🩺 Diabetes Prediction App

AI-Powered Health Risk Assessment

A modern, elegant web app that predicts diabetes risk using machine learning.

---

Overview

The Diabetes Prediction App is a simple, fast, and user-friendly tool that helps users estimate their risk of diabetes based on basic health information. It uses a trained machine learning model to generate predictions instantly, all wrapped in a clean, beautiful interface built with Streamlit.

---

🔗 Live App:

👉 https://diabetes-prediction-ixtwehdx5ekeoe2zfzybbf.streamlit.app/

App Image

---

Key Highlights

• Beautiful, intuitive design — anyone can use it

• AI-powered predictions based on medical data

• Instant results with one click

• Accepts 8 important health metrics:

  • Pregnancies
  • Glucose
  • Blood Pressure
  • Skin Thickness
  • Insulin
  • BMI
  • Diabetes Pedigree Function
  • Age

• Fully deployed online — no installation needed

• Built with real machine-learning techniques

---

How It Works

(Simple enough for non-technical readers, informative enough for technical ones)

• The user enters their health information
• The app sends the values to a machine learning model
• The model checks patterns learned from real medical data
• The user receives a High Risk or Low Risk result
• Results are displayed instantly, with no waiting

---

Tech Stack

• Frontend: Streamlit
• Backend: Python
• Machine Learning: scikit-learn
• Data: PIMA Indians Diabetes Dataset
• Deployment: Streamlit Cloud

---

For Non -Technical Team

The app uses a trained artificial intelligence model that looks at patterns in medical data to estimate diabetes risk.

---

🧰 Running the App Locally (For Developers)

  git clone https://github.com/your-username/diabetes-prediction.git
  cd diabetes-prediction
  pip install -r requirements.txt
  streamlit run app.py

---

📘 Model Details

• The machine learning model was trained using the PIMA Indians Diabetes dataset, performing:
• Data cleaning & preprocessing
• Feature scaling
• Model training (Random Forest )
• Evaluation using accuracy, confusion matrix

---

🧪 Example Input

Feature	Sample Value
Glucose	120
BMI	32.0
Age	33
Insulin	79

---

Future Improvements

• Add multiple ML models & model comparison
• Improve UI/UX with advanced components
• Integrate real medical dataset validation
• Add authentication for saving predictions
• Create an API endpoint (FastAPI / Flask)
• Mobile-friendly UI redesign
• User accounts for saving patient results
• Improved visualizations & health tips

---

Acknowledgments

• Medical Diabetes Dataset
• Streamlit Community
• scikit-learn Developers

---

🤝 Contributing

• Pull requests are welcome!
• Feel free to open issues for feature requests or bug reports.

---

📜 License

• This project is licensed under the MIT License.

---

👨‍💻 Author

• Name- Joseph Hinga Mwangi
• Email- hingamwangijoseph@gmail.com
• Github profile- https://github.com/JosephHinga