Background Inpatient glucose management can be challenging due to evolving factors that influence a patient's blood glucose (BG) throughout hospital admission. The purpose of our study was to predict the category of a patient's next BG measurement based on electronic medical record (EMR) data.
Purpose of Review Glucose management in the hospital is difficult due to non-static factors such as antihyperglycemic and steroid doses, renal function, infection, surgical status, and diet. Given these complex and dynamic factors, machine learning approaches can be leveraged for prediction of glucose trends in the hospital to mitigate and prevent suboptimal hypoglycemic and hyperglycemic outcomes. Our aim was to review the clinical evidence for the role of machine learning–based models in predicting hospitalized patients’ glucose trajectory. Recent Findings The published literature on machine learning algorithms has varied in terms of population studied, outcomes of interest, and validation methods. There have been tools developed that utilize data from both continuous glucose monitors and large electronic health records (EHRs). With increasing sample sizes, inclusion of a greater number of predictor variables, and use of more advanced machine learning algorithms, there has been a trend in recent years towards increasing predictive accuracy for glycemic outcomes in the hospital setting. While current models predicting glucose trajectory offer promising results, they have not been tested prospectively in the clinical setting. Summary Accurate machine learning algorithms have been developed and validated for prediction of hypoglycemia and hyperglycemia in the hospital. Further work is needed in implementation/integration of machine learning models into EHR systems, with prospective studies to evaluate effectiveness and safety of such clinical decision support on glycemic and other clinical outcomes.
BACKGROUND Continuous glucose monitors (CGM) have shown great promise in improving outpatient blood glucose (BG) control; however, CGMs are not routinely used in the hospital. OBJECTIVE The purpose of our study was to evaluate times series analytical approaches for prediction of inpatient BG using only point-of-care and serum glucose observations. METHODS Electronic health record data from 184,361 admissions from five Johns Hopkins Health System hospitals were collected from patients who were discharged between January 1, 2015 and May 31, 2019. After excluding BG measurements obtained in quick succession or from critically ill patients, there were 2,436,226 BG observations included. The outcome of interest was the next BG measurement (mg/dL). Multiple time series predictors were created and then analyzed using different machine learning techniques. RESULTS When analyzing time series predictors independently, increasing variability in a patient’s BG decreased predictive accuracy. Likewise, inclusion of older BG measurements decreased predictive accuracy. When non-glycemic clinical predictors were added to machine learning algorithms, there was generally minimal improvement in predictive accuracy. CONCLUSIONS The most recent BG measurement holds more predictive value than the moving average or trend of a patient’s previous BG measurements. These relationships become less strong as glucose variability increases. Further studies should determine the potential of using time series analyses for prediction of inpatient hypoglycemia and hyperglycemia.
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 <=70 mg/dl), controlled (BG 71-180 mg/dl), or hyperglycemic (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. Disclosure A. D. Zale: None. M. S. Abusamaan: None. N. Mathioudakis: None. Funding National Institute of Diabetes and Digestive and Kidney Diseases (K23DK111986)
Background Continuous glucose monitors have shown great promise in improving outpatient blood glucose (BG) control; however, continuous glucose monitors are not routinely used in hospitals, and glucose management is driven by point-of-care (finger stick) and serum glucose measurements in most patients. Objective This study aimed to evaluate times series approaches for prediction of inpatient BG using only point-of-care and serum glucose observations. Methods Our data set included electronic health record data from 184,320 admissions, from patients who received at least one unit of subcutaneous insulin, had at least 4 BG measurements, and were discharged between January 1, 2015, and May 31, 2019, from 5 Johns Hopkins Health System hospitals. A total of 2,436,228 BG observations were included after excluding measurements obtained in quick succession, from patients who received intravenous insulin, or from critically ill patients. After exclusion criteria, 2.85% (3253/113,976), 32.5% (37,045/113,976), and 1.06% (1207/113,976) of admissions had a coded diagnosis of type 1, type 2, and other diabetes, respectively. The outcome of interest was the predicted value of the next BG measurement (mg/dL). Multiple time series predictors were created and analyzed by comparing those predictors and the index BG measurement (sample-and-hold technique) with next BG measurement. The population was classified by glycemic variability based on the coefficient of variation. To compare the performance of different time series predictors among one another, R2, root mean squared error, and Clarke Error Grid were calculated and compared with the next BG measurement. All these time series predictors were then used together in Cubist, linear, random forest, partial least squares, and k-nearest neighbor methods. Results The median number of BG measurements from 113,976 admissions was 12 (IQR 5-24). The R2 values for the sample-and-hold, 2-hour, 4-hour, 16-hour, and 24-hour moving average were 0.529, 0.504, 0.481, 0.467, and 0.459, respectively. The R2 values for 4-hour moving average based on glycemic variability were 0.680, 0.480, 0.290, and 0.205 for low, medium, high, and very high glucose variability, respectively. The proportion of BG predictions in zone A of the Clarke Error Grid analysis was 61%, 59%, 27%, and 53% for 4-hour moving average, 24-hour moving average, 3 observation rolling regression, and recursive regression predictors, respectively. In a fully adjusted Cubist, linear, random forest, partial least squares, and k-nearest neighbor model, the R2 values were 0.563, 0.526, 0.538, and 0.472, respectively. Conclusions When analyzing time series predictors independently, increasing variability in a patient’s BG decreased predictive accuracy. Similarly, inclusion of older BG measurements decreased predictive accuracy. These relationships become weaker as glucose variability increases. Machine learning techniques marginally augmented the performance of time series predictors for predicting a patient’s next BG measurement. Further studies should determine the potential of using time series analyses for prediction of inpatient dysglycemia.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.