Analysis to Predict Coronary Thrombosis Using Machine Learning Techniques

Cardio vascular Diseases (CVDs) are the main reason for over 17.9 million deaths annually. 80% of cardiovascular deaths are due to strokes and heart attacks and 26% of those deaths occur too early to people who are under the age of 70. Most of the people around the world are struggling to control th...

Full description

Saved in:
Bibliographic Details
Published in2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) pp. 21 - 27
Main Authors Lakshmi Padmaja, D, Sai Sruthi, B, Surya Deepak, G, Sri Harsha, G K
Format Conference Proceeding
LanguageEnglish
Published IEEE 07.04.2022
Subjects
Classification
Computational modeling
Heart
Heart disease
Machine Learning
Measurement
Metrics
Radio frequency
Stroke (medical condition)
Support vector machines
Thrombosis
Online AccessGet full text

Cover

More Information
Summary:Cardio vascular Diseases (CVDs) are the main reason for over 17.9 million deaths annually. 80% of cardiovascular deaths are due to strokes and heart attacks and 26% of those deaths occur too early to people who are under the age of 70. Most of the people around the world are struggling to control the risk factors which lead to cardiovascular disease, while the rest remain unaware that they are prone. General risk factors of this disease are lack oxygen and nutrients to the heart. The goal of this research is to make a 10-year prediction based on a person's lifestyle and medical data in order to assess his or her risk of developing coronary heart disease. To understand the gathered data, it has been visualized by the means of Data analysis. Machine learning (ML) techniques, such as Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Decision Tree(DT), are employed on the Framingham dataset to predict the chance of disease.
DOI:10.1109/ICSCDS53736.2022.9760765