Implementation of Machine Learning Assisted PPG-based Non-Invasive Blood Glucose Monitoring System

DOI

10.2991/978-94-6463-884-4_74How to use a DOI?

Keywords

Diabetes; BGM; PPG; Machine Learning; NIRS

Abstract

Diabetes is a major global health problem characterized by elevated or poorly controlled blood sugar levels. It is a leading cause of death worldwide and continues to rise, affecting millions of people. Although medical technology has advanced, a reliable, non-invasive solution for glucose monitoring is not yet widely available. As a result, the most trusted method for daily glucose measurement in personal healthcare relies on clinical laboratory tests, which, unfortunately, require the repeated discomfort of blood collection. This study presents a non-invasive, in vivo glucose monitoring system using photoplethysmography (PPG) and machine learning techniques, offering a better alternative to conventional approaches. The proposed system utilizes Near-Infrared Spectroscopy (NIRS) and reflection PPG to estimate blood glucose concentration. This study analyzes the correlation between blood glucose levels and PPG signal features captured using a fingertip-sensing circuit. A dataset of 40 individuals’ PPG signals and invasive glucose levels was collected. Key features like peak amplitudes, heart rate, signal power, and peak ratio were extracted and analyzed using Support Vector Regression (SVR) and Random Forest Regression (RFR). The models showed lower errors, with R² values of 0.636 and 0.838, respectively, for non-invasive glucose estimation.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Tanmoy Kumar Paul
AU  - Juhayer Mahtab Tasin
AU  - Md. Jahirul Islam
AU  - Md. Rejvi Kaysir
PY  - 2025
DA  - 2025/11/18
TI  - Implementation of Machine Learning Assisted PPG-based Non-Invasive Blood Glucose Monitoring System
BT  - Proceedings of the 8th International Conference on Engineering Research, Innovation, and Education 2025 (ICERIE 2025)
PB  - Atlantis Press
SP  - 614
EP  - 621
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-884-4_74
DO  - 10.2991/978-94-6463-884-4_74
ID  - Paul2025
ER  -