Machine Learning-Based Prediction of Cardiovascular Diseases Using Flask

Health care is an inescapable task in a human’s life. Cardiovascular diseases, also known as CVDs, are amongst the most prevalent causes of death globally, costing the lives of around 17.9 million people each year. CVDs include heart and blood vessel abnormalities that encompass problems such as coronary heart disease, brain disease, rheumatic heart disease, and more. The deaths can be reduced by early detection and treatment of cardiac problems. The present study compares the performance of various machine learning methodologies like SVM, KNN, and decision tree in terms of accuracy. For the prediction of cardiovascular diseases, we have taken few inputs like BP, cholesterol, glucose, current smoking, cigarettes count, BMI, and age. After implementing these methods, KNN had given the best accuracy in the detection of cardiovascular diseases (CVDs). KNN achieved about 80% accuracy in detection. After that we developed a user-friendly website, where users can be able to check whether they were facing any heart-related diseases by giving their parameters like glucose, cholesterol, BP, and so on.