A Comparative Study Utilizing Machine Learning Algorithms to Predict Heart Disease in Young and Middle-Aged Adults

Abstract

Early diagnosis is crucial since heart disease is getting more and more common. In the field of medicine, machine learning algorithms are now used to predict cardiac and cardiovascular illness. examining and confirming the functionality of machine learning. Heart disease is becoming more and more commonplace worldwide. A multitude of factors impact the likelihood of a heart attack and other illnesses. In many countries, limited cardiovascular competency makes it difficult to predict complications related to heart disease. One way to predict the possibility of a heart disease-related issue is to use data mining and machine learning techniques to identify which machine learning classifiers are most accurate for various diagnostic applications. Several supervised machine-learning algorithms are evaluated for their effectiveness in predicting cardiac illness. Use the heart disease individual dataset available via Kaggle. This work employs several machine-learning algorithms, including. Using Logistic Regression (LR), Navie Bayes (NB), Extreme Gradient Boost (EGB), K-Nearest Neighbor (K-NN), Support Vector Classifier (SVC), Random Forest (RF), and Decision Tree (DT), a neural network is constructed. Capable of categorizing binary data. For every feature across all deployed, estimated feature significance ratings were supplied. Ways. This helps identify the main risk factors for heart disease in addition to increasing model accuracy and assisting in the best forecast. Lastly, in comparison to all machine learning methods and Neural. The Binary Classification Neural Network, as a network model, produced the highest testing accuracy of more than 90%.