Neutrosophic Fuzzy Simple Additive Weighting with Artificial Intelligence for Sustainable Heart Disease Recognition and Classification

Heart disease (HD) is considered the main cause of death rate around the world. Multiple systems and biomedical instruments in hospitals take large amounts of medical data. Thus, understanding the data linked with HD is vital to enhance the prediction performance. The timely intervention of HD is the most important factor in preventing patients from additional damage. In recent times, non-invasive medical procedures, including artificial intelligence-based approaches have been used in the healthcare sector. Particularly machine learning (ML) applies various techniques and algorithms that are extensively applied and are especially effective in accurately detecting HDs within short period. However, HD prediction is a challenging task. The largest size of medicinal database has made it a challenge for clinicians to understand the complicated feature relations and make disease predictions. Therefore, this study presents a Neutrosophic Fuzzy SAW with Artificial Intelligence for Sustainable Heart Disease Recognition and Classification (NFSAW-AISHDC) technique in Healthcare Sector. The NFSAW-AISHDC technique mainly focuses on the adoption of neutrosophic fuzzy simple additive weighting (NFSAW) with feature selection process for HD detection. The NFSAW-AISHDC method exploits min-max scalar to scale the input medical data. For feature selection, the NFSAW-AISHDC method uses beluga whale optimization (BWO) algorithm to choose feature subsets. Moreover, the NFSAW-AISHDC technique applies NFSAW approach to the identification of HDs. The performance values of the NFSAW-AISHDC methodology undergoes using benchmark database. The experimental outcome underlined the promising results of the NFSAW-AISHDC method with other models.