Heart Disease Prediction Using Various Classification Models

Abstract

Heart disease can be prevented with accurate prediction, but it can also be fatal if the prediction is erroneous. The results and characterization of the UCI Machine Learning Heart Disease dataset are investigated in this research using various machine learning and deep learning mechanisms. This study includes the ensemble of methods, well known algorithms, comparisons with other better methodologies, using an efficient feature selection technique, hybrid approach, fuzzy based algorithms, removing the noisy data using an enhanced approach, and so on. The dataset contains 14 key attributes that were used in the assessment. The precision of machine learning algorithms is determined by the dataset used for training and testing. The knowledge saved can be useful as a source for anticipating future illnesses. The purpose of this study is to summarize fresh research together with relative outcomes on coronary health risk, as well as to encourage innovative goals using data mining and machine learning frameworks.