I wanted to make something that could help doctors, medical groups and health insurance companies scan their documents (images, files) and detected their members' protected health information and then scrub it out on device. This would help them avoid leaking protected data accidentally and help them not have to manually scrub this data out before it's safe to post on the network. Leaks of this kind of data can be costly per HIPAA.
I used Computer Vision to scan an image for text, then classified if it was one of the nearly 20 forms of protected health data, then scrubbed it out on device by drawing a box over it if it was. It's not 100% accurate but showed good results - I also added the ability to tap on the image and manually scrub an area, as well as remove any incorrect classifications. Figured I'd post for more feedback - what a fun event, and it was so great to talk to aspiring and past YC alumni and partners!
