依赖评估器的患者自适应心电图导联-通道分配
Evaluator-Dependent Patient-Adaptive ECG Lead-Channel Allocation
浏览论文内容
中文总结 AI 辅助
该研究在PTB-XL数据集上证实,自适应心电图通道分配策略的性能依赖于所用诊断评估器,联合优化感知与诊断系统仍是未解决的问题。
中文摘要 AI 辅助
针对心电图(ECG)导联-通道选择的患者条件采集策略,通过为每位患者的观测心脏状态定制通道预算,性能可优于全人群固定协议。然而,任意给定通道的采集价值是相对于下游诊断评估器定义的,因此在某一评估器下学习到的边际效用,在更换评估器时未必能迁移。我们在PTB-XL数据集上对这种评估器依赖性开展实证研究:冻结两个在受控任意掩码逻辑评估器下训练的策略(ECG-on-Demand和MGA),再用预测性更强的掩码原始波形ResNet1D对其未改变的采集轨迹打分。我们为每个评估器分别提供了穷尽搜索得到的、与指标匹配的全人群固定对照,以实现清晰的交互对比。在保留的验证折中,当预算k=4时,ECG-on-Demand从D_C=-0.011(在受控评估器下偏向自适应)变为D_S=+0.029(在强评估器下偏向固定),产生的负对数似然(NLL)交互值为+0.041(95%置信区间[+0.030, +0.050])。在两个策略、五个预算和三个概率指标下,全部30个交互估计值均为正,配对置信区间不包含零。三项事后敏感性分析——共同参考打分、用策略生成掩码与随机掩码的混合训练强评估器、以及评估器对齐的Strong-MGA策略训练——均保留了正的交互区间,使得参考选择和掩码分布的人为因素难以成为合理解释。评估器对齐训练缩小了但未消除该差距。这些结果表明,自适应ECG通道分配应与其预期的诊断主干联合开发和验证,而联合优化的感知-诊断系统仍是一个未解决的问题。
英文摘要
The diagnostic value of an ECG channel depends on the model that interprets it. We test whether adaptive acquisition retains its advantage over fixed protocols when that model changes. Two policies developed with a logistic evaluator are frozen and assessed with a masked waveform ResNet1D, using exhaustive, metric-matched fixed comparators. On PTB-XL, replacing the evaluator reverses the mean adaptive advantage in negative log-likelihood and Brier score across the tested budgets, while calibration responds less uniformly. The shift persists with common fixed references and broader training-mask exposure. Training a policy against the stronger evaluator partly recovers the lost advantage. These retrospective exploratory results show that acquisition quality cannot be assessed independently of the downstream evaluator and motivate validating adaptive policies with the model intended for diagnosis.