Heart Sounds for High Blood Pressure Prediction

Abstract

Hypertension, a major risk factor for cardiovascular diseases, often goes undetected due to its asymptomatic nature. This study explores a novel approach to detecting elevated blood pressure using heart sounds, aiming to provide a non-invasive, potentially continuous monitoring solution. We evaluated our approach on a new dataset of 260 participants, employing patient-independent cross-validation to ensure generalisability. Our methodology utilises a convolutional neural network-based Hidden Semi-Markov Model for heart sound segmentation, followed by extraction of hand-crafted amplitude, duration, and frequency features. A random forest model was implemented for the binary classification of hypertension, achieving a promising 70% accuracy with 72% sensitivity. We conducted comprehensive analyses, including auscultation location and feature importance evaluation, and the investigation of the heart rate – blood pressure relationship. Our findings demonstrate the feasibility of this approach, providing a robust foundation for further research and development in this domain.