Non-invasive wearables for remote monitoring of HbA1c and glucose variability: proof of concept

Abstract

IntroductionDiabetes prevalence continues to grow and there remains a significant diagnostic gap in one-third of the US population that has pre-diabetes. Innovative, practical strategies to improve monitoring of glycemic health are desperately needed. In this proof-of-concept study, we explore the relationship between non-invasive wearables and glycemic metrics and demonstrate the feasibility of using non-invasive wearables to estimate glycemic metrics, including hemoglobin A1c (HbA1c) and glucose variability metrics.Research design and methodsWe recorded over 25 000 measurements from a continuous glucose monitor (CGM) with simultaneous wrist-worn wearable (skin temperature, electrodermal activity, heart rate, and accelerometry sensors) data over 8–10 days in 16 participants with normal glycemic state and pre-diabetes (HbA1c 5.2–6.4). We used data from the wearable to develop machine learning models to predict HbA1c recorded on day 0 and glucose variability calculated from the CGM. We tested the accuracy of the HbA1c model on a retrospective, external validation cohort of 10 additional participants and compared results against CGM-based HbA1c estimation models.ResultsA total of 250 days of data from 26 participants were collected. Out of the 27 models of glucose variability metrics that we developed using non-invasive wearables, 11 of the models achieved high accuracy (<10% mean average per cent error, MAPE). Our HbA1c estimation model using non-invasive wearables data achieved MAPE of 5.1% on an external validation cohort. The ranking of wearable sensor’s importance in estimating HbA1c was skin temperature (33%), electrodermal activity (28%), accelerometry (25%), and heart rate (14%).ConclusionsThis study demonstrates the feasibility of using non-invasive wearables to estimate glucose variability metrics and HbA1c for glycemic monitoring and investigates the relationship between non-invasive wearables and the glycemic metrics of glucose variability and HbA1c. The methods used in this study can be used to inform future studies confirming the results of this proof-of-concept study.

Digital Biomarkers for Personalized Nutrition: Predicting Meal Moments and Interstitial Glucose with Non-Invasive, Wearable Technologies

“…Future development of activity tracking should explicitly separate physical activity from sedentary behavior to improve personalized insight into their relation to glucose concentrations. Interestingly, two other studies showed a larger contribution of meal composition than that of physical activity, while comparable features for nutrition were used (number of calories, protein, sugar, fat, and carbohydrates over a specific time window) [ 30 , 58 ]. While the importance of physical activity in our model and that of Bent et al was comparable (17% and 19%, respectively), the influence of nutrition was lower in our model (20% and 37%, respectively) [ 58 ].…”

“…Interestingly, two other studies showed a larger contribution of meal composition than that of physical activity, while comparable features for nutrition were used (number of calories, protein, sugar, fat, and carbohydrates over a specific time window) [ 30 , 58 ]. While the importance of physical activity in our model and that of Bent et al was comparable (17% and 19%, respectively), the influence of nutrition was lower in our model (20% and 37%, respectively) [ 58 ]. Possibly, this is explained by the fact that they focused on persons with prediabetes only, while the current study targeted a healthy population.…”

Emergence of integrated biosensing-enabled digital healthcare devices

“…Electrochemical platforms, low-cost electromyography, non-invasive wearables for HbA1c and glucose etc., are used for biomarker sensing and commercialization. [175][176][177][178] Health management schedules for oral wearable sensors, stretchable strain sensors for joint motion and respiration monitoring, finger-based pulse oximeters, glucose monitoring systems among adults with type 2 diabetes, bipolar disorder treatment systems etc., have become standard elements of intensive care and follow-up plans. [179][180][181][182][183] Table 6 outlines some health management advances in the biosensing field based on device development.…”

Review of Noninvasive Continuous Glucose Monitoring in Diabetics

“…The management of T2D will be considerably aided by real-time monitoring of blood glucose indexes through continuous noninvasive devices in T2D patients. 8 Meals and activities will affect body glucose homeostasis, while continuous glucose monitoring (CGM) identifies minor health abnormalities of users, allowing patients to understand the changing trend, fluctuation range and influencing factors of blood glucose, and realize more comprehensive and effective management of diabetes. 9 For diabetics, CGM reduces doctor visits 5 and guarantees that medical professionals have a timely understanding of patients' conditions, which enhances the disease and maximizes the benefits of intervention measures.…”

“…The most common kind of diabetes, T2D, is brought on by insulin resistance, which can be more easily avoided and treated with proper blood glucose management. The management of T2D will be considerably aided by real-time monitoring of blood glucose indexes through continuous noninvasive devices in T2D patients …”