Disease of heart is a crucial medical condition.
This needs timely and accurate intervention for successful treatment outcomes. It's equally vital to recognize symptoms of heart disease early. This can significantly enhance health outcomes. It also can prevent severe complications. In this research paper we delve into use of Machine Learning (ML) techniques. The focus is early detection of heart disease symptoms. The study concentrates on creation of predictive models. The goal is to assess risk of developing heart disease in an individual. The required analysis is a mix of physiological and clinical parameters. They originate from health data spanning past and present. Leveraging ML is the target. The aim is to bolster early diagnosis. The paper also aims for more effective prevention against heart disease. In this research we made use of one dataset. The dataset is from Kaggle. It was used
to evaluate accuracy of different machine learning algorithms. The best accuracy achieved is 86.578%. The dataset's parameters are Age, Sex, Is Smoking, Cigarettes Per Day, BP Medicine, Prevalent Stroke. Furthermore, there is Prevalent Hypertension, Diabetes, Total Cholesterol. Followed by Systolic BP, Diastolic BP, BMI, Heart Rate and Glucose.