Heart Failure Analysis Project

Overview

This project focuses on analyzing heart failure data using machine learning and artificial intelligence (AI) techniques. The goal is to build predictive models that identify patterns in the data and provide insights into factors contributing to heart failure. The project includes data preprocessing, model training, evaluation, and visualization.

Key Concepts in AI

1. Supervised Learning
   The project uses supervised learning to train models on labeled data, predicting outcomes such as heart failure likelihood.

2. Neural Networks
   Neural networks are employed to model complex relationships in the data. The trained model's weights and biases are saved as .npy files.

3. Data Preprocessing
   Steps include handling missing values, normalizing data, and splitting the dataset into training and validation sets.

4. Model Evaluation
   Metrics like accuracy, precision, recall, and F1-score are used to assess model performance.

5. Ethical AI
   The project emphasizes ethical AI practices, including data privacy and avoiding bias in predictions.

Project Structure

PyCharmMiscProject/
├── analiza_insuficiena_cardiaca.ipynb  # Jupyter Notebook for analysis
├── heart.csv                          # Dataset
├── model/                             # Directory for model weights
│   ├── best_train_b.npy
│   ├── best_train_w_in.npy
│   ├── best_valid_b.npy
│   ├── best_valid_w_in.npy
├── .gitignore                         # Git ignore file

How to Run

1. Clone the repository:

   git clone https://github.com/tothantonio/repository-name.git
   cd repository-name

2. Install dependencies:

   pip install -r requirements.txt

3. Open the Jupyter Notebook:

   jupyter notebook analiza_insuficiena_cardiaca.ipynb

4. Follow the notebook steps to preprocess data, train the model, and evaluate results.

Requirements

• Python 3.8+
• Jupyter Notebook
• NumPy
• Pandas
• Scikit-learn
• Matplotlib

Ethical Considerations

• Ensure the dataset does not contain sensitive or personally identifiable information.
• Avoid using the model for medical diagnosis without consulting healthcare professionals.
• Be transparent about the model's limitations.

Future Work

• Experiment with different model architectures to improve accuracy.
• Add support for additional datasets to enhance generalization.
• Deploy the model as a web application for broader accessibility.

License

This project is licensed under the MIT License. See the LICENSE file for details.