See all projects

Prediction4Protection: Machine Learning Application in Early Heart Disease Prediction

High School
Mills E Godwin High School - CMS
Graduation Year
Student review
I think my experience with my mentor exceeded my expectations and I enjoyed forming a personal bond with her.

View Polygence scholar page
Project description

The availability and widespread distribution of healthcare in third-world and developing countries is scarce, and the threat of unreliable medical care is only exacerbated by issues of poverty and financial instability. Even within developed countries, the rights of healthcare are often infringed upon by the burdens of inadequate scheduling and unaffordable costs for the average citizen. Without proper screening and regular medical visits, early detection and treatment of heart disease, one of the prime methods of diminishing the risks the condition carries, the numbers of people who succumb to heart diseases are at a much higher rate than what they could be with modern technology. Recognizing the potential in providing this care for everyone, this project was created with the aim of predicting heart disease using the same indicators identified by healthcare professionals. In this way, those with a family history of heart disease, those with preexisting conditions, those who do not have proper access to medical care, and those who simply yearn to assess their health will still have the ability to do so with a short assessment that has the potential of saving their life. Ankita is working on a machine learning project with applications in the medical field, specifically heart disease detection, the top killer across the world. She is using heart health data to predict if a patient has glaucoma. She will work through a traditional machine learning pipeline consisting of collecting and cleaning the data, training and tuning a model, and testing it to measure its performance. In the end, she will create a web application that will allow users to input their data and return a positive or negative CVD diagnosis in real time.

Prediction4Protection: Machine Learning Application in Early Heart Disease Prediction
Project outcome

The outcome of this project was a Streamlit mobile application which can be accessed from a simple link and browser extension. This application has a 95+% accuracy and can be opened in browsers around the world.

MS Master of Science candidate
Quantitative, Comp Sci
computer science (Python, C++, Java), data science and machine learning (Scikit-Learn, numpy, Keras, Pandas, TensorFlow)
Mentor review

She was very helpful and flexible with any questions I had no matter what progress I made.

Interested in starting
your own project?
Apply today!

Already have an account? Log In
By registering you agree to our terms of use and privacy policy, and consent that we or our partner provider may reach out to you using a system that can auto-dial.