Photoplethysmography Feature Extraction for Non-Invasive Glucose Estimation by Means of MFCC and Machine Learning Techniques

TL;DR

This paper introduces a non-invasive method to estimate blood glucose levels using photoplethysmography signals and machine learning, achieving high accuracy.

Contribution

The novelty lies in using MFCCs for PPG signal analysis combined with machine learning for glucose estimation without requiring prior calibration.

Findings

The best model achieved a mean absolute error of 9.85 mg/dL and a correlation of 0.94 with real glucose values.

99.53% of validation samples fell within zones A and B of the Clarke Error Grid Analysis.

Abstract

Diabetes Mellitus is considered one of the most widespread diseases in the world. Traditional glucose monitoring devices carry discomfort and risks associated with the frequent extraction of blood from users. The present article proposes a noninvasive glucose estimation system based on the application of Mel Frequency Cepstral Coefficients (MFCCs) for the characterization of photoplethysmographic signals (PPG). Two variants of the MFCC feature extraction methods are evaluated along with three machine learning techniques for the development of an effective regression function for the estimation of glucose concentration. A comparison between the performance of the algorithms revealed that the best combination achieved a mean absolute error of 9.85 mg/dL and a correlation of 0.94 between the estimated concentration and the real glucose values. Similarly, 99.53% of the validation samples were distributed within zones A and B of the Clarke Error Grid Analysis. The proposed system achieves levels of correlation comparable to analogous technologies that require earlier calibration for its operation, which indicates a strong potential for the future use of the algorithm as an alternative to invasive monitoring devices.

Figures