[论文解读] A pilot study of the Earable device to measure facial muscle and eye movement tasks among healthy volunteers

Matthew F. Wipperman, Galen Pogoncheff+10 more|arXiv (Cornell University)|Feb 1, 2022

Facial Nerve Paralysis Treatment and Research参考文献 43被引用 5

一句话总结

本初步研究评估了可穿戴设备Earable在健康志愿者中通过肌电图（EMG）、眼电图（EOG）和脑电图（EEG）信号对面部和眼动进行客观、定量测量的性能。结果表明，利用这些信号的汇总特征可准确分类模拟的绩效结果（mock-PerfO）任务——在说话、咀嚼和吞咽任务中F1分数均超过0.9，优于卷积神经网络（CNN）模型，其中EMG和EOG特征在分类中起关键作用。

ABSTRACT

Many neuromuscular disorders impair function of cranial nerve enervated muscles. Clinical assessment of cranial muscle function has several limitations. Clinician rating of symptoms suffers from inter-rater variation, qualitative or semi-quantitative scoring, and limited ability to capture infrequent or fluctuating symptoms. Patient-reported outcomes are limited by recall bias and poor precision. Current tools to measure orofacial and oculomotor function are cumbersome, difficult to implement, and non-portable. Here, we show how Earable, a wearable device, can discriminate certain cranial muscle activities such as chewing, talking, and swallowing. We demonstrate using data from a pilot study of 10 healthy participants how Earable can be used to measure features from EMG, EEG, and EOG waveforms from subjects performing mock Performance Outcome Assessments (mock-PerfOs), utilized widely in clinical research. Our analysis pipeline provides a framework for how to computationally process and statistically rank features from the Earable device. Finally, we demonstrate that Earable data may be used to classify these activities. Our results, conducted in a pilot study of healthy participants, enable a more comprehensive strategy for the design, development, and analysis of wearable sensor data for investigating clinical populations. Additionally, the results from this study support further evaluation of Earable or similar devices as tools to objectively measure cranial muscle activity in the context of a clinical research setting. Future work will be conducted in clinical disease populations, with a focus on detecting disease signatures, as well as monitoring intra-subject treatment responses. Readily available quantitative metrics from wearable sensor devices like Earable support strategies for the development of novel digital endpoints, a hallmark goal of clinical research.

研究动机与目标

• 评估Earable是否能从EMG、EOG和EEG信号中提取并处理与受控面部和眼动任务相关的有意义特征。
• 评估Earable衍生特征的重测信度和数据质量。
• 确定Earable特征是否能够区分不同类型的模拟绩效结果（mock-PerfO）活动。
• 识别在分类颅神经肌肉和眼动任务时最具信息量的特征类型。

提出的方法

• 从Earable设备在16项模拟绩效结果（mock-PerfO）任务期间采集的原始EMG、EOG和EEG波形中提取了161个汇总特征。
• 使用特征向量训练机器学习模型进行活动分类，性能在保留的测试集上进行评估。
• 训练了一个卷积神经网络（CNN），使用低层次的原始波形表示，以与基于特征的模型进行分类性能比较。
• 应用方差成分分析以评估测试-重测信度及早、晚两次会话中受试者内部的一致性。
• 计算Spearman等级相关系数和组内相关系数（ICC）以评估特征的稳定性和可重复性。
• 对特征进行统计排序，以识别对任务身份最具预测力的特征。

实验结果

研究问题

• RQ1 Earable能否可靠地从健康个体的受控面部和眼动中提取并处理EMG、EOG和EEG特征？
• RQ2 Earable特征在重复测量（测试-重测）及不同时间段之间的一致性如何？
• RQ3 基于Earable特征训练的机器学习模型能否以高准确率区分不同类型的模拟绩效结果（mock-PerfO）任务？
• RQ4 哪些类型的特征（EMG、EOG、EEG或派生统计量）在分类特定任务时最具信息量？
• RQ5 基于汇总特征的模型是否在任务分类上优于使用原始波形数据的深度学习模型？

主要发现

• Earable利用汇总特征对说话、咀嚼和吞咽任务的分类F1分数均超过0.9，表明其具有出色的判别性能。
• EMG特征对所有任务的分类均至关重要，而EOG特征在分类与视线相关的活动时尤为重要。
• 基于特征的分类模型在模拟绩效结果（mock-PerfO）任务分类中优于CNN模型，表明在此情境下，工程化特征比原始波形表示更有效。
• 方差成分分析显示，特征在受试者和时间点之间具有良好的一致性，ICC值表明测试-重测信度良好。
• 本研究识别出一组经统计排序的最具预测力的特征，为未来数字终点的开发提供了框架。
• 结果支持Earable作为客观、便携且可重复评估神经肌肉疾病中颅神经相关功能的工具的潜力。