90% Accuracy for Photoplethysmography-Based Non-Invasive Blood Glucose Prediction by Deep Learning with Cohort Arrangement and Quarterly Measured HbA1c

Implicit HbA1c Achieving 87% Accuracy within 90 Days in Non-Invasive Fasting Blood Glucose Measurements Using Photoplethysmography

To reduce the error induced by overfitting or underfitting in predicting non-invasive fasting blood glucose (NIBG) levels using photoplethysmography (PPG) data alone, we previously demonstrated that incorporating HbA1c led to a notable 10% improvement in NIBG prediction accuracy (the ratio in zone A of Clarke's error grid). However, this enhancement came at the cost of requiring an additional HbA1c measurement, thus being unfriendly to users. In this study, the enhanced HbA1c NIBG deep learning model (blood glucose level predicted from PPG and HbA1c) was trained with 1494 measurements, and we replaced the HbA1c measurement (explicit HbA1c) with "implicit HbA1c" which is reversely derived from pretested PPG and finger-pricked blood glucose levels. The implicit HbA1c is then evaluated across intervals up to 90 days since the pretest, achieving an impressive 87% accuracy, while the remaining 13% falls near the CEG zone A boundary. The implicit HbA1c approach exhibits a remarkable 16% improvement over the explicit HbA1c method by covering personal correction items automatically. This improvement not only refines the accuracy of the model but also enhances the practicality of the previously proposed model that relied on an HbA1c input. The nonparametric Wilcoxon paired test conducted on the percentage error of implicit and explicit HbA1c prediction results reveals a substantial difference, with a p-value of 2.75 × 10-7.

Noninvasive Blood Glucose Monitoring Systems Using Near-Infrared Technology—A Review

The past few decades have seen ongoing development of continuous glucose monitoring (CGM) systems that are noninvasive and accurately measure blood glucose levels. The conventional finger-prick method, though accurate, is not feasible for use multiple times a day, as it is painful and test strips are expensive. Although minimally invasive and noninvasive CGM systems have been introduced into the market, they are expensive and require finger-prick calibrations. As the diabetes trend is high in low- and middle-income countries, a cost-effective and easy-to-use noninvasive glucose monitoring device is the need of the hour. This review paper briefly discusses the noninvasive glucose measuring technologies and their related research work. The technologies discussed are optical, transdermal, and enzymatic. The paper focuses on Near Infrared (NIR) technology and NIR Photoplethysmography (PPG) for blood glucose prediction. Feature extraction from PPG signals and glucose prediction with machine learning methods are discussed. The review concludes with key points and insights for future development of PPG NIR-based blood glucose monitoring systems.

Sense and Learn: Recent Advances in Wearable Sensing and Machine Learning for Blood Glucose Monitoring and Trend-Detection

Diabetes mellitus is characterized by elevated blood glucose levels, however patients with diabetes may also develop hypoglycemia due to treatment. There is an increasing demand for non-invasive blood glucose monitoring and trends detection amongst people with diabetes and healthy individuals, especially athletes. Wearable devices and non-invasive sensors for blood glucose monitoring have witnessed considerable advances. This review is an update on recent contributions utilizing novel sensing technologies over the past five years which include electrocardiogram, electromagnetic, bioimpedance, photoplethysmography, and acceleration measures as well as bodily fluid glucose sensors to monitor glucose and trend detection. We also review methods that use machine learning algorithms to predict blood glucose trends, especially for high risk events such as hypoglycemia. Convolutional and recurrent neural networks, support vector machines, and decision trees are examples of such machine learning algorithms. Finally, we address the key limitations and challenges of these studies and provide recommendations for future work.