This heart disease prediction project is one of my first and favorite machine learning projects. Before this, I worked on a few simpler projects to understand the fundamentals of machine learning, coding, and how different components work together. However, this project was a significant step forward in applying my skills to a real-world problem.

I have dedicated significant time to refining this project, integrating multiple technologies to enhance its performance and usability. It incorporates key tools and techniques I’ve learned, including Docker, GitHub Actions, Streamlit for web app development, exploratory data analysis (EDA), and pickle files for saving models and pipelines. Additionally, I implemented rigorous testing to ensure the reliability of both the model and the application.

To make the project publicly accessible, I explored various deployment platforms like Heroku and AWS but opted for a cost-free solution using Streamlit.io. If you'd like to check it out, here’s the link: Heart Prediction Web App.

My goal was to achieve the highest possible accuracy, and I successfully reached 86% in predicting heart disease. This project not only showcases my technical expertise but also reflects my commitment to continuously improving my data science and software development skills.

📂 View the Source Code

Click here to view the full code