Photoplethysmography and Machine Learning for the Hypertension Risk Stratification

Blood pressure is a basic physiological parameter in the cardiovascular circulatory system. PhotoPlethysmoGraphy (PPG) signal represents a convenient, wearable, and low-cost technology that can be applied to various aspects of cardiovascular monitoring, including the detection of blood pressure, i.e., the hypertension level. The goal of this paper is to explore the behavior of a set of machine learning methods with respect to the hypertension risk stratification. With reference to this issue, the discrimination ability of the investigated algorithms has been considered at three different granularity levels, i.e. by suitably joining some of the classes making up the data set, so as to partition this latter into three different ways. To fulfill our goal, the Cuff-Less Blood Pressure Estimation Data Set is considered here. This data set is composed by many signals, including PPG data acquired from a group of subjects, and their Blood Pressure values, that are used to represent their hypertension levels. We have used a large group of machine learning tools, relying on differing working methods, and their numerical comparison has been carried out in terms of risk stratification results.