This project aims to predict the presence of kidney disease based on various symptoms and demographics information using machine learning techniques.
Chronic Kidney Disease (CKD) is a significant public health concern globally, affecting millions of individuals and posing substantial challenges to healthcare systems worldwide. Timely detection and accurate prediction of CKD progression are crucial for effective management and intervention strategies, aiming to mitigate its adverse outcomes and improve patient care. Machine learning (ML) techniques have emerged as valuable tools in healthcare, offering promising avenues for early detection and prediction of various diseases, including CKD. By leveraging large-scale patient data, ML models can identify intricate patterns and risk factors associated with CKD onset and progression, enabling healthcare providers to make informed decisions and intervene proactively.
- Google Colab
- numpy
- pandas
- matplotlib
- seaborn
The dataset used in this project is sourced from Kaggle. It contains information about individual symptoms, demographic characteristics, and CKD presence (target variable).
To run this project locally, follow these steps:
- Clone the repository:
- git clone: (https://github.com/kausik-t/EDA_Demo.git)
- Run the Colab notebook:
The Colab notebook Kidney Disease Prediction.ipynb contains the code for data preprocessing, model training, and evaluation. Follow the instructions in the notebook to execute the code and train the machine learning model.
The trained model achieves an accuracy of approximately 75% on the test dataset. Detailed evaluation metrics are provided in the notebook.