Inspiration
We want to help people prevent medical conditions with easy-to-use check-ups.
What it does
It is a web application that provides access to Machine Learning algorithms trained on medical data to provide medical predictions based on questionnaire results.
How we built it
We search for medical datasets, train Machine Learning algorithms with the data using SciKit Learn, and deploy an application using Streamlit.
Challenges we ran into
Health records are protected data that are not easily accessible for research. Therefore, we had to look for public datasets with fewer samples than expected.
Accomplishments that we're proud of
We got the work done on time and got an excellent prediction score. Also, we overcame a creativity slump that we got working on a previous idea by switching to making this one.
What we learned
We learned how to work as a team to distribute different tasks. Also, we learned about medical conditions and their terminology.
What's next for MedCheck
- Algorithm refinement
- Addition of more questionnaires
- UI / UX improvements
Github Repository
Built With
- heroku
- numpy
- pandas
- python
- scikit-learn
- streamlit
Log in or sign up for Devpost to join the conversation.