Previously submitted to: JMIR Diabetes (no longer under consideration since Nov 27, 2023)
Date Submitted: Jul 18, 2023
Warning: This is an author submission that is not peer-reviewed or edited.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.
Automatic prediabetes prediction using heart rate variability
ABSTRACT
Background:
Approximately 25% of prediabetics progress to overt type 2 diabetes within 3 to 5 years and 70% develop overt diabetes in their lifetime. Prediabetics could be identified through screening, which could reduce the healthcare burden. HRV is an index of the autonomic nervous system and serves as a measurable indicator for various chronic diseases. Commercial wearable devices have the potential to capture HRV in non-clinical settings.
Objective:
This study evaluates if machine learning techniques applied to HRV data captured in non-clinical settings could be used as a non-invasive biomarker to classify healthy adults and those with elevated blood glucose levels.
Methods:
Four machine learning classification algorithms: support vector machine (SVM), k-Nearest Neighbours (KNN), Naive Bayes (NB), and Decision Tree (DT), was applied to the computed HRV parameters to perform classification.
Results:
The overall best performance accuracy of 80% was achieved by KNN, and DT trained on HRV data with a time window length of 5 min. The study observed that HRV parameters computed from wearables in non-clinical settings could classify healthy adults and those with elevated blood glucose levels with acceptable accuracy.
Conclusions:
The findings of this study could inform the use of machine learning approaches with wearable device data to screen prediabetes individuals.
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.