←back to thread

Show HN: I'm a dermatologist and I vibe coded a skin cancer learning app

(molecheck.info)
422 points sungam | 2 comments | 07 Sep 25 10:38 UTC | HN request time: 0.48s | source

Coded using Gemini Pro 2.5 (free version) in about 2-3 hours.

Single file including all html/js/css, Vanilla JS, no backend, scores persisted with localStorage.

Deployed using ubuntu/apache2/python/flask on a £5 Digital Ocean server (but could have been hosted on a static hosting provider as it's just a single page with no backend).

Images / metadata stored in an AWS S3 bucket.

Show context
derbOac ◴[07 Sep 25 22:51 UTC] No.45162922[source]▶
Cool but it seems like it would get more difficult with more non-cancerous but medically concerning lesions (eg due to infectious disease).
replies(1): >>45163442 #
1. sungam ◴[08 Sep 25 00:04 UTC] No.45163442[source]▶
This is true - there are more than 2000 different conditions in dermatology but the most important ones to recognise are skin cancers
replies(1): >>45167026 #
2. derbOac ◴[08 Sep 25 11:33 UTC] No.45167026[source]▶
My concern (?) is the task is unrealistically easy without more varieties of lesions to distinguish from cancer.