表征还不够：用于阿片类药物使用障碍非接触式压力与渴求感感知的身体局部热证据
Representation Is Not Enough: Body-Localized Thermal Evidence for Contactless Stress and Craving Sensing in Opioid Use Disorder
AI总结：
本研究针对阿片类药物使用障碍的非接触式压力与渴求感感知问题，提出弱监督架构FABLE-Therm，在保留局部证据下实现0.938 AUROC，可迁移至渴求感，还揭示了表征改进不足以实现公平部署的问题。
AI中文摘要：
移除生理监测设备的可穿戴设备也会失去其监督：即指示压力反应发生的位置和时间的信号。因此，非接触式压力感知成为一个弱监督的证据定位问题，其中必须将片段级标签追溯到产生该标签的身体区域和时刻。我们通过FABLE-Therm解决了这个问题，这是一种弱监督架构，可在身体区域、时间和编码器特定表示中保留局部证据，直至最终决策。FABLE-Therm在嵌入级别融合冻结的基础模型编码器，其理论解释了为什么局部融合可以优于特征拼接和预测平均。我们在阿片类药物使用障碍（OUD）中研究此问题，其中压力是主要的复发触发因素，且早期康复期间难以持续使用可穿戴设备。使用固定热视频，FABLE-Therm在保留参与者上实现了0.938的AUROC，其学习到的表征可迁移至自我报告的渴求感，据我们所知，这是首次证明可从非接触式热视频中恢复渴求感。局部证据还支持对部署失败进行参与者级别分析。我们发现，仅改进表征不足以实现公平部署：来自服务不足群体的额外数据仅能恢复约一半的队列差距，而其余部分反映了人与人之间的异质性。这种模态无关的分解适用于具有可识别亚群的模型。结合首个队列结构化的非接触式热OUD基准，我们的结果表明，保留局部证据既支持准确感知，也支持对模型在谁身上失败以及为何失败进行原则性分析。
英文摘要：
Removing wearables from physiological monitoring also removes their supervision: the signal indicating where and when a stress response occurred. Contactless stress sensing therefore becomes a weakly supervised evidence-localization problem, where a clip-level label must be traced to the body regions and moments that produced it. We address this with FABLE-Therm, a weakly supervised architecture that preserves localized evidence across body regions, time, and encoder-specific representations until the final decision. FABLE-Therm fuses frozen foundation-model encoders at the embedding level, with theory explaining why localized fusion can outperform feature concatenation and prediction averaging. We study this problem in opioid use disorder (OUD), where stress is a major relapse trigger and sustained wearable use can be difficult during early recovery. Using fixed thermal video, FABLE-Therm achieves 0.938 AUROC on held-out participants, and its learned representation transfers to self-reported craving, providing, to our knowledge, the first evidence that craving can be recovered from contactless thermal video. Localized evidence also enables participant-level analysis of deployment failure. We find that improving representation alone is insufficient for equitable deployment: additional data from the underserved group would recover only about half of the cohort gap, while the remainder reflects person-to-person heterogeneity. This modality-agnostic decomposition applies to models with identifiable subpopulations. Together with the first cohort-structured contactless thermal OUD benchmark, our results show that preserving localized evidence supports both accurate sensing and principled analysis of who a model fails and why.
