multiple-disease-of-Kidney-Heart

The increasing prevalence of chronic diseases such as kidney disease and heart disease necessitates the development of accurate, early, and automated diagnostic systems. This study presents a Multiple Disease Detection Framework that leverages machine learning and deep learning models to simultaneously detect kidney disease and heart disease with high precision. For kidney disease detection, we employ a combination of Decision Tree Classifier, AdaBoost Classifier, XGBoost Classifier, and CatBoost Classifier to evaluate and compare performance based on various clinical parameters. For heart disease, the framework integrates AdaBoost Classifier, Extra Trees Classifier, and a Convolutional Neural Network (CNN) model to capture both structured and unstructured health data patterns. The system is trained on publicly available datasets and evaluated using key performance metrics such as accuracy, precision, recall, and F1-score. The results demonstrate that ensemble-based machine learning models and deep learning architectures can be effectively used for the early and reliable detection of multiple diseases. This hybrid approach holds significant potential for integration into clinical decision support systems, improving diagnostic workflows and patient outcomes.

Keywords: Kidney Disease Detection, Heart Disease Classification, Ensemble Machine Learning, Convolutional Neural Network (CNN), Multi-Disease Diagnosis