Photoplethysmography Driven Hypertension Identification: A Pilot Study

Abstract

To prevent and diagnose hypertension early, there has been a growing demand to identify its states that align with patients. This pilot study aims to research how a non-invasive method using photoplethysmographic (PPG) signals works together with deep learning algorithms. A portable PPG acquisition device (Max30101 photonic sensor) was utilized to (1) capture PPG signals and (2) wirelessly transmit data sets. In contrast to traditional feature engineering machine learning classification schemes, this study preprocessed raw data and applied a deep learning algorithm (LSTM-Attention) directly to extract deeper correlations between these raw datasets. The Long Short-Term Memory (LSTM) model underlying a gate mechanism and memory unit enables it to handle long sequence data more effectively, avoiding gradient disappearance and possessing the ability to solve long-term dependencies. To enhance the correlation between distant sampling points, an attention mechanism was introduced to capture more data change features than a separate LSTM model. A protocol with 15 healthy volunteers and 15 hypertension patients was implemented to obtain these datasets. The processed result demonstrates that the proposed model could present satisfactory performance (accuracy: 0.991; precision: 0.989; recall: 0.993; F1-score: 0.991). The model we proposed also demonstrated superior performance compared to related studies. The outcome indicates the proposed method could effectively diagnose and identify hypertension; thus, a paradigm to cost-effectively screen hypertension could rapidly be established using wearable smart devices.

Rehabilitation Assessment System for Stroke Patients Based on Fusion-Type Optoelectronic Plethysmography Device and Multi-Modality Fusion Model: Design and Validation

“…These studies all involved the rehabilitation assessment of stroke. In the first study [26], Wei et al's model (CNN-LSTM-Attention) achieved only 72.73% accuracy. In the second study [17], based on the NIHSS scale, 234 features were extracted from EKG, ABP, and PPG signals, and a linear kernel SVM classifier was employed, resulting in an accuracy of 82.7%.…”

“…In previous research, Wei et al [26] designed a PPG acquisition device and proposed a model that combines the Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and an attention mechanism This model achieved a good accuracy rate of 99.1% in the diagnosis and identification of hypertension. However, when using this model for stroke-patient rehabilitation assessment, the accuracy rate was found to be relatively low.…”

Photoplethysmography for Assessing Microcirculation in Hypertensive Patients After Taking Antihypertensive Drugs: A Review

“…Nowadays, recently published papers are related to weather PPG wave patterns to calculate blood pressure. Yan et al 35 reported a PPG method that can work with a degree-learning algorithm, which is beneficial for the diagnosis and identification of hypertension. Liang et al 36 reported an approach to hypertension management based on arterial wave propagation theory and investigated changes in different BP levels.…”