• Mohith Saran Kanamarlapudi
• Keerthana Peddinti
• Guna Sekhar Chowdary
• Koushik Rao Gorikanti
• Dr. Jhansi Yellapu

The heart is an essential organ of the human body because it pumps blood through blood veins to all of the body's organs.. They are systolic and diastolic cycles. If the heart cycle gets failed then heart muscles do not pump blood well to the whole body. To reduce the death rate of heart failure a reliable system is to be developed. So, there is a need for a Heart failure Prediction system with high reliability, high accuracy to analyze the disease risk. This prediction system makes use of machine learning classification, regression, ensemble algorithms such as “Decision Tree Classifier (DT), Random Forest Classifier, Support Vector Classifier (SVM), Logistic Regression (LR), Gaussian Naïve Bayes Classifier (GNB) , K-Nearest Neighbours (KNN)”. This system predicts the disease into 0 or 1 i.e., High risk and low risk. The different metrics are used for evaluation of the model: accuracy, precision, recall, f1-score, support, cross-validation score (CV Score). The highest performance obtained using Logistic regression (accuracy = 83.1%, cross-validation = 84.3%), followed by Naïve Bayes (accuracy = 82.7%, cross-validation =82.3%), followed by Support Vector Classifier (accuracy = 82.3%, cross-validation = 85.1%), followed by KNN (accuracy = 81.8%, cross-validation =85.1%), followed by Random Forest Classifier (accuracy = 80.2%, cross-validation =83.5%), followed by Decision Tree Classifier (accuracy = 71.6%, cross-validation =78.1%). These outcomes suggest that the proposed technique is capable of predicting the condition of the disease accurately.

Machine Learning, Decision Tree Classifier, Random Forest Classifier, Support Vector Machine, Logistic Regression, Gaussian Naïve Bayes Classifier, K-Nearest Neighbours (KNN)

"Classification of Heart Disease Risk using Machine Learning Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.a88-a97, April-2022, Available :http://www.jetir.org/papers/JETIR2204013.pdf

"Classification of Heart Disease Risk using Machine Learning Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppa88-a97, April-2022, Available at : http://www.jetir.org/papers/JETIR2204013.pdf