Abstract: Heart attack is one of the most pressing problems in health care. Heart-related or cardiovascular diseases are the leading cause of many deaths in the world over the past few decades and have emerged as the most life-threatening disease. We need a reliable, accurate, and feasible system for urgently diagnosing such diseases for proper treatment. Nowadays, machine learning is known to play a huge role in the medical industry and the application of machine learning algorithms and techniques on various medical data sets to automate the analysis of large and complex data using various machine learning models for disease diagnosis, classification, or prediction. Results. Several researchers are recently using various machine learning techniques to help the healthcare industry and professionals diagnose heart-related diseases. This research provides an improvement on the factors and triggers that may lead to a heart attack. This research focuses on developing a simplified framework that combines several machine learning techniques such as Naïve Bayes, Support Vector Machine (SVM), K-Nearest Neighbor, Decision tree, and Random Forest to help predict early heart attacks for different age groups using patient data. Both quantitative and qualitative approaches are used, which helped to analyze and evaluate data specifically collected from the Saudi community to conduct this research. The results indicated that the proposed developed framework outperformed the model in the initial stage as it gave SVM greater accuracy in less time to predict with an accuracy of 85.99%. Finally, the framework is evaluated using evaluation criteria, in addition to comparing the work with the previous work.
Keywords: Classification Algorithms, Accuracy, Heart Attack, Machine Learning, Cardiovascular Disease.
|
DOI:
10.17148/IJARCCE.2022.11911
