Classification and Diagnosis of Heart Disease Using Machine Learning

Abstract

Ayedh Abdulaziz Mohsen, Kharroubi Naoufel, Taher Alrashahy and Somia Noaman

The study aimed to explore the application of machine learning techniques in diagnosing and classifying various types of heart diseases. A number of algorithms commonly used in healthcare, such as the naive Bayes model, SVM, k-nearest neighbour (K- NN), and others, were reviewed. This study highlights the importance of the quality of the data used in the database to obtain an accurate and reliable diagnosis. The data were collected from patient records in hospitals and clinics and were analysed and compared with those of previous relevant studies. Clinical decision assistance software has been used to help surgeons make medical decisions based on patient information. Positive results have been achieved that confirm the effectiveness of using machine learning techniques in diagnosing heart disease. These technologies have shown the potential to improve the accuracy and efficiency of diagnosis, leading to improved patient outcomes and reduced health burdens. The findings also revealed the need to develop effective diagnostic tools and enhance the prevention of heart disease. This study provides an important foundation for healthcare professionals and doctors working in the field of cardiology, as the techniques used can help them better understand and diagnose conditions and improve patient care.

PDF