This project aims to develop a comprehensive classification system for chronic kidney disease (CKD) to address the growing healthcare challenge in Egypt. By leveraging machine learning and deep learning techniques, we seek to analyze patient data to predict the presence of CKD and facilitate early diagnosis and intervention.
- Utilizes a variety of datasets, including publicly available and Egyptian-specific data, to ensure relevance to the local context.
- Employs traditional machine learning techniques such as Logistic Regression, K-Nearest Neighbors, Decision Trees, Naïve Bayes, Random Forest, Support Vector Machines, and XGBoost.
- Incorporates deep learning using a Multi-Layer Perceptron (MLP) neural network for enhanced predictive accuracy.
- Libraries used include Scikit-learn, XGBoost, TensorFlow, Keras, Matplotlib, Seaborn, and NumPy for model development, training, evaluation, and visualization.
- Rigorous preprocessing techniques are applied to handle missing values, feature scaling, and encoding categorical variables.
- Model performance is evaluated using standard metrics such as accuracy, precision, recall, and F1-score, with confusion matrices providing insights into predictive performance.
- Future directions may include exploring additional deep learning architectures to further enhance model accuracy and applicability.
- Clone the repository to your local machine.
- Run the Jupyter Notebook or Python script to execute the code and generate predictions.
- Adjust hyperparameters and explore different algorithms as needed.
- Provide feedback and contribute to ongoing efforts to improve CKD management strategies.
- Youssef Ashraf ElNaggar
- Abdelrhman Salah Salem
- Ahmed Sherif
- Mohamed Megahed