Leveraging Scalable Classifier Mining for Improved Heart Disease Diagnosis

The scalable classifier mining technique proposed in this article aims to improve the accuracy and scalability of heart disease prediction models. This method employs a wide range of methodologies, including data preparation, feature selection, ensemble learning, and distributed computing, among others, to handle complicated patterns in large datasets quickly. By merging decision trees, random forests, and XGBoost classifiers with the Apache Spark distributed computing platform, the proposed method outperforms both traditional machine learning techniques and cutting-edge deep learning algorithms. The proposed method achieved an accuracy of 93.5%, which is higher than any of the conventional machine learning methods and comparable to or better than the most cutting-edge deep learning methods. By encompassing all of the essential processes, such as preprocessing, feature selection, ensemble learning, model merging, and distributed computing, this technique assures that the model is accurate, efficient, and easy to comprehend. As a result, it is an especially well-suited approach for clinical applications. The proposed technique has effectively shown its potential to increase the accuracy and scalability of heart disease prediction models, resulting in high accuracy, scalability, and interpretability.