The Diabetes Prediction App is a machine learning-powered web application designed to predict whether a person is diabetic or not based on various health metrics. Built using Python, Streamlit, and scikit-learn, the app allows users to input health parameters or load models to get instant predictions.
🌐 Deployed App: Diabetes Prediction App
- User-Friendly Input: Easily input health metrics like glucose levels, BMI, and age.
- Real-Time Prediction: Get instant predictions of "Diabetic" or "Non-Diabetic."
- Interactive UI: Responsive and intuitive interface built with Streamlit.
- Scalable Model: Uses machine learning models to ensure accurate predictions.
The app accepts the following inputs:
- Pregnancies: Number of times the patient has been pregnant.
- Glucose: Plasma glucose concentration.
- Blood Pressure: Diastolic blood pressure (mm Hg).
- Skin Thickness: Triceps skin fold thickness (mm).
- Insulin: 2-Hour serum insulin (mu U/ml).
- BMI: Body mass index (weight in kg/height in m²).
- Diabetes Pedigree Function: Diabetes pedigree function (genetic risk score).
- Age: Age of the patient.
-
Clone the Repository
git clone https://github.com/uttkarsh-thakur26/Diabetes-Risk-Prediction-Using-Machine-Learning
-
Install Dependencies Ensure you have Python 3.7+ installed. Install the required libraries:
pip install -r requirements.txt
-
Run the App
streamlit run application.py
-
Open the app in your browser at
http://localhost:8501.
- Python: Core programming language.
- Streamlit: For building interactive web apps.
- scikit-learn: For machine learning model development.
- Pandas & NumPy: Data processing libraries.
- Add advanced visualizations for predictions.
- Include options for loading user datasets.
- Support additional disease predictions.
Contributions are welcome! Please open an issue or create a pull request for suggestions and improvements.