发表机构
California State Polytechnic University, Pomona（加州州立理工大学波莫纳分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对PD筛查需标签的问题，提出基于冻结预训练编码器的无标签面部+语音PD筛查方法，引入对齐原则，在YouTubePD基准上实现AUROC 0.802，为PD筛查提供新方案。
AI 中文摘要
帕金森病（PD）是第二常见的神经退行性疾病。典型的机器学习筛查方法需要PD标签，但可用数据受隐私问题和专家标注需求的限制。我们提出一种完全基于冻结预训练编码器的无标签面部+语音PD筛查方法——面部表情Vision Transformer和HuBERT，其中没有PD标签参与任何拟合；仅以健康对照组作为参考。语音模态使用通过健康语音的时间拉伸和气息退化构建的合成构音障碍对比激活加法（CAA）方向；面部模态使用对对照组嵌入簇的k近邻异常分数。我们引入对齐原则，这是一种事后分析，表明当合成与真实疾病方向的余弦相似度超过零时，合成退化CAA检测器有效。在YouTubePD基准上测量，语音的该余弦值为+0.37（CAA有效，AUROC为0.765），面部的为-0.48（CAA失效；异常检测成功，AUROC为0.751）。等权重后期融合达到AUROC 0.802（95%置信区间[0.70,0.89]），阴性预测值（NPV）为0.95，支持排除分诊的解释。过拟合审计显示语音检测器迁移效果良好，而面部侧及因此融合的AUROC在外部验证前可能偏乐观。
英文摘要
Parkinson's disease (PD) is the second most common neurodegenerative disorder. Typical machine learning screening methods require PD labels, but the available data is limited by privacy concerns and the need for expert annotation. We propose a label-free face-plus-voice PD screen built entirely on frozen pretrained encoders--a face-expression Vision Transformer and HuBERT--in which no PD label touches any fit; the reference is training controls only. The voice modality uses a synthetic-dysarthria contrastive activation addition (CAA) direction built from time-stretch and breathy degradation of healthy speech; the face modality uses a k-nearest-neighbor anomaly score to the control embedding cluster. We introduce the alignment principle, a post-hoc analysis showing that a synthetic-degradation CAA detector works when the cosine similarity between the synthetic and real disease directions exceeds zero. Measured on the YouTubePD benchmark, this cosine is +0.37 for voice (CAA works, AUROC 0.765) and -0.48 for face (CAA fails; anomaly succeeds, AUROC 0.751). Equal-weight late fusion reaches AUROC 0.802 (95% CI [0.70,0.89]) with NPV 0.95, supporting a rule-out triage interpretation. An overfitting audit shows the voice detector transfers cleanly, while the face-side--and thus fused--AUROC is potentially optimistic pending external validation.
