Early Cardiovascular Disease Detection Using Predictive Machine-Learning Models: Evaluation and Insights

Cardiovascular illnesses are a significant cause of death worldwide, emphasizing the vital need for early detection to improve treatment and reduce healthcare expenses. Machine learning has become a crucial tool in healthcare because it can be used to analyze intricate data patterns and deliver accurate prognostic assessments. Implementing this technology in cardiology is critical for assessing risks, detecting problems early, and customizing treatment plans. This study aimed to develop a predictive machine-learning model for the early detection of heart disease. Eight classifiers, namely, k-nearest neighbors, support vector machine, logistic regression, random forest, decision tree, artificial neural networks, gradient boosting, and CN2 rule induction, were utilized to enhance the accuracy of heart disease predictions in the field of machine learning. One of the contributions of the proposed method is its enhanced early detection of cardiovascular disease compared with existing models using the same dataset in terms of both performance and complexity. This study evaluated various classifiers and their efficacies, offering helpful information for the development of trustworthy prediction models for cardiovascular diseases. These models were evaluated for heart illness using the UCI dataset and achieved improved accuracy and performance metrics. From the perspective of AUC, accuracy, F1-score, precision, and recall, the results of this study demonstrate the efficacy of the CN2 rule induction and random forest models for detecting cardiovascular disorders.