Developing a low-cost cardiovascular mobile screening kit
Name
1102057009-MIT.pdf
Size
3.09 MB
Format
Adobe PDF
Checksum (MD5)
9df032493de246dc447c86ff4d735a4c
Author(s)
Ma, Botong.
Advisor(s)
Richard Ribon Fletcher.
Date Issued
2019
Publisher
Massachusetts Institute of Technology
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.
Description
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 148-159).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
Persistent DSpace Link
