Hypertension Management via Photoplethysmography: An Ensemble Learning-Based Approach for Classification of Blood Pressure Using Fourier Synchrosqueezed Transform

As the global prevalence of hypertension continues to rise, researchers have increasingly explored the potential of artificial intelligence (AI) for developing self-tracking blood pressure (BP) monitoring systems.An ideal approach would utilize photoplethysmography (PPG) signals, as they enable non-invasive wearable-based hypertension monitoring without reliance on cuff-based devices.This study investigated a PPG-based system for automated BP classification using an ensemble bagging technique with 200 decision trees.Given the nonstationary properties and motion artifact susceptibility of PPG signals, time-frequency (TF) analysis was conducted using Fourier Synchrosqueezed Transforms (FSST) to generate high-resolution TF representations.A set 44 features were extracted from the transformed signals, revealing the dynamic statistical properties over time.Three experimental models were trained on datasets incorporating different FSST variables.Unlike prior studies using small datasets, the models were trained on a large dataset comprising 46,572 subjectsegments across varied BP ranges, collected from the MIMIC-III intensive care database.This large dataset allowed boosting models accuracies and generalizability, achieving 100% training accuracy and 95.7% to 96.9% testing accuracy across the FSST experimental settings.The system also showed excellent results on three different classification tasksnormotension vs. hypertension, normotension vs. prehypertension, and non-hypertension vs. hypertension -with F1 scores reaching 99.1%.Moreover, the lightweight decision tree models enabled training in just minutes on this large dataset, indicating low computational complexity.Overall, this study presents an efficient PPG-based hypertension classification system.Results suggest potential for convenient clinical-grade BP monitoring beyond healthcare settings.