Deep Learning Classification of Photoplethysmogram Signal for Hypertension Levels

TL;DR

This study explores deep learning techniques for classifying hypertension levels using PPG signals, achieving high accuracy with ensemble methods and neural network combinations, which can enhance non-invasive blood pressure monitoring.

Contribution

It introduces a novel combination of STFT-based feature extraction with various neural networks and ensemble methods for hypertension classification using PPG signals.

Findings

LSTM models achieved 100% precision and specificity.

Maximum accuracy of 71.9% with LSTM-CNN model.

Ensemble methods reached 100% accuracy in classification.

Abstract

Continuous photoplethysmography (PPG)-based blood pressure monitoring is necessary for healthcare and fitness applications. In Artificial Intelligence (AI), signal classification levels with the machine and deep learning arrangements need to be explored further. Techniques based on time-frequency spectra, such as Short-time Fourier Transform (STFT), have been used to address the challenges of motion artifact correction. Therefore, the proposed study works with PPG signals of more than 200 patients (650+ signal samples) with hypertension, using STFT with various Neural Networks (Convolution Neural Network (CNN), Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), followed by machine learning classifiers, such as, Support Vector Machine (SVM) and Random Forest (RF). The classification has been done for two categories: Prehypertension (normal levels) and Hypertension (includes Stage I and Stage II). Various performance metrics have been obtained with two batch sizes of 3 and 16 for the fusion of the neural networks. With precision and specificity of 100% and recall of 82.1%, the LSTM model provides the best results among all combinations of Neural Networks. However, the maximum accuracy of 71.9% is achieved by the LSTM-CNN model. Further stacked Ensemble method has been used to achieve 100% accuracy for Meta-LSTM-RF, Meta- LSTM-CNN-RF and Meta- STFT-CNN-SVM.