Machine Learning Approach for Diagnosis of Heart Diseases
Manal Makram, N. Ali, Ammar Mohammed
May 8, 2022
Citations
1
Citations
Journal
2022 2nd International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC)
Full text
Semantic Scholar
Key Takeaway Key Takeaway: The neural network achieves the best results with an accuracy score of 96.15 for classifying cardiovascular diseases, outperforming other machine learning models.
Abstract
For decades, cardiovascular diseases have been the leading cause of death. According to the most recent WHO data, coronary heart disease deaths in Egypt accounted for 29.38 percent of all deaths in 2018. Egypt is currently ranked 15 in the world. Early detection of cardiac diseases can reduce mortality rates, manage resources, and save money. In this paper, we introduce machine learning models to classify cardiovascular diseases. The heart disease dataset was obtained from Egypt's Ain Shams University, Specialized Hospital for the inpatient department's Coronary Care Unit. A comparative analysis of several classifiers indicates that the neural network achieves the best results with an accuracy score of 96.15 heart disease classification, Machine learning (ML), support vector machine (SVM), k-nearest neighbor (KNN) and artificial neural network (ANN)