Accuracy of a Risk Alert Threshold for ICU Hypoglycemia: Retrospective Analysis of Alert Performance and Association with Clinical Deterioration Events

Abstract

Objective: To quantify the accuracy of and clinical events associated with a risk alert threshold for impending hypoglycemia during ICU admissions. Design: Retrospective electronic health record review of clinical events occurring ≥1 and ≤12 hours after the hypoglycemia risk alert threshold was met. Setting: Adult ICU admissions from June 2020 through April 2021 at the University of Virginia Medical Center. Patients: 342 critically-ill adults that were 63.5% male with median age 60.8 years, median weight 79.1 kg, and median body mass index of 27.5 kg/m2. Interventions: Real-world testing of our validated predictive model as a clinical decision support tool for ICU hypoglycemia. Measurements and Main Results: We retrospectively reviewed 350 hypothetical alerts that met inclusion criteria for analysis. The alerts correctly predicted 48 cases of Level 1 hypoglycemia that occurred ≥1 and ≤12 hours after the alert threshold was met (positive predictive value= 13.7%). Twenty-one of these 48 cases (43.8%) involved Level 2 hypoglycemia. Notably, three myocardial infarctions, one medical emergency team call, two initiations of cardiopulmonary resuscitation, 6 unplanned surgeries, 19 deaths, 20 arrhythmias, and 38 blood or urine cultures were identified or obtained ≥1 and ≤12 hours after an alert threshold was met. Alerts identified 102 total events of hypoglycemia and/or clinical deterioration, yielding a positive predictive value for any event of 29.1%. Conclusions: Alerts generated by a validated ICU hypoglycemia prediction model had positive predictive value of 29.1% for hypoglycemia and other associated adverse clinical events.