Coronary heart disease optimization system on adaptive-network-based fuzzy inference system and linear discriminant analysis (ANFIS-LDA)

Abstract

Coronary heart disease is a great concern in the field of healthcare, and one of the main causes of death across the world. In the USA, as in Europe, it is responsible for the highest mortality rate. Although the risk of coronary heart disease has been recognized, few studies have been conducted on this topic. On the other hand, computer science has become an important part of our lives. The use of medicine and medical science-related artificial intelligence facilitating the diagnosis and analysis of diseases and health problems is attracting considerable attention. The present study focuses on the determination of the optimum method for using artificial intelligence in a clinical decision support system in order to provide a solution and diagnosis regarding the research and medical issues related to the application of such a system. In the present study, we have developed a prediction model capable of the risk assessment of coronary heart disease by optimizing an adaptive-network-based fuzzy inference system (ANFIS) and linear discriminant analysis (LDA) on the basis of the dataset of Korean National Health and Nutrition Examinations Survey V. The ANFIS-LDA method, which is optimized using a hybrid method, exhibits a high prediction rate of 80.2 % and is more efficient and effective than the existing methods. We expect that our study to contribute to the prevention of coronary heart disease.