Machine Learning-Based Diabetes Detection Using Photoplethysmography Signal Features

TL;DR

This study explores using non-invasive photoplethysmography signals combined with machine learning algorithms to detect diabetes, offering a promising approach for remote and continuous monitoring.

Contribution

It introduces a novel non-invasive method utilizing PPG signals and machine learning for diabetes detection, with rigorous validation on unseen subjects.

Findings

Achieved an F1-Score of approximately 58.8% with Logistic Regression.

Model performance indicates potential for non-invasive diabetes detection.

PPG features contain relevant diabetes-related information.

Abstract

Diabetes is a prevalent chronic condition that compromises the health of millions of people worldwide. Minimally invasive methods are needed to prevent and control diabetes but most devices for measuring glucose levels are invasive and not amenable for continuous monitoring. Here, we present an alternative method to overcome these shortcomings based on non-invasive optical photoplethysmography (PPG) for detecting diabetes. We classify non-Diabetic and Diabetic patients using the PPG signal and metadata for training Logistic Regression (LR) and eXtreme Gradient Boosting (XGBoost) algorithms. We used PPG signals from a publicly available dataset. To prevent overfitting, we divided the data into five folds for cross-validation. By ensuring that patients in the training set are not in the testing set, the model's performance can be evaluated on unseen subjects' data, providing a more accurate assessment of its generalization. Our model achieved an F1-Score and AUC of $58.8\pm20.0\%$ and $79.2\pm15.0\%$ for LR and $51.7\pm16.5\%$ and $73.6\pm17.0\%$ for XGBoost, respectively. Feature analysis suggested that PPG morphological features contains diabetes-related information alongside metadata. Our findings are within the same range reported in the literature, indicating that machine learning methods are promising for developing remote, non-invasive, and continuous measurement devices for detecting and preventing diabetes.