Pathophysiologic Signature of Impending ICU Hypoglycemia in Bedside Monitoring and Electronic Health Record Data: Model Development and External Validation

Abstract

We tested the hypothesis that routine monitoring data could describe a detailed and distinct pathophysiologic phenotype of impending hypoglycemia in adult ICU patients. DESIGN:Retrospective analysis leading to model development and validation. SETTING:All ICU admissions wherein patients received insulin therapy during a 4-year period at the University of Virginia Medical Center. Each ICU was equipped with continuous physiologic monitoring systems whose signals were archived in an electronic data warehouse along with the entire medical record. PATIENTS:Eleven thousand eight hundred forty-seven ICU patient admissions. INTERVENTIONS:The primary outcome was hypoglycemia, defined as any episode of blood glucose less than 70 mg/dL where 50% dextrose injection was administered within 1 hour. We used 61 physiologic markers (including vital signs, laboratory values, demographics, and continuous cardiorespiratory monitoring variables) to inform the model. MEASUREMENTS AND MAIN RESULTS:Our dataset consisted of 11,847 ICU patient admissions, 721 (6.1%) of which had one or more hypoglycemic episodes. Multivariable logistic regression analysis revealed a pathophysiologic signature of 41 independent variables that best characterized ICU hypoglycemia. The final model had a cross-validated area under the receiver operating characteristic curve of 0.83 (95% CI, 0.78-0.87) for prediction of impending ICU hypoglycemia. We externally validated the model in the Medical Information Mart for Intensive Care III critical care dataset, where it also demonstrated good performance with an area under the receiver operating characteristic curve of 0.79 (95% CI, 0.77-0.81). CONCLUSIONS:We used data from a large number of critically ill inpatients to develop and externally validate a predictive model of impending ICU hypoglycemia. Future steps include incorporating this model into a clinical decision support system and testing its effects in a multicenter randomized controlled clinical trial.

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

“…Prediction Assistant collected laboratory results and flowsheet vital signs from the electronic health record (EHR) along with continuous cardiorespiratory monitoring data from the UVA Kafka System in real-time (7). Prediction Assistant used these data to estimate the relative risk of impending ICU hypoglycemia based on our validated multivariable logistic regression model containing 41 independent predictors (6). For this, the model was employed in the current cohort to estimate the probability of hypoglycemia in the next 12 hours, then that probability was divided by 0.00436 ( i.e ., the average probability of hypoglycemia in the next 12 hours).…”

“…The well-established biochemical, hemodynamic, and electrophysiological changes that occur during hypoglycemia (2) make it an ideal target for predictive analytics monitoring; however, few studies have focused on model development specifically for ICU hypoglycemia (3)(4)(5). We recently described a pathophysiologic signature of impending ICU hypoglycemia that incorporated hemodynamic and electrophysiological bedside monitoring data in a logistic regression model (6). A necessary step in translating this model to clinical practice is understanding how it would perform when operationalized as a real-time alert.…”

Machine Learning Models for Inpatient Glucose Prediction

“…Their externally validated logistic regression achieved AUCs of 0.72 and 0.71 when predicting hypoglycemia during the first week of a patient’s admission. Horton et al published a logistic regression model that included 41 predictors for impending hypoglycemia during a patient’s ICU stay [ 47 ]. They trained their model using physiologic data up to 12 h prior to a hypoglycemic episode that required treatment with 50% dextrose and excluded any subsequent episodes of hypoglycemia in that patient’s admission.…”

The principles of whole-hospital predictive analytics monitoring for clinical medicine originated in the neonatal ICU

“…While sepsis is a flagship example, there are other subacute potentially catastrophic illnesses in which we can expect a subclinical prodrome. These include respiratory deterioration leading to emergency intubation 19 , 22 , 23 , hemorrhage leading to large transfusion 19 , 24 , 25 , hypoglycemia 26 , and the multiple reasons that ward patients deteriorate and require ICU transfer 20 , 27 . Their common characteristics are (1) a natural progression of physiological derangement that begins subtly, (2) a logical approach to diagnostic testing, and (3) therapy that is most effective early in the course of the illness.…”