Heart Disease Prediction with Machine Learning Algorithms

Project Documentation

Click here to access project documentation

PPT

Click here to access project presentation

Objective of the Project

The primary objective of creating the heart disease prediction model is to develop a robust and accurate tool for early detection and risk assessment of heart diseases. By leveraging machine learning algorithms, the model aims to analyze diverse medical parameters and provide timely predictions, enabling proactive healthcare interventions. Ultimately, the goal is to enhance preventive care strategies and contribute to better patient outcomes by identifying potential heart-related risks in advance.

Data Source Used

https://www.kaggle.com/datasets/fedesoriano/heart-failure-prediction

Machine Learning Algorithms Used:

1. Logistic Regression
2. K-Nearest Neighbors (KNN)
3. Support Vector Machine (SVM)
4. Decision Tree Classifier
5. Random Forest Classifier
6. Naïve Bayes
7. Bagging
8. Adaptive Boosting
9. Extreme Gradient Boosting
10. MaxVoting

[Maximum Accuracy achieved: 92% (approx) using Logistic Regression]

Website

Click here to access project website