Key points are not available for this paper at this time.
Coronary illness stands apart as a conspicuous supporter of worldwide death rates. Biomedical devices and various hospital applications generate extensive clinical data, providing a rich resource for predictive analysis. Artificial Intelligence (AI) is increasingly harnessed to forecast heart conditions, with Machine Learning (ML) emerging as a potent tool for informed decision-making and precise predictions. Significant strides are evident in the medical industry's adoption of machine learning techniques. This progress primarily hinges on training models with sample cases, utilizing data from clinical tests to predict ailments. Consequently, a comprehensive understanding of heart disease-related data becomes imperative for enhancing prediction accuracy. A pivotal role is played by feature selection in this process, as it effectively eliminates redundant and irrelevant features, thereby reducing the training cost and time of predictive models. This article advocates for the usage of AI-based highlight determination methods in anticipating coronary illness. The proposed work introduces a disease prediction model employing various combinations of feature selection techniques. The efficacy of the prediction model is assessed using a dataset sourced from a heart disease database. The proposed strategies are assessed because of exactness, accuracy, review, and f1-score. Moreover, these systems have the potential to assist physicians in making precise decisions during the diagnosis of heart disease.
Ramathilagam et al. (Tue,) studied this question.