Heart Disease Prediction Using Machine Learning Classification Models

A machine learning project focused on the early and accurate prediction of heart disease using clinical and medical parameters.

By leveraging features like age, cholesterol levels, and ECG results, this project aims to replace traditional, time-consuming diagnostic methods with efficient and interpretable classification models.

---

Objective

• Develop a robust ML framework for heart disease prediction
• Compare multiple classification algorithms to identify the best-performing model
• Enable early detection using standard medical diagnostic parameters

---

Features

Exploratory Data Analysis

• Statistical summary of medical features
• Distribution plots for key parameters (age, cholesterol, blood pressure, etc.)
• Correlation analysis between features and heart disease outcome

Data Preprocessing

• Handling missing values and duplicate records
• Feature scaling and normalization
• Label encoding for categorical variables
• Train-test split for unbiased evaluation

Classification Models

• Logistic Regression
• Decision Tree
• Random Forest
• K-Nearest Neighbors (KNN)
• Support Vector Machine (SVM)

Model Evaluation

• Accuracy, Precision, Recall, F1-Score
• Confusion Matrix visualization
• ROC-AUC curve comparison across models

Feature Importance

• Identifying the most significant clinical predictors
• Model interpretability for medical use cases

---

Tech Stack

Language

• Python

Libraries

• Pandas
• NumPy
• Matplotlib
• Seaborn
• Scikit-learn

Environment

• Jupyter Notebook

---

Project Structure

Heart-Disease-Prediction-Using-Machine-Learning-Classification-Models/
│
├── main.ipynb        # Full analysis notebook (EDA + model training + evaluation)
└── README.md

---

Getting Started

Prerequisites

pip install pandas numpy matplotlib seaborn scikit-learn

Run the Notebook

jupyter notebook main.ipynb

---

Dataset Features

Feature	Description
Age	Age of the patient
Sex	Gender (1 = male, 0 = female)
cp	Chest pain type (0–3)
trestbps	Resting blood pressure (mm Hg)
chol	Serum cholesterol (mg/dl)
fbs	Fasting blood sugar > 120 mg/dl
restecg	Resting ECG results (0–2)
thalach	Maximum heart rate achieved
exang	Exercise-induced angina
oldpeak	ST depression induced by exercise
target	Heart disease present (1) or absent (0)

---

Future Improvements

• Hyperparameter tuning using GridSearchCV / RandomizedSearchCV
• Add deep learning models (Neural Networks)
• Deploy as a web app using Flask or Streamlit
• Integrate with patient health records for real-world usage
• Explainability using SHAP values

---

License

MIT License