README.md

---
title: Diabetes Readmission
emoji: 💬
colorFrom: yellow
colorTo: purple
sdk: gradio
sdk_version: 5.42.0
app_file: app.py
pinned: false
hf_oauth: true
hf_oauth_scopes:
- inference-api
---

An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

# 🩺 Diabetes Readmission Prediction Web App

An interactive machine learning application deployed on **Hugging Face Spaces** to predict the likelihood of hospital readmission for diabetic patients using clinical and demographic data.

🔗 **Live Space:**  
https://huggingface.co/spaces/Parishri07/Diabetes_readmission

---

## 📌 Project Overview

Hospital readmission among diabetic patients is a critical healthcare challenge. This project provides a **web-based prediction system** that helps estimate the probability of readmission using machine learning models.

The application is designed for:
- Educational purposes
- Healthcare analytics demonstrations
- Machine learning deployment practice

---

## ✨ Key Features

- 🔍 **Readmission Prediction**  
  Predicts whether a diabetic patient is likely to be readmitted.

- 🖥️ **Interactive Web Interface**  
  Clean and simple UI built using **Gradio**.

- ⚡ **Real-Time Inference**  
  Instant predictions based on user inputs.

- 🧩 **Modular Codebase**  
  Easy to extend with new models or features.

---

## 📂 Project Structure

Diabetes_readmission/
├── app.py # Main application file
├── requirements.txt # Python dependencies
├── README.md # Project documentation
├── .python_version # Python version for Hugging Face Space
├── data/ 
├── models/ 
└── notebooks/  

---

## 🚀 How the App Works

1. User enters patient clinical information through the UI.
2. Input data is processed and passed to a trained ML model.
3. The model predicts readmission risk.
4. Results are displayed instantly on the interface.

---

## 🧠 Machine Learning Approach

The prediction system may use supervised ML models such as:

- Logistic Regression
- Random Forest
- Gradient Boosting / XGBoost

Model performance is evaluated using:
- Accuracy
- Precision
- Recall
- ROC-AUC

---

## 🛠️ Technologies Used

- **Python**
- **Gradio**
- **Scikit-learn**
- **Pandas & NumPy**
- **Hugging Face Spaces**

---