Clinical Diagnosis of Cardiac Diseases Using Anthropometric Features and Deep Learning

Cardiac illnesses constitute the leading motive of death in industrialized countries; therefore, the powerful scientific prognosis is extraordinarily critical for improving patient care. In current years, deep gaining knowledge has become an effective tool for picking out capabilities related to cardiac illnesses and improving diagnostic checks' performance. This paper gives a singular approach to diagnosing cardiac illnesses through anthropometric capabilities and deep-gaining knowledge. Thru the use of convolutional neural networks (CNNs), we were able to accurately become aware of bizarre styles in subjects' electrocardiogram (ECG) and numerical values of numerous anthropometric parameters inclusive of age, gender, frame mass index (BMI), waist circumference, and body fat percent, in addition to gadget mastering algorithms implemented to the outcomes. Furthermore, that allows us to beautify and make our machine sturdier; fusion techniques were carried out to the aforementioned anthropometric functions and ECG information. The results display the effectiveness of our proposed technique in diagnosing acute and continual cardiac diseases, which in turn can improve the clinical prognosis of cardiac diseases and consequently affect the diagnosis of patients.