English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Continuous Glucose Monitors (CGMs) provide tremendous value for diabetes detection and management. However, their high cost and regulatory complications have prevented the widespread use of CGMs. On the other hand, Heart Rate (HR) monitors are in wide use and growing in popularity. In this work, we investigate the connection between HR monitor and CGM devices to find a cheaper alternative for measuring glucose dysregulation. We recruited 550 volunteers that included healthy, type 2 diabetic, pre-diabetic, and gestational diabetic cohorts to wear CGM and HR monitors for 10 days. Although the physiological mechanisms underlying glucose regulation and heart rate share many commonalities, we find that commonly used features in time series analysis yield poor correlations between CGM and HR signals. However, by learning a joint representation between CGM and HR using Canonical Correlation Analysis (CCA), we can learn CGM and HR features in CCA space respectively that have a statistically significant correlation. Finding HR features that maximize the CCA objective with CGM enables us to learn about a subject's glucose regulatory system using an HR monitor alone and not require cumbersome CGMs. Here we consider the detection of diabetes with heart rate monitors as a particular application. We find that CCA representations of heart rate can serve as a proxy for using CGMs in diabetes classification.

ieee access

Heart Rate and CGM Feature Representation Diabetes Detection From Heart Rate: Learning Joint Features of Heart Rate and Continuous Glucose Monitors Yields Better Representations