596-P: Machine Learning Prediction of Blood Glucose in Hospitalized Patients

Background: Inpatient glucose management can be challenging due to various evolving factors that influence a patient's blood glucose (BG). Providers could benefit from a clinical decision support tool that predicts the trajectory of a patient's BG reading. The purpose of our study was to predict the category of a patient's next BG reading based on electronic medical record (EMR) data. Methods: EMR data from 184,361 admissions, containing 4,538,418 BG readings from five hospitals in the Johns Hopkins Health System were collected over a 4.5 year period. The outcome was category of next BG reading: hypoglycemic (BG 180 mg/dl). A LogitBoost machine learning algorithm that included a broad range of clinical predictors was used to predict the outcome and validated internally (within one hospital) and externally (between different hospitals). Results: Our machine learning model achieved 86.2% (95% CI: 86.1%-86.2%) accuracy on internal validation and 80.4%-83.2% on external validation. On internal validation, the positive likelihood ratio (+LR) for a prediction of controlled, hyperglycemic, and hypoglycemic were 2.4, 12.3, and 47.4 respectively; the negative likelihood ratio (-LR) for a prediction of controlled, hyperglycemic, and hypoglycemic were 0.09, 0.38, and 0.99 on internal validation. From a safety standpoint, only 0.23% of hyperglycemic observations were predicted to be hypoglycemic on internal validation. On external validation, the +LR for prediction of controlled, hyperglycemic, and hypoglycemic were 2.2-2.8, 6.3-8.5, and 23.1-62.7; the -LR for a prediction of controlled, hyperglycemic, and hypoglycemic were 0.13-0.16, 0.32-0.42, and 0.98-0.99. Conclusions: A machine learning algorithm accurately predicts the category of a patient's next BG reading. Further studies should determine the success of implementing this model into the EMR to decrease the rates of hypoglycemia and hyperglycemia in hospitalized patients.