Apppublic

Niha1710/hiv-case-prediction

sourceHugging Facemitupdated 6mo agoView on Hugging Face

1likes

App README

🔬 HIV Occurrence Prediction

An AI-powered web application that predicts the risk of HIV occurrence based on patient demographic, clinical, and behavioral factors using Logistic Regression.

🚀 Features

—Clean, modern Streamlit UI
—Logistic Regression model for risk prediction
—Label Encoding for categorical variables
—Probability-based risk output
—Medical disclaimer included

📋 Input Features

Feature	Type
Age	Numeric
Gender	Categorical
Marital Status	Categorical
Education Level	Categorical
Employment Status	Categorical
Area of Residence	Categorical
Number of Sexual Partners	Numeric
Condom Use	Categorical
STI History	Categorical
Blood Transfusion History	Categorical
IV Drug Use	Categorical
Previously Tested for HIV	Categorical

🧠 Model

—Algorithm: Logistic Regression
—Preprocessing: Label Encoding
—Output: Binary Classification (High Risk / Low Risk) + Probability

⚠️ Disclaimer

This tool is for research and educational purposes only. It is not a substitute for professional medical advice, diagnosis, or treatment. Always consult a qualified healthcare provider for HIV testing and counseling.

🛠️ How to Run Locally

bash

pip install -r requirements.txt
streamlit run app.py

📁 Files

├── app.py                  # Main Streamlit application
├── model.pkl               # Trained Logistic Regression model
├── label_encoder.pkl       # Label Encoder for categorical features
├── requirements.txt        # Python dependencies
└── README.md               # This file