Encoder for heart disease prediction

 This project uses a transformer-based neural network (FTTransformer) to predict heart disease, leveraging data from the Cleveland Heart Disease dataset.

• Data Preprocessing: Loaded and cleaned data, engineered features, and split for training and testing.
• Transformer-Based Model: Employed FTTransformer with embedding and encoder layers for classification.
• Model Performance: Achieved 83% accuracy, evaluated using precision, recall, F1-score, and a confusion matrix.

Built using Python, PyTorch, and data preprocessing tools for effective heart disease prediction.

For more details, features, and how to use it, explore the full project on GitHub: https://github.com/Adnaneessalmi/Encoder-for-heart-disease-prediction.