Correct me if I’m wrong, but right now it’s not *if* we can detect many diseases with AI tools, it’s that they often *over* diagnose and there are many false positives in their testing.
Edit: Please someone with the time check me on this as it may be a dated comment to make with all the sudden AI/ML changes.
v4ss42 on
I would imagine that a better benchmark is whether they outperform human pathologists, not existing models.
BuildwithVignesh on
If it really holds up in wider trials, that’s a huge step for early cancer detection. AI in diagnostics is moving faster than anyone expected.
Leave A Reply
Du musst angemeldet sein, um einen Kommentar abzugeben.
3 Kommentare
Correct me if I’m wrong, but right now it’s not *if* we can detect many diseases with AI tools, it’s that they often *over* diagnose and there are many false positives in their testing.
Edit: Please someone with the time check me on this as it may be a dated comment to make with all the sudden AI/ML changes.
I would imagine that a better benchmark is whether they outperform human pathologists, not existing models.
If it really holds up in wider trials, that’s a huge step for early cancer detection. AI in diagnostics is moving faster than anyone expected.