AI 中文总结
研究针对运动障碍评估中多传感模式整合不足问题，通过同步记录脑电-惯性测量单元数据，评估特定任务模态性能和多模态融合。结果表明脑电和惯性测量单元各有优势，后期融合可利用互补性提高评估可靠性，为大规模临床验证提供依据。
AI 中文摘要
帕金森病等运动障碍需要全面的运动评估，但整合多种传感模式以进行各种运动任务的可靠数字评估流程仍未得到充分表征。我们进行了一项概念验证研究，评估了十种运动活动中特定任务的模态性能和多模态融合。从六名参与者处记录了同步的脑电-惯性测量单元数据（52个记录对）。我们评估了用于16通道脑电（125Hz）的EEGNet+Transformer模型以及基于手工制作的加速度计和陀螺仪特征（25Hz）的XGBoost模型。在基于受试者的5折交叉验证设置下，惯性测量单元的准确率达到94.41±0.58%，在10项活动中的7项上优于脑电，而脑电的准确率为92.82±1.45%，在节律性骑行中误差更低（分别为4.03%和12.10%）。通过逻辑回归的后期融合达到了98.68±0.32%，与单独使用脑电相比误差降低了81.5%，并将最差任务的准确率从单一模态的约87%提高到96.76%。融合还将跨任务性能方差从约3%降低到1.06%（配对t检验，p<0.001，自由度=4；p值因折叠依赖性而近似），表明在整个评估组中可靠性更均匀。尽管样本量小限制了可推广性，但这些结果表明脑电和惯性测量单元提供了不对称的、任务相关的优势，后期融合可以利用这种互补性来提高评估可靠性。本研究为运动障碍人群的大规模临床验证提供了方法和实证依据。
英文摘要
Movement disorders such as Parkinson's disease require comprehensive motor assessment, but reliable digital assessment pipelines integrating multiple sensing modalities across diverse motor tasks remain insufficiently characterized. We present a proof-of-concept study evaluating task-specific modality performance and multimodal fusion across ten motor activities. Synchronized EEG-IMU data were recorded from six participants (52 recording pairs). We evaluated an EEGNet + Transformer model for 16-channel EEG (125 Hz) and XGBoost on hand-crafted accelerometer and gyroscope features (25 Hz). Under 5-fold cross-validation in a subject-dependent setting, IMU achieved 94.41+/-0.58% accuracy and outperformed EEG on 7 of 10 activities, while EEG achieved 92.82+/-1.45% and showed lower error for rhythmic cycling (4.03% vs. 12.10%). Late fusion via logistic regression reached 98.68+/-0.32%, giving an 81.5% error reduction versus EEG alone and improving worst-task accuracy from approximately 87% for a single modality to 96.76%. Fusion also reduced cross-task performance variance from approximately 3% to 1.06% (paired t-test, p < 0.001, df = 4; p-values approximate given fold dependence), showing more uniform reliability across the assessment battery. Although the small sample limits generalizability, these results suggest that EEG and IMU provide asymmetric, task-dependent strengths and that late fusion can leverage this complementarity to improve assessment reliability. This study provides methodological and empirical motivation for larger-scale clinical validation in movement disorder populations.
