Non-invasive method for blood glucose monitoring using ECG signal

Abstract Introduction: Tight glucose monitoring is crucial for diabetic patients by using a Continuous Glucose Monitor (CGM). The existing CGMs measure the Blood Concentration (BGC) from interstitial fluid. These technologies are quite expensive, and most of them invasive. Previous studies have demonstrated that hypoglycemia hyperglycemia episodes affect electrophysiology heart. However, they did not determine cohort relationship between BGC ECG parameters. Material method: In this work, we propose new method determining surface signals. Recurrent Convolutional Neural Networks (RCNN) were applied to segment Then, extracted features employed two mathematical equations. This has been tested on 04 over multiple days D1namo dataset, signals instead intracardiac signal. Results: We able with an accuracy 94% RCNN algorithm. According results, proposed was estimate Mean Absolute Error (MAE) 0.0539, Squared (MSE) 0.1604. addition, linear confirmed in paper. Conclusion: paper, potential use BGC. Additionally, features. That fact will open perspectives further research, namely physiological models. Furthermore, findings point possible application wearable devices non-invasive continuous blood via machine learning.