CKD Prediction Using AI

Overview Chronic Kidney Disease (CKD) is a significant public health problem worldwide. Early prediction and diagnosis are crucial for effective management and treatment. This project aims to leverage Artificial Intelligence (AI) techniques to predict CKD using medical data. The project is divided into two phases, each employing different machine learning algorithms.

Project Structure Phase 1: Deep Neural Network (DNN) Algorithm Phase 2: Artificial Neural Network (ANN) with Normalization

Table of Contents Project Overview Project Structure Dataset Installation Usage Phase 1: DNN Algorithm Phase 2: ANN with Normalization Results

Dataset The dataset used in this project is sourced from [source name or link]. It includes various medical features that are relevant for CKD prediction.

Installation To get started with this project, clone the repository and install the necessary dependencies.

git clone https://github.com/yourusername/ckd-prediction-using-ai.git cd ckd-prediction-using-ai pip install -r requirements.txt

Phase 1: DNN Algorithm In the first phase, we use a Deep Neural Network (DNN) to predict CKD. The DNN model is trained on the dataset to identify patterns and relationships between features.

Model Architecture:

Input Layer Hidden Layers Output Layer Training:

Phase 2: ANN with Normalization In the second phase, we use an Artificial Neural Network (ANN) with normalization techniques to enhance prediction accuracy. Normalization helps in scaling the data to a specific range, which can improve the model's performance.

Normalization Techniques:

Min-Max Scaling Z-score Normalization Model Architecture:

Input Layer Hidden Layers Output Layer Training:

Results The results from both phases are compared to determine the effectiveness of each approach. Detailed performance metrics, including accuracy, precision, recall, and F1-score, are documented.