Abstract: Since there are more and more cases of heart disease every day, it is important and concerning to anticipate any prospective problems. It takes accuracy and quickness to complete this difficult diagnosis. I will create a system that predict whether or not a patient will be diagnosed with heart disease based just on patient's medical history using a number of machine learning techniques, including such regression models, Random Forest, and KNN. The model is controlled in a very beneficial method to boost the accuracy of myocardial infarction prediction in each individual. Random Forest, KNN, and Logistic Regression are used in the suggested model, which has the advantage of predicting heart disease symptoms in a specific person with greater accuracy than previously used classifiers like naive bayes. These techniques will also show better accuracy than other classifiers like naive bayes. So, a great deal of pressure has been reduced by using the presented model to assess the possibility that the classifier will accurately and consistently detect cardiovascular disease. This experiment teaches us a lot that we can utilise to forecast who will develop heart diseases.
Keywords: Random Forest, KNN, Logistic Regression, Machine Learning, Prediction.
|
DOI:
10.17148/IJARCCE.2023.12325
