Developing a low-cost cardiovascular mobile screening kit

Abstract

Cardiovascular disease (CVD) is the leading cause of mortality worldwide, and 80% of CVD deaths occur in lower and middle-income countries. While many CVD risk factors can be improved by behavioral change or low-cost medication, a major challenge remains in identifying at-risk patients since most people are asymptomatic. Thus, low-cost non-invasive diagnostic tools are crucial in low-resource areas without routine blood tests or regular clinical exams. This thesis presents a low-cost cardiovascular screening kit that focuses on signs of arterial stiffening, the root issue of many CVDs. Since pulse wave velocity (PWV) and pulse wave analysis (PWA) features were known to be correlated with arterial stiffening, we developed a Python API that would extract these features from the pulse waveforms collected using the devices in our screening kit. Using these features, we also trained a machine learning algorithm to accurately identify patients that are at-risk. We confirm the usefulness of PWV and PWA features for CVD screening, and anticipate that as the number of training data points increase, our machine learning model will enable individuals to live a healthier lifestyle.