Neural Network-based Diabetic Type II High-Risk Prediction using Photoplethysmogram Waveform Analysis

Abstract

This work aims to predict and classify patients into diabetic and nondiabetic subjects based on age and four independent variables extracted from the analysis of photoplethysmogram (PPG) morphology in time domain. The study has two main stages, the first one was the analysis of PPG waveform to extract b/a, RI, DiP, and SPt indices. These parameters contribute by some means to the prediction of diabetes. They were statistically significant and correlated with the HbA1C test. The second stage was building a neural network based classifier to predict diabetes. The model showed an accuracy of 90.2% in training phase and an accuracy of 85.5% in testing phase. The findings of this research work may contribute towards the prediction of diabetes in early stages. Also, the proposed classifier showed a high accuracy in predicting the existence of diabetes in Saudi people population.

[Retracted] Classification of Diabetes Using Photoplethysmogram (PPG) Waveform Analysis: Logistic Regression Modeling

“…Additionally, Figure 2 examines the multiple boxplots for the used predictor variables in this model. The developed model is aligned with the ANN model developed by [ 15 ] in terms of age and b / a predictors. The advantage of the LR model is in using bigger datasets, and it uses the SP index as a new predictor that contributes towards the prediction and classification of diabetes.…”

“…The PPG represents a plethysmograph that is obtained optically; it measures the volume of an organ [15]. It is normally used for the tracking and detection of changes in blood volume in the tissues [16].…”

“…The pulse oximeters, vascular diagnostics systems, and digital beat-to-beat blood pressure measurement devices are well-known examples of PPG technology [14]. A neural network-based classifier has been developed by [15] to predict diabetes utilizing indices extracted from PPG waveform. Another researcher utilized decision trees to predict diabetes mellitus type 2 [19].…”