Welcome to the Heart Attack Prediction Project! This project leverages data science and machine learning techniques to predict the likelihood of heart attacks based on various health metrics. The goal is to create a model that can assist in early detection and improve preventive measures for cardiovascular diseases.

The primary aim of this project is to:

• Analyze health data to identify patterns and correlations.
• Train and evaluate predictive models for heart attack risk assessment.
• Provide actionable insights for healthcare professionals and individuals.

• Exploratory Data Analysis (EDA): Gain insights from the dataset through visualizations and statistical analysis.
• Model Development: Build and compare multiple machine learning models to predict heart attack risks.
• Performance Metrics: Evaluate models using metrics like accuracy, precision, recall, and F1-score.
• Feature Importance: Identify critical health factors contributing to heart attack risks.

This project utilizes the following tools and libraries:

• Python - Core programming language
• Jupyter Notebook - For interactive analysis and model development
• Pandas - Data manipulation and analysis
• NumPy - Numerical computations
• Matplotlib & Seaborn - Data visualization
• Scikit-learn - Machine learning models and evaluation
• Random Forest - Advanced machine learning model for better accuracy

The dataset was sourced from Kaggle and contains the following key attributes:

• Age: Age of the individual
• Gender: Male or Female
• Chest Pain Type: Type of chest pain experienced
• Resting Blood Pressure: Blood pressure in mmHg
• Cholesterol Level: Serum cholesterol in mg/dl
• Fasting Blood Sugar: Whether fasting blood sugar > 120 mg/dl (1 = true; 0 = false)
• Resting ECG Results: Electrocardiographic results
• Maximum Heart Rate Achieved
• Exercise-Induced Angina: 1 = Yes; 0 = No
• ST Depression: Value of ST depression induced by exercise
• Target: Whether the individual experienced a heart attack (1 = Yes; 0 = No)

1. Load the dataset into the notebook.

2. Follow the steps in the Jupyter Notebook to:

   • Perform data cleaning and preprocessing.
   • Conduct exploratory data analysis (EDA).
   • Train machine learning models.
   • Evaluate model performance.

3. Experiment with hyperparameters and visualize results.

The project includes:

• Comprehensive analysis of health metrics.
• Insights into significant risk factors for heart attacks.
• A trained predictive model with evaluation metrics.

• Omar Hashem – Team Leader 👨‍💻
• Omar Mohamed – member 💻
• Abdelrahman Mohamed Abdelaty – member 💻
• Youssef Bahy – member 💻
• Ali Afifi – member 💻
• Mohamed Khater – member 💻

• Kaggle Dataset for providing the data.
• Open-source libraries and the Python community for continuous support.

Thank you for exploring the Heart Attack Prediction Project! If you have any questions or suggestions, feel free to reach out. 💡