hypothermia. A battery of models such as gradient boosting machine, random forest, AdaBoost, and support vector machine was evaluated. The best-performing model was prospectively validated. A total of 148 patients with 193 ICU stays were eligible for the model development cohort. The gradient boosting model performed best with an AUROC of 85%(SD=1.6) and a precision of 59.2%(SD=8.8) for a 30-minute lead time before the onset of Hypothermia onset. As expected, the model showed a decline in model performance at higher lead times, such as AUROC of 77.2%(SD=2.3 ) and precision of 41.34%(SD=4.8) for four hours ahead of Hypothermia onset. Our model produced equal and superior results for the prospective validation, where an AUROC of 79.8% and a precision of 53% for a 30-minute lead time before the onset of Hypothermia whereas an AUROC of 69.6% and a precision of 38.52% for a (30minutes-4Hours) lead time prospective validation of Hypothermia. Therefore our methodology outperforms the SOTA performance in predicting hypothermia, a major complication in pediatric ICUs