Research on Heart Disease Auxiliary Diagnosis based on Naive Bayes Classification

Abstract

Cardiovascular diseases (CVDs) have become a global health crisis, drawing widespread attention due to their severity and the significance of associated risk factors. The gravity of the situation necessitates a concerted effort to develop effective predictive tools and intervention methods to combat the escalating burden of heart diseases. As a result, this study addresses the urgent need for early prediction and intervention strategies for heart diseases. It collects various medical data related to heart disease patients, screens and extracts key datasets, and constructs a robust predictive model using the Naive Bayes method. The model is capable of analyzing and extracting predictive-relevant key features from a large set of diverse categorical features, thereby enhancing the efficiency and accuracy of the Naive Bayes model. With input from a relatively small amount of medical data, the model can assess an individual's risk of developing heart disease. This innovative approach not only conserves precious healthcare resources but also empowers healthcare institutions with the capability to monitor patient conditions and take timely, well-informed actions. Despite its inherent limitations, this research represents a significant step towards model-assisted heart disease prediction and highlights the potential application of machine learning models in the medical field, paving the way for future studies in personalized medicine.