Publication Date

Fall 2019

Degree Type

Master's Project

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Robert Chun

Second Advisor

Katerina Potika

Third Advisor

Nikhil Lahoti

Keywords

classification, electrocardiogram, heart disease, machine learning, myocardial infarction, neural networks

Abstract

Myocardial Infarction (MI), commonly known as a heart attack, occurs when one of the three major blood vessels carrying blood to the heart get blocked, causing the death of myocardial (heart) cells. If not treated immediately, MI may cause cardiac arrest, which can ultimately cause death. Risk factors for MI include diabetes, family history, unhealthy diet and lifestyle. Medical treatments include various types of drugs and surgeries which can prove very expensive for patients due to high healthcare costs. Therefore, it is imperative that MI is diagnosed at the right time. Electrocardiography (ECG) is commonly used to detect MI. ECG is a process in which the electrical signals of the heart are measured by electrodes placed on a patient’s limbs and chest to measure heart signals. In recent years, the availability of medical datasets and the invention of wearable devices have opened new possibilities in early detection of this disease. Wearable devices that measure ECG correctly and have built- in machine learning models can potentially save millions of lives the world over. This research explores traditional machine learning techniques such as Support Vector Machines and Decision Trees as well as a new technique, Capsule Neural Network, for MI detection. Even though the new technique achieves remarkable results, its accuracy is less compared to the traditional machine learning techniques used for MI detection.

Download

Share

COinS