Moritz A. Knolle

It is shown that predictions on a patient's unseen future data can change significantly if a model observed that same patient's anonymised historical data during training, a phenomenon known as memorisation bias, which exists across diverse data modalities and model architectures, and over prolonged time spans.

Overconfident predictions in medical imaging segmentation can be corrected with a simple gradient adjustment that enhances model calibration without sacrificing accuracy.