A Comprehensive Study for Blood Glucose Level Monitoring Using Photoplethysmography | ||||
| Aswan University Journal of Sciences and Technology | ||||
| Volume 5, Issue 2, June 2025, Page 1-13 PDF (1.51 MB) | ||||
| Document Type: Review papers | ||||
| DOI: 10.21608/aujst.2025.351471.1162 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
Abdelrhman Yahia Soliman  1; Ahmed Ezzat Refai2; osama Ahmed omer1; Ahmed Soliman3
| ||||
| 1Department of Electrical Engineering, Faculty of Engineering, Aswan University | ||||
| 2Department of Electronics and Communications, Luxor Higher Institute of Engineering and Technology, Luxor 85834, Egypt | ||||
| 3Electrical Engineering Department, Faculty of Engineering, Aswan University | ||||
| Abstract | ||||
| Abnormal blood glucose levels pose a significant risk to patient health, as they can cause severe complications and potentially become life-threatening if not promptly identified and managed. Given the importance of early detection, there has been a growing focus on the development of effective, non-invasive techniques for monitoring blood glucose. One such promising approach involves the use of photoplethysmography (PPG) signals, which have attracted considerable attention within both the medical and engineering communities. Over the past decade, researchers have leveraged advancements in artificial intelligence (AI) and machine learning to refine methods for estimating blood glucose levels using PPG-based data. These efforts span a wide range of algorithms and modelling techniques, including deep learning architectures, signal processing methods, and feature extraction strategies. This survey aims to provide a comprehensive overview of the latest contributions to this field, examining how various approaches address challenges such as measurement accuracy, individual variability, and real-time feasibility. By critically evaluating these AI-driven techniques, we shed light on the current state of PPG-based blood glucose measurement and outline potential directions for future research and clinical application. | ||||
| Keywords | ||||
| digital medicine; blood glucose; non-invasive; photoplethysmography; deep learning; continuous glucose monitoring | ||||
|
Statistics Article View: 106 PDF Download: 99 |
||||
