Accepted for/Published in: JMIR Formative Research
Date Submitted: Aug 19, 2022
Date Accepted: Dec 21, 2022
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Evaluation of Regression Models for Prediction of Next Glucose Measurement in Hospitalized Patients
ABSTRACT
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.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.