Offline reinforcement learning (RL) offers considerable promise for optimizing ICU treatment decisions, yet standard evaluation metrics Mean Squared Error (MSE) and Fitted Q-Evaluation (FQE) assess only behavioral imitation and cannot detect Toxic Mimicry, a failure mode in which agents replicate harmful patterns such...
Results show that separating broad evidence discovery from narrow evidence-admissible assessment improves longitudinal clinical verification and reduces unsupported conclusions.
Xin Lin, Yu-Bo Feng, Wei-Xin Liu et al.· 0 citations
CRS-Bench provides a controlled framework for selecting medical image encoders from multi-axis reliability profiles rather than clean-test AUROC alone, and summarizes these dimensions using the Clinical Reliability Score (CRS), a Pareto-aware, reference-relative score combining dominance, profile balance, and worst-axi...
Xingtao Lin, Hangqi Ren, Caiwan Sun et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.