A review of machine learning techniques in photoplethysmography for the non-invasive cuff-less measurement of blood pressure

Abstract

Hypertension or high blood pressure is a leading cause of death throughout the world and a critical factor for increasing the risk of serious diseases, including cardiovascular diseases such as stroke and heart failure. Blood pressure is a primary vital sign that must be monitored regularly for the early detection, prevention and treatment of cardiovascular diseases. Traditional blood pressure measurement techniques are either invasive or cuff-based, which are impractical, intermittent, and uncomfortable for patients. Over the past few decades, several indirect approaches using photoplethysmogram (PPG) have been investigated, namely, pulse transit time, pulse wave velocity, pulse arrival time and pulse wave analysis, in an effort to utilise PPG for estimating blood pressure. Recent advancements in signal processing techniques, including machine learning and artificial intelligence, have also opened up exciting new horizons for PPG-based cuff less and continuous monitoring of blood pressure. Such a device will have a significant and transformative impact in monitoring patients’ vital signs, especially those at risk of cardiovascular disease. This paper provides a comprehensive review for non-invasive cuff-less blood pressure estimation using the PPG approach along with their challenges and limitations.