Thread

1. plaidfuji · 1789828169 · focus · HN ↗

   It is 2026. How are we still publishing articles on medical diagnostics data science and using area under the ROC curve as the primary metric of success. ROC-AUC of 0.9 under severe class imbalance (almost always the case in diagnostics) could still mean something like 4/5 predicted diagnoses are wrong (false positives). Precision-Recall curve + mAP or GTFO.

   Science article in question: <a href="https:&#x2F;&#x2F;www.science.org&#x2F;doi&#x2F;abs&#x2F;10.1126&#x2F;science.aec6129" rel="nofollow">https:&#x2F;&#x2F;www.science.org&#x2F;doi&#x2F;abs&#x2F;10.1126&#x2F;science.aec6129

   Also, the most interesting result here is that the CNN-based feature encoder significantly outperformed a vision transformer encoder backbone…

   1. steve-atx-7600 · 1789844793 · focus · HN ↗

      Teaching students how to interpret evidence must be way undervalued still. I went to one of the top CS schools 20 years ago and you could get a degree without even taking a single probability or stats class of any kind.

Unofficial Hacker News client; not affiliated with Y Combinator.