/Heart-Disease-Prediction

This project develops a machine learning model to predict heart disease risk based on symptoms and medical history. The model achieved the best accuracy with Logistic Regression, as it works well for binary classification problems.

Primary LanguageJupyter NotebookMIT LicenseMIT

🫀 Heart Disease Prediction

📋 Overview

This project aims to predict the possibiltiy of heart disease in individuals based on various health parameters using machine learning algorithms. The model uses historical health data to make predictions that can assist in early diagnosis.

🔧 Technologies Used

  • Python
  • Pandas
  • NumPy
  • Scikit-learn
  • Matplotlib / Seaborn (for visualization)
  • Flask / Streamlit (for web application, if applicable)

📊 Dataset

The dataset used in this project is sourced from Kaggle. It contains various health parameters such as:

  • AgeCategory: Age group or range of the individual.
  • Sex: Biological sex (Male or Female).
  • BMI: Body Mass Index, a measure of body fat.
  • SleepTime: Average hours of sleep per day.
  • Mental Health: Days of poor mental health in the last 30 days.
  • Physical Health: Days of poor physical health in the last 30 days.
  • Smoking: Smoking status (Yes or No).
  • Alcohol Drinking: Alcohol consumption status (Yes or No).
  • Stroke: History of stroke (Yes or No).
  • DiffWalking: Difficulty in walking or climbing stairs (Yes or No).
  • Race: Race or ethnicity of the individual.
  • Diabetic: Diabetes diagnosis (Yes, No, or Borderline).
  • Phyisical Activity: Engagement in regular physical activity (Yes or No).
  • General Health: Self-assessed overall health status.
  • Asthma: Asthma diagnosis (Yes or No).
  • Kidney Disease: Kidney disease diagnosis (Yes or No).
  • Skin Cancer: Skin cancer diagnosis (Yes or No).
  • Target Variable (Heart Disease): Presence of heart disease (Yes or No).

Note

Make sure to preprocess the dataset before training the model. This includes handling missing values, encoding categorical variables, and normalizing numerical features.

✨ Features

  • Input health metrics to predict heart disease risk.
  • Model trained on various algorithms (e.g., Logistic Regression, Decision Trees, etc.) to find the most accurate model.
  • Visualization of data and model performance metrics.
  • (Optional) Web application for user input and predictions using Flask or Streamlit.

🤝 Contributing

If you would like to contribute to this project, please fork the repository and submit a pull request. Ensure that your changes are well-documented and tested.