arXiv cs.AI· Walter Endrizzi, Flavio Ragni, Raffaele Marchesi, Stefano Bovo, Monica Moroni, Giuseppe Jurman, Venet Osmani·· 4 小时前AI 评分45
临床类别不平衡下选择性预测失效的结构性漏洞与修正研究
When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance
AI 导读
临床 AI 选择性预测在严重类别不平衡下会失效：标准不确定性度量退化为类别的代理指标，系统性地惩罚少数类患者，而非反映真实的临床模糊性。研究者在 56 个合成条件和三个神经退行性疾病队列（多发性硬化、帕金森病、阿尔茨海默病）上验证了这一问题，并发现结合阈值感知度量与 CCR 可恢复单调性，避免少数类被排除。论文建议在类别不平衡场景下采用阈值对齐的不确定性度量和按类分层的评估。
正文 · 原文
Abstract: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.
| Comments: | this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37561 [cs.LG] |
| (or arXiv:2610.37561v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37561 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Venet Osmani [view email]
[v1]
Tue, 27 Oct 2026 17:08:31 UTC (442 KB)
来源：arXiv cs.AI · arxiv.org