An Empirical Approach to Heart Disease Prediction Using Machine Learning Algorithms: A Case Study on Heart Disease
Abstract
Heart disease remains a major health concern worldwide, necessitating effective early prediction and diagnosis to reduce its impact. In this research paper, we explore the use of machine learning algorithms for heart disease prediction, leveraging data from the UCI Machine Learning Repository. The dataset contains 270 instances with 13 features and is divided into two classes: "class" with 150 instances and "Present class" with 120 instances. We employ two machine learning algorithms, Multilayer Perceptron (MLP) and Support Vector Machine (SVM), to evaluate their performance in classifying heart disease cases. Our results reveal that both MLP and SVM demonstrate promising accuracy, precision, and recall, showcasing their potential in enhancing heart disease prediction models.
Keywords
Download Options
Introduction
The fundamental organ of the human body is heart. The limit of the heart is to siphon the blood and circles entire body [1]. The coronary ailment (HD) has been viewed as one of the complex and life deadliest human disorders on earth. In this ailment, for the most part the heart can't push the fundamental proportion of blood to various bits of the body to fulfill the conventional functionalities of the body, and along these lines, in the end the cardiovascular breakdown occurs. As shown by the World Wellbeing Association (WHO), a normal 17 million people fail horrendously consistently from cardiovascular sickness, particularly coronary disappointments and strokes [4][10].
The symptoms of coronary disease consolidate shortness of breath, inadequacy of genuine body, enlarged feet, and exhaustion with related signs, for example, raised jugular venous squeezing component and periphery edema achieved by valuable heart or noncardiac inconsistencies [9]. The assessment strategies in starting stages used to recognize coronary sickness were tangled, and its ensuing unpredictability is one of the critical reasons that impact the standard of life. The coronary ailment assurance and treatment are very mind boggling, especially in the rural countries, in light of the remarkable openness of suggestive mechanical get together and absence of specialists and others resources which impact authentic assumption and treatment of heart patients. The exact and genuine examination of the coronary ailment risk in patients is essential for diminishing their connected risks of serious heart issues and further developing security of heart [10].
Conclusion
In this research, we embarked on a comprehensive exploration of machine learning algorithms for heart disease prediction using data sourced from the UCI Machine Learning Repository. Heart disease remains a pervasive and potentially lifethreatening condition, underscoring the importance of accurate prediction and early diagnosis. Our study aimed to assess the performance of two prominent machine learning algorithms, Multilayer Perceptron (MLP) and Support Vector Machine (SVM), in this critical task.
Our results demonstrate that both MLP and SVM exhibit strong predictive capabilities, with SVM achieving slightly superior performance. SVM's high accuracy, precision, and recall scores (93.47%, 93.5%, and 93.5% respectively) highlight its potential as a valuable tool for identifying individuals at risk of heart disease. Its ability to minimize false positives and false negatives signifies its practical utility in real-world healthcare scenarios.