TITLE:
Identification of Cardiovascular Disease via Diverse Machine Learning Methods
AUTHORS:
Araf Islam, Mohammad Abu Saleh, Afia Fairooz Tasnim, Md. Samiun, Syeda Kamari Noor, Kanchon Kumar Bishnu
KEYWORDS:
Decision Tree, Logistic Regression, Random Forest, Preprocessing, Machine Learning, Accuracy
JOURNAL NAME:
Journal of Computer and Communications,
Vol.12 No.12,
December
26,
2024
ABSTRACT: Over the past ten years, there has been an increase in cardiovascular disease, one of the most dangerous types of disease. However, cardiovascular detection is a technique that analyzes data and precisely diagnoses cardiovascular disease using machine learning algorithms. Early diagnosis may lead to better outcomes for heart treatment. Then, utilizing machine learning to detect cardiac disease will be easy in a couple of seconds. This study proposes an automatic way for detecting cardiovascular diseases such as heart disease using machine learning. A physician’s accurate and thorough evaluation of a patient’s cardiovascular risk plays a critical role in lowering the incidence and severity of heart attacks and strokes as well as improving cardiovascular protection. To develop technology for the early detection of cardiovascular disease, the Kaggle dataset was gathered. Certain preprocessing techniques were used to improve accuracy and outcomes. Ultimately, we employed decision trees, logistic regression, and random forests to reach our objective. Of these, random forest yielded the highest accuracy of 96%, making them useful for obtaining high-quality results with greater precision.