An enhanced cardiovascular disease Diagnosis using machine learning And automated deep learning

Abstract

Cardiovascular diseases (CVDs) are a category of heart and blood vessel illnesses that include coronary heart disease, cerebrovascular disease, peripheral arterial disease, rheumatic heart disease, congenital heart disease, deep vein thrombosis, and pulmonary embolism. In 2016, an estimated 17.9 million individuals died from CVDs, accounting for 31% of all global fatalities. In 2016, India recorded 63 %of overall sufferers owing to NCDs, with CVDs accounting for 27 %. CVDs are also responsible for 45 % of mortality in the 40-69 age range. Individuals at risk of CVD may have elevated blood pressure, glucose, and cholesterol levels, as well as being overweight or obese. Identifying people at the highest risk of CVDs and ensuring they receive adequate therapy can save lives. newlineAccording to the World Health Organization (WHO), India accounts for one-fifth of all stroke and ischemic heart disease fatalities, particularly among young individuals. With this motivation, the proposed research methodology implements various classification methods along with the Predefined filter methodologies. The selections of the algorithmic methods are reviewed by literature based on the merits and demerits. The addition of particular methodologies into the right detection mechanism provides maximum accuracy and enhances the results. The electrocardiogram (ECG) is a common 1-dimensional biological signal used to identify cardiovascular disorders. Due to the time-varying dynamics and various patterns of ECG signals, computer-aided diagnostic algorithms struggle to automatically categorise 1D ECG data newline