https://github.com/bdeekshith066/diabetes-prediction-ml-model
Diabetes prediction ML model with 78.664% accuracy trained on a dataset with 768 entries and 9 health metrics, facilitating early identification of diabetes risk.
https://github.com/bdeekshith066/diabetes-prediction-ml-model
Last synced: 8 months ago
JSON representation
Diabetes prediction ML model with 78.664% accuracy trained on a dataset with 768 entries and 9 health metrics, facilitating early identification of diabetes risk.
- Host: GitHub
- URL: https://github.com/bdeekshith066/diabetes-prediction-ml-model
- Owner: bdeekshith066
- Created: 2024-01-30T15:06:35.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-01-30T15:46:47.000Z (over 2 years ago)
- Last Synced: 2025-03-16T00:33:14.432Z (over 1 year ago)
- Language: Python
- Size: 941 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Diabetes Prediction Machine Learning Model
This repository hosts a machine learning model for predicting the likelihood of diabetes in individuals based on key health metrics. The model, trained on the provided dataset named **dataset.cnv**, demonstrates an accuracy of 78.664% in predicting diabetes.
## Overview
Diabetes is a prevalent health concern, and early prediction can play a pivotal role in effective management and prevention. This machine learning model leverages a dataset with 768 entries and 9 columns, including features such as pregnancies, glucose levels, blood pressure, skin thickness, insulin levels, BMI, diabetes pedigree function, age, and the outcome (0 for non-diabetic, 1 for diabetic).
## Features
- **Machine Learning Algorithm**: The model employs a state-of-the-art machine learning algorithm fine-tuned for diabetes prediction.
- **Accuracy**: Achieving an accuracy of 78.664% on the test dataset, this model provides reliable predictions.
- **Input Features**: The model considers a comprehensive set of health metrics, ensuring a robust analysis for accurate diabetes predictions.
## Data
### Columns
1. **Pregnancies**: Number of times pregnant
2. **Glucose**: Plasma glucose concentration a 2 hours in an oral glucose tolerance test
3. **BloodPressure**: Diastolic blood pressure (mm Hg)
4. **SkinThickness**: Triceps skin fold thickness (mm)
5. **Insulin**: 2-Hour serum insulin (mu U/ml)
6. **BMI**: Body mass index (weight in kg/(height in m)^2)
7. **DiabetesPedigreeFunction**: Diabetes pedigree function
8. **Age**: Age in years
9. **Outcome**: Class variable (0 if non-diabetic, 1 if diabetic)
### Usage
1. **Download the Dataset**: Access the dataset which is uploaded above.
2. **File Format**: The dataset is provided in the ".cnv" format, facilitating seamless integration for training and evaluation.
3. **Data Exploration**: Perform an exploratory data analysis to understand feature distributions before utilizing the dataset for model training.
### Dataset Structure
- **dataset.cnv**: The main dataset file with 768 rows and 9 columns.
### How to Use
1. **Training**: Utilize the provided Jupyter notebook (*diabetes_prediction_model.ipynb*) or script to train the model on your dataset.
2. **Prediction**: Leverage the trained model for diabetes prediction by providing relevant input features.
### How to Contribute
Contributions are welcome! Whether you're enhancing the model, adding features, or improving documentation, follow the standard GitHub workflow. Fork the repository, create a branch, make changes, and submit a pull request.