Cardiovascular Disease Prediction: using Ensemble Learning

This repository hosts a software application designed to predict the probability of an individual having cardiovascular disease. By employing ensemble learning techniques, the software combines multiple machine learning models, including Logistic Regression, Gradient Boosting Classifier, and Random Forest Classifier, to enhance predictive accuracy. Users can input various attributes such as age, gender, blood pressure, cholesterol level, and lifestyle habits into the software to obtain predictions about their cardiovascular health.

The Cardiovascular Disease Detection software is a valuable tool for individuals seeking insights into their cardiovascular health risk and guidance on promoting a heart-healthy lifestyle. Users can benefit from the web applications ease of use and compare predictions from different machine learning models to make informed health decisions. Contributions and feedback from the community are welcomed to further enhance the softwares capabilities and impact.

• Ensemble Learning: The software employs an ensemble learning approach to combine multiple machine learning models for better predictive performance.
• Web Application: A user-friendly web application allows users to input their attributes and receive predictions for cardiovascular disease.
• Input Attributes: The software considers several input attributes, including age, gender, blood pressure, cholesterol level, smoking and drinking habits, and exercise routines.
• High Accuracy: The ensemble model used in the software achieves an accuracy of approximately 74% on the test dataset.
• Instructions for High Chance of Cardiovascular Disease: If the prediction indicates a high likelihood of cardiovascular disease, the software provides guidance, including consulting a healthcare professional, making lifestyle changes, and adhering to prescribed medications.
• Instructions for Low Chance of Cardiovascular Disease: If the prediction indicates a low likelihood of cardiovascular disease, the software advises maintaining a healthy lifestyle, scheduling regular check-ups, and promoting cardiovascular health awareness.
• Dataset: The software utilizes the Cardiovascular Disease dataset (cardio_train.csv) for training the machine learning models.
• License: The project is licensed under the MIT License, allowing for open-source contributions and usage.
• Acknowledgments: The development of this software is inspired by the need for a user-friendly cardiovascular disease risk prediction tool. The software credits the open-source community for providing essential libraries and tools.