Background and Objectives: Cardiovascular diseases have been identified as one of the most prevalent global health issues, and delays in treatment can lead to increased mortality among patients. The primary objective of this study has been to enhance the identification of heart disease patients using a machine learning classification system.
Methods: In this research, machine learning classification systems with rule-based learning techniques have been employed. These techniques are built upon two fundamental principles, reinforcement learning, and genetic algorithms. The Mishgan style has been selected as the optimization method, and a dataset of heart disease patients from the Afshar Research Center has been utilized for the training and learning of the system.
Findings: Following the training of the system, a set of valuable rules has been generated and utilized in the testing phase for predicting heart disease patients. The experimental results indicate that using the Mishgan-style machine learning classification system has improved the identification of heart disease patients, resulting in an 88% increase in prediction accuracy. In other words, this approach enables a more comprehensive identification of heart disease patients.
Conclusion Considering the study's outcomes, the use of the Mishgan-style machine learning classification system as an optimal approach has enhanced the identification of heart disease patients and increased prediction accuracy. This method can contribute significantly to timely treatment of heart disease patients and the reduction of morbidity and mortality associated with these diseases.