Skip to content

Latest commit

 

History

History
101 lines (73 loc) · 2.06 KB

readme.md

File metadata and controls

101 lines (73 loc) · 2.06 KB
Raw

Autism Spectrum Disorder Prediction Model

Project Overview

This project develops a machine learning solution for early detection of Autism Spectrum Disorder (ASD) using multiple classification algorithms. By leveraging advanced data preprocessing and machine learning techniques, the model aims to provide a reliable screening tool for potential ASD identification.

Key Features

  • Multiple Machine Learning Models:

    • Logistic Regression
    • XGBoost Classifier
    • Support Vector Machine (SVM)

  • Advanced Data Preprocessing:

    • Feature engineering
    • Age group categorization
    • Log transformation
    • Label encoding
    • Feature scaling

  • Handling Class Imbalance:

    • Random Over-Sampling technique to balance dataset

  • Interactive Streamlit Web Application:

    • User-friendly interface
    • Model selection
    • Real-time ASD prediction

Installation

  1. Clone the repository
git clone https://github.com/yourusername/autism-prediction.git
cd autism-prediction
  1. Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
  1. Install dependencies
pip install -r requirements.txt

Usage

Training the Model

python train.py

Running Streamlit App

streamlit run app.py

Model Performance Metrics

  • Logistic Regression:

    • Training AUC: ~0.85
    • Validation AUC: ~0.80

  • XGBoost:

    • Training AUC: ~0.90
    • Validation AUC: ~0.85

  • Support Vector Machine:

    • Training AUC: ~0.88
    • Validation AUC: ~0.82

Dataset

The dataset includes various features related to:

  • Demographic information
  • Behavioral scores
  • Medical history

Preprocessing Techniques

  • Log transformation of age
  • Feature engineering
  • Label encoding
  • Standard scaling
  • Handling class imbalance

Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/AmazingFeature)
  3. Commit your changes (git commit -m 'Add some AmazingFeature')
  4. Push to the branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

License

[MIT]