This repository contains an implementation of an Artificial Neural Network (ANN) for the purpose of predicting diabetes based on various health metrics.
The application takes into consideration various health parameters including:
- Pregnancies
- Glucose
- Blood Pressure
- Skin Thickness
- Insulin
- BMI (Body Mass Index)
- Diabetes Pedigree Function
- Age
Using these parameters, the ANN model predicts the likelihood of an individual having diabetes.
- Training Accuracy: 83%
- Validation Accuracy: 80%
The model is trained on the Pima Indians Diabetes Database from Kaggle.
- Clone the repository:
git clone https://github.com/MohammadAminDHM/Diabetes-Detection-with-ANN.git
- Navigate to the project directory and install required packages (assuming you're using pip):
cd Diabetes-Detection-with-ANN
pip install -r requirements.txt
- Run the application (specific command based on how you've set it up, e.g.,
python app.py
) - also you can access to my notebook in my kaggle account NoteBook. please upvote my note book :)
- Implement more advanced models for better accuracy.
- Incorporate more parameters to improve prediction capability.
- Provide a user-friendly GUI for easy interaction.