Development of smart cardiovascular measurement system using feature selection and machine learning models for prediction of sleep deprivation, cold hands and feet, and Shanghuo syndrome

Abstract

This study aimed to develop a smart cardiovascular measurement system using ECG and PPG to evaluate health issues: sleep deprivation, cold hands and feet, and the Shanghuo syndrome. The proposed methods extracted features from physical Signal and utilized diverse machine learning techniques for the evaluation. The results demonstrated prediction accuracies exceeding 82% (87% for sleep deprivation using k-nearest neighbor, 83% for cold hands and feet using a kernel classifier, and 82% for the Shanghuo syndrome using ensemble learning). Moreover, this study identified novel features associated with sleep deprivation, cold hands and feet, and the Shanghuo syndrome in the context of traditional Chinese medicine (TCM). An accurate prediction of TCM-defined cold hands and feet and Shanghuo syndrome, while considering relevant physiological features, is critical in the field of machine learning research. The developed system can be seamlessly integrated with the existing instruments to facilitate self-health management and collaboration with medical treatment.