Inspiration A family member of one of our team members has had cancer in the past. The process for detection was long and flawed. It took us over 3 days and hundreds of hours for an accurate detection. What it does OncoAlert leverages advanced machine learning algorithms to analyze medical imaging and patient data for early detection of various types of cancer. By integrating machine learning models with a large dataset of medical images, OncoAlert can identify cancerous patterns that may be missed by the human eye, providing a faster and more accurate diagnosis. Having this as an option for medical facilities can improve many aspects of the diagnosis process, such as time it takes to analyze each image and accessibility. How we built it We used React.js and Node.js for the front end and used Flask servers to connect Python backend files with the frontend. Challenges we ran into inaccurate datasets, slow computer speeds, database size
Accomplishments that we're proud of Gained lots of new skills, learned how to use flask to connect back-end to the front-end, created our first successful ML app using external machine learning libraries.
What we learned We learned how to work in a team, use github as a team and use VScode live-share as a group-working feature. How to download dataset and use them. What's next for OncoAlert Definitely a higher accuracy score , we are planning to expand the range of cancer types detected in our app. Enhance UI and UX. Build strong connections with healthcare services and hospitals.
Log in or sign up for Devpost to join the conversation.