Diabetes Prediction

Abstract

1. Introduction

The Diabetes Prediction with AI project leverages a machine learning model to predict diabetes risk. Built with Streamlit, the app explains predictions using SHAP and permutation importance while showcasing model performance metrics. This model has not been reviewed by medical professionals; it is developed solely for experimental and testing purposes. The model was developed based on the ROC AUC metric, while efforts were made to improve the Recall metric when selecting the threshold, as this decision was made due to the medical context.

Check out the live application: Diabetes Prediction App

This project demonstrates a machine learning solution for predicting diabetes based on user-provided health data. The application uses Streamlit for an interactive web interface and advanced interpretability tools like SHAP and permutation importance to explain model predictions.

2. Objective

Diabetes Prediction with AI & Machine Learning model and visualisation with streamlit.

This project demonstrates how Jupyter Notebook, Machine Learning, scikit-learn can be applied to a real-world AI & Machine Learning problem.

3. Key Features / Modules

• Interactive Input: Enter health parameters (Pregnancies, Glucose, Insulin, BMI, Age).
• Diabetes Prediction: Real-time risk prediction with probability.
• SHAP Explanations: Visualize individual prediction explanations using:
• Waterfall Plot
• Force Plot
• Permutation Importance: Analyze which features most influence the predictions.
• Performance Metrics:
• Accuracy
• Precision
• F1 Score

4. Technology Stack

5. System Requirements

General requirements for this technology stack — check the README for exact versions.

• Python 3.8 or later with Jupyter Notebook / JupyterLab (or Google Colab)
• pip for dependencies
• Git (to clone the repository)

6. Installation & Setup

git clone https://github.com/UznetDev/Diabetes-Prediction.git
cd Diabetes-Prediction

Full setup instructions are in the project README.

7. Future Enhancements

Suggested extensions you can add to make this your own project.

• Deploy the model as a web app with Streamlit, Flask or FastAPI
• Compare against an additional model and report the metric difference
• Add explainability (SHAP / Grad-CAM)

8. Viva / Review Questions

Common questions examiners ask for projects in this domain.

1. What dataset does the project use and how was it pre-processed?
2. Which algorithm / model architecture is used and why was it chosen over alternatives?
3. How are training and testing data split, and how is overfitting avoided?
4. Which evaluation metrics (accuracy, precision, recall, F1) are reported and what do they mean here?
5. How would you deploy this model for real users?

9. Source Code & License

This project is developed by UznetDev and published on GitHub under the MIT License. Please follow the license terms and credit the original author when you use or modify this code.