Date of Publication :25th September 2023

Abstract: In recent decades, heart diseases have become the leading cause of mortality worldwide. These diseases encompass a range of cardiovascular conditions, including blood vessel diseases, heart rhythm problems, and congenital heart defects. Early diagnosis plays a crucial role in effective management and improved patient outcomes, highlighting the need for precise and reliable methods of early detection through automation currently, physicians rely on clinical tests and their knowledge of patients' symptoms to diagnose cardiovascular disorders. However, patients with heart disease require early diagnosis, effective treatment, and ongoing monitoring. Data mining techniques have been utilized in the past to identify and predict cardiac diseases to address these needs. However, previous research has primarily focused on identifying major contributing factors for heart disease prediction, with less attention given to assessing the strength of these factors. As the incidence of heart diseases continues to rise, it becomes increasingly important to predict and detect these conditions at an early stage. However, accurate diagnosis presents challenges that call for precise and efficient procedures. Automation provides a potential solution by leveraging advanced technology and data mining techniques to analyze large datasets and identify patterns. Automating the diagnostic process can improve the speed and accuracy of diagnosis, leading to better patient outcomes and more effective management of cardiovascular diseases. This study focuses on estimating the risk of heart disease in patients based on various medical characteristics. A heart disease prediction system was developed using the patients' medical information. Machine learning algorithms, such as logistic regression, were employed to predict and categorize patients with heart disease. The suggested model demonstrated sufficient strength in predicting the presence of heart disease, showing higher accuracy compared to other classifiers like naive Bayes. The accurate identification of heart disease adds significant value to medical care, reducing costs and improving patient outcomes. The heart disease prediction system used in this study improves medical care by accurately identifying individuals at risk of heart disease. Automation and data mining techniques enhance the precision and efficiency of diagnosis, leading to better management of cardiovascular diseases.

Reference :