ABSTRACT
In today’s world, cardiac diseases have emerged as the major cause of mortality in India and several other low- and middle-income countries. The number of people who die from cardiovascular diseases such as heart attacks and strokes will keep rising if this trend continues. The health sector gathers a huge amount of data on heart disease, but unfortunately, they cannot identify any essential information to make the most effective prediction. Despite the fact that numerous researchers have focused on heart disease prevention and therapy, the outcomes’ precision remains relatively low. This chapter aims to employ multi-criteria decision-making (MCDM), to correctly predict the prevalence of heart disease in an individual in order to save more lives by diagnosing and treating the patient before any significant issues arise. The Heart Disease UCI dataset’s features are reduced by removing unnecessary attributes. The MCDM can use a variety of normalisation techniques, and the results of two different MCDM normalisation techniques are compared. As compared to traditional methodologies, the proposed method has proven to be more effective in achieving high accuracy. It’s also been proved to be more effective at detecting and treating heart disease.
