Research Article
Towards Predicting the Risk of Cardiovascular Disease Using Machine Learning Approach
@INPROCEEDINGS{10.1007/978-3-030-93709-6_33, author={Hanna Teshager Mekonnen and Michael Melese Woldeyohannis}, title={Towards Predicting the Risk of Cardiovascular Disease Using Machine Learning Approach}, proceedings={Advances of Science and Technology. 9th EAI International Conference, ICAST 2021, Hybrid Event, Bahir Dar, Ethiopia, August 27--29, 2021, Proceedings, Part I}, proceedings_a={ICAST}, year={2022}, month={1}, keywords={Cardiovascular disease Risk prediction Machine learning techniques}, doi={10.1007/978-3-030-93709-6_33} }- Hanna Teshager Mekonnen
Michael Melese Woldeyohannis
Year: 2022
Towards Predicting the Risk of Cardiovascular Disease Using Machine Learning Approach
ICAST
Springer
DOI: 10.1007/978-3-030-93709-6_33
Abstract
Cardiovascular disease (CVDs) is one of the leading causes of mortality in the world taking around 18 million lives every year. As a result of the silent progression of CVDs, the rate of mortality is increasing at a higher rate than communicable, maternal, and neonatal diseases in a country like Ethiopia. The early stage detection and treatment, in turn, reduces the rate of mortality as well as the health care cost. For this, a total data set consisting of 10,029 unlabeled instances were analyzed from the Ethiopian Public Health Institution (EPHI). The data were collected by NCD STEPS survey. The population’s demographic and behavioral characteristics and also each participant’s physical and medical measurement data included in this dataset. Thus the given dataset doesn’t have a target variable. Therefore, in order to identify the hidden patterns from unsupervised learning, we use the k-means clustering algorithm and specify the number of clusters to k = 3 and cluster the patient condition into high risk, medium risk, and low risk. The data is further experimented with five different machine learning (ML) algorithm to build a predictive model for the risk of CVDs. The result obtained from the experiment using an artificial neural network (ANN) shows a promising result which is 99.4% accuracy. This result shows it’s possible to build an effective and efficient model for predicting the risk of having cardiovascular disease.
