An Effective Investigation on Implementation of Different Learning Techniques Used for Heart Disease Prediction

Coronary artery disease and its aftereffects are among the leading causes of death worldwide in the modern era, despite the fact that death rates can be considerably lowered with timely detection and thorough prevention. A variety of artificial intelligence methods are employed in the prediction of coronary artery disease. We provide a medical recommendation system that effectively helps the early detection and management of heart disease by merging many classifiers. Fast Fourier transformation is used in conjunction with ensemble learning techniques in electronic health systems to improve the diagnosis of heart disease and medication use. The accuracy and applicability of the proposed strategy are compared with established methods for predicting cardiac disease. The proposed system supports cardiovascular risk prediction and recommendation functions, and it is thought that the ensemble model facilitates accurate prediction and the medical suggestion process. Additionally, time series analysis of the patient's data is made simpler by rapid Fourier transformation. Furthermore, the findings that show the ensemble machine learning model outperforms the individual classifiers are explained by the assumption that the proposed system's input dataset is free of noise and missing values.