Hacker News Reader

Comment by blueblisters | Hacker News Reader

This is an interesting perspective. Since you're an eye surgeon, this might be a relevant question.

What do you think of the relative success of Diabetic Retinopathy (DR) diagnostic models, especially the FDA approval of the clinical trials Digital Diagnostics (formerly IDxDR) [1]? Their approach to the model architecture was slightly different from the black-box approach of other labs, wherein IDxDR's model is trained to look for clinically relevant indicators for DR. Is that a more likely route for future diagnostic AI models?

[1]: https://dxs.ai/newsroom/pivotal-trial-results-behind-the-fda...

View on HN

Not OP, but anesthesiologist and hobby programmer for 15 years. What you are describing is a fundamental flaw of the current AI effort: the data that supports AI models is mostly irrelevant to the problem. In medicine, the saying goes: 90% of diagnoses are made on patient history. Ironically, there is no reason that would change for AI-enabled systems given the same information.

So to answer you directly yes, it's a better route until we have better information available. But it's also the wrong route to take in the long term. It would be far better to attempt to produce better supporting information.

Honestly, I don't know what to think. Ophthalmology is a great field for AI researchers (lots of images: the eye is an organ that you can photograph and analyze visually in every angles, almost like in dermatology). In Ophthalmology, diabetic retinopathy is an evident take : lots of people involved, lots of annotated pictures available, screening programs.

However, I would like to see the performances of the algorithm on different fundus camera. It is also important to realize that diabetic retinopathy classification is very easy to learn, to the point that if the screening is such a problem, it is easier to ask the person that takes the pictures (In France, a nurse or an orthoptist) to phone the doctor when he/she sees something strange on the eye fundus.

Do you happen to know of a dataset that contains a fundus picture of the back of the eye plus a regular high-res photo of the full eye?

Also https://www.eyenuk.com/us-en/products/eyeart/

Reply on news.ycombinator.com