研究揭示临床类别不平衡下不确定性量化会系统性误判少数患者
When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance
搞医疗 AI 或可信预测的都该看看：类别不平衡时不确定性分数其实是在报数据稀疏，不是真模糊，论文给了修正方法。
论文研究选择性预测在临床任务中的失效机制：当数据类别严重失衡时，标准不确定性度量不再反映临床模糊性，而是变成类别归属的代理指标。研究在 56 个合成条件以及多发性硬化、帕金森病、阿尔茨海默病三个神经退行性疾病队列上验证了这一结构性偏差。实验显示用标准熵做 CCR 在 tau=0.5 时破坏类内单调性，无法保护少数类患者。结合阈值感知的度量可恢复严格单调性，并保持各类别风险有界且均衡。论文建议临床部署采用阈值对齐的不确定性度量与按类别分层的评估。
When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance
Background. Selective prediction systems improve the safety of clinical artificial intelligence by deferring ambiguous cases to human experts while automating high-confidence decisions. However, this safety mechanism relies entirely on the premise that uncertainty scores accurately reflect clinical ambiguity. In prognostic tasks characterized by severe class imbalance, where the clinical outcome of interest is a minority, this assumption breaks down. Standard uncertainty measures cease to capture clinically aligned ambiguity; instead, they become a proxy for class membership, systematically penalizing minority patients regardless of their individual predictive clarity. Results. Across 56 synthetic conditions and three neurodegenerative cohorts spanning severe class imbalance to near-balanced conditions (multiple sclerosis, Parkinson's Disease, Alzheimer's Disease), our framework consistently maintained bounded, balanced risk across trajectories. In contrast, global metrics either collapsed minority Sensitivity or protected the minority at the expense of majority patients. Applying CCR with standard entropy fails to protect the minority because it breaks within-class monotonicity when tau=0.5. Combining CCR with threshold-aware metrics restores strict monotonicity, correctly identifies ambiguous patients, and safely mitigates minority exclusion. Conclusions. Under clinical class imbalance, standard uncertainty quantification measures dataset sparsity rather than clinical ambiguity, creating a systemic illusion of safety. This bias is a correctable structural flaw. Clinical pipelines deploying selective prediction under imbalance should adopt threshold-aligned uncertainty measures and class-stratified evaluation. This reduces class-specific risk imbalance, supporting safer selective prediction under the evaluated conditions without silently excluding the most vulnerable patients.