Predicting hypoglycemia in critically Ill patients using machine learning and electronic health records.

Hypoglycemia is a common occurrence in critically ill patients and is associated with significant mortality and morbidity. We developed a machine learning model to predict hypoglycemia by using a multicenter intensive care unit (ICU) electronic health record dataset. Machine learning algorithms were trained and tested on patient data from the publicly available eICU Collaborative Research Database. Forty-four features including patient demographics, laboratory test results, medications, and vitals sign recordings were considered. The outcome of interest was the occurrence of a hypoglycemic event (blood glucose < 72 mg/dL) during a patient's ICU stay. Machine learning models used data prior to the second hour of the ICU stay to predict hypoglycemic outcome. Data from 61,575 patients who underwent 82,479 admissions at 199 hospitals were considered in the study. The best-performing predictive model was the eXtreme gradient boosting model (XGBoost), which achieved an area under the received operating curve (AUROC) of 0.85, a sensitivity of 0.76, and a specificity of 0.76. The machine learning model developed has strong discrimination and calibration for the prediction of hypoglycemia in ICU patients. Prospective trials of these models are required to evaluate their clinical utility in averting hypoglycemia within critically ill patient populations.

Data-driven curation process for describing the blood glucose management in the intensive care unit.

Analysis of real-world glucose and insulin clinical data recorded in electronic medical records can provide insights into tailored approaches to clinical care, yet presents many analytic challenges. This work makes publicly available a dataset that contains the curated entries of blood glucose readings and administered insulin on a per-patient basis during ICU admissions in the Medical Information Mart for Intensive Care (MIMIC-III) database version 1.4. Also, the present study details the data curation process used to extract and match glucose values to insulin therapy. The curation process includes the creation of glucose-insulin pairing rules according to clinical expert-defined physiologic and pharmacologic parameters. Through this approach, it was possible to align nearly 76% of insulin events to a preceding blood glucose reading for nearly 9,600 critically ill patients. This work has the potential to reveal trends in real-world practice for the management of blood glucose. This data extraction and processing serve as a framework for future studies of glucose and insulin in the intensive care unit.

Real-world characterization of blood glucose control and insulin use in the intensive care unit.

The heterogeneity of critical illness complicates both clinical trial design and real-world management. This complexity has resulted in conflicting evidence and opinion regarding the optimal management in many intensive care scenarios. Understanding this heterogeneity is essential to tailoring management to individual patients. Hyperglycaemia is one such complication in the intensive care unit (ICU), accompanied by decades of conflicting evidence around management strategies. We hypothesized that analysis of highly-detailed electronic medical record (EMR) data would demonstrate that patients vary widely in their glycaemic response to critical illness and response to insulin therapy. Due to this variability, we believed that hyper- and hypoglycaemia would remain common in ICU care despite standardised approaches to management. We utilized the Medical Information Mart for Intensive Care III v1.4 (MIMIC) database. We identified 19,694 admissions between 2008 and 2012 with available glucose results and insulin administration data. We demonstrate that hyper- and hypoglycaemia are common at the time of admission and remain so 1 week into an ICU admission. Insulin treatment strategies vary significantly, irrespective of blood glucose level or diabetic status. We reveal a tremendous opportunity for EMR data to guide tailored management. Through this work, we have made available a highly-detailed data source for future investigation.