Snake Optimization of Multiclass SVM for Efficient Diagnosis of Heart Disease Risk Prediction

Cardiovascular diseases are identified as a leading cause of death within the general population. Diagnosing heart disease poses a considerable challenge due to its complexity and the need for both precision and efficiency. Early detection is pivotal in lowering the risk of fatality. Various factors such as age, gender, cholesterol and glucose levels, and heart rate contribute to the onset of severe cardiac issues. However, due to the multifaceted nature of these variables, healthcare professionals often find it challenging to comprehensively assess individual risk profiles. Machine learning algorithms can enable rapid, low-cost detection of heart disease. In this paper, we introduce an approach that leverages Machine learning algorithm that is Support Vector Machine techniques to gauge the susceptibility of individuals to cardiovascular disease. The best accuracy of multiclass SVM with Linear function depends on optimal parameter selection; of kernel scale (gamma) (σ) and box constraint (C). Intelligent optimization methods such as Snake optimization are used to select the optimal values of kernel scale (σ) and box constraint (C). Compared to existing state-of-the-art models, our proposed methodology attained an accuracy rate of 92.35%. This represents a substantial advancement, particularly for a condition that has widespread prevalence.