Predicting hypoglycemia in ICU patients: a machine learning approach.

Abstract

Background: The current study sets out to develop and validate a robust machine-learning model utilizing electronic health records (EHR) to forecast the risk of hypoglycemia among ICU patients in Jordan.

Research design and methods: The present study drew upon a substantial cohort of 13,567 patients admitted 26,248 times to the intensive care unit (ICU) over 10 years from July 2012 to July 2022. The primary outcome of interest was the occurrence of any hypoglycemic episode during the patient's ICU stay. Developing and testing predictor models was conducted using Python machine-learning libraries.

Results: A total of 1,896 were eligible to participate in the study, 206 experienced at least one hypoglycemic episode. Eight machine-learning models were trained to predict hypoglycemia. All models showed predicting power with a range of 74.53-99.69 for AUROC. Except for Naive Bayes, the six remaining models performed distinctly better than the basic logistic regression usually used for prediction in epidemiological studies. CatBoost model was consistently the best performer with the highest AUROC (0.99), accuracy and precision, sensitivity and specificity, and recall.

Conclusions: We used machine learning to anticipate the likelihood of hypoglycemia, which can significantly decrease hypoglycemia incidents and enhance patient outcomes.