Skip to content

kruthi-sb/Cardiac_Events_ML

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

91 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Predictive Analysis of Cardiac Events using Machine Learning Techniques

Overview

This project aims to predict the risk of cardiac disease using machine learning techniques. The dataset used in this project is the Heart Attack dataset from the UCI repository. The project includes data preprocessing, exploratory data analysis, and the implementation of multiple machine learning algorithms to build models for prediction. The models are compared and evaluate using various metrics.

Dataset

The Heart Attack dataset used in this project is obtained from the UCI Machine Learning Repository. It contains information about patients who have had a heart attack within the past two years. The dataset includes 14 attributes and 303 observations.

Methods

  1. Data preprocessing
  2. Exploratory Data Analysis
  3. Machine Learning Algorithms
  4. Model Evaluation using Basic Metrics
    • Accuracy, Precision, Recall, F1 Score or Classification Report
    • Confusion Matrix
  5. Hyperparameter Tuning using Grid Search
  6. Model Evaluation using Advanced Metrics
    • Basic Metrics or Classification Report
    • Confusion Matrix
    • k-Fold Cross Validation
    • ROC
    • PRC
    • Learning Curve
  7. Feature Importance

Algorithms Used

Supervised Learning Algorithms for Classification:

  1. Logistic Regression
  2. K-Nearest Neighbors
  3. Support Vector Machine
  4. Decision Tree
  5. Random Forest
  6. AdaBoost
  7. Gradient Boosting
  8. Naive Bayes
  9. Ensemble (experiment)

Conclusions

It was found that Random Forest performed the best with an accuracy score of 95%.

Installation

To run this project, you will need to have Python-3 and the following libraries installed:

  • pandas
  • numpy
  • matplotlib
  • seaborn
  • sklearn

Usage

The code for this project is provided in the Jupyter notebook format. The notebook is well-commented and easy to follow along.

Author

Kruhti S B

License

This project is licensed under the MIT License - see the LICENSE.md file for details.

About

Prediction of Heart attacks using ML

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published