EDNCL: An Efficient Deep Learning Approach to Identify Cardiovascular Diseases Based on Enhanced Deep Neural Classifier Logic

In light of the detrimental consequences of heart disease on society, there has been a concerted effort to improve its diagnosis and treatment. Data mining and the storage of medical information can enhance patient management opportunities as technology and medical diagnostics become more synergistic. Consequently, it is imperative to investigate the interdependence of the risk factors in patients' medical histories and to understand their respective contributions to the prognosis of cardiac disease. The objective of this research is to conduct an analysis of the numerous components in patient data in order to accurately predict cardiac disease. The proposed model, which is referred to as Enhanced Deep Neural Classifier Logic (EDNCL), has been employed to identify the most critical attributes for the prediction of heart disease. This model is designed to accurately predict cardiovascular disease using deep learning principles. It is necessary to cross-validate the suggested scheme with the more traditional Random Forest Classifier (RFC) learning strategy in order to determine its effectiveness. The efficacy of vision transformer models is contrasted to the state-of-the-art methodology RFC in order to illustrate the framework's contribution. The proposed framework demonstrates notable classification results, as evidenced by the experiment results. The potential of this methodology to accurately detect cardiac disease from acoustic signals is illustrated in this study. These discoveries offer promising prospects for improving patient care and medical diagnosis.