Geed Shashwati, Grainger Megan L, Mitchell Abigail, Anderson Cassidy C, Schmaulfuss Henrike L, Culp Seraphina A, McCormick Eilis R, McGarry Maureen R, Delgado Mystee N, Noccioli Allysa D, Shelepov Julia, Dromerick Alexander W, Lum Peter S
Department of Rehabilitation Medicine, Georgetown University, Washington, DC, United States.
MedStar National Rehabilitation Hospital, Washington, DC, United States.
Front Physiol. 2023 Mar 22;14:1116878. doi: 10.3389/fphys.2023.1116878. eCollection 2023.
This study aims to investigate the validity of machine learning-derived amount of real-world functional upper extremity (UE) use in individuals with stroke. We hypothesized that machine learning classification of wrist-worn accelerometry will be as accurate as frame-by-frame video labeling (ground truth). A second objective was to validate the machine learning classification against measures of impairment, function, dexterity, and self-reported UE use. Cross-sectional and convenience sampling. Outpatient rehabilitation. Individuals (>18 years) with neuroimaging-confirmed ischemic or hemorrhagic stroke >6-months prior ( = 31) with persistent impairment of the hemiparetic arm and upper extremity Fugl-Meyer (UEFM) score = 12-57. Participants wore an accelerometer on each arm and were video recorded while completing an "activity script" comprising activities and instrumental activities of daily living in a simulated apartment in outpatient rehabilitation. The video was annotated to determine the ground-truth amount of functional UE use. The amount of real-world UE use was estimated using a random forest classifier trained on the accelerometry data. UE motor function was measured with the Action Research Arm Test (ARAT), UEFM, and nine-hole peg test (9HPT). The amount of real-world UE use was measured using the Motor Activity Log (MAL). The machine learning estimated use ratio was significantly correlated with the use ratio derived from video annotation, ARAT, UEFM, 9HPT, and to a lesser extent, MAL. Bland-Altman plots showed excellent agreement between use ratios calculated from video-annotated and machine-learning classification. Factor analysis showed that machine learning use ratios capture the same construct as ARAT, UEFM, 9HPT, and MAL and explain 83% of the variance in UE motor performance. Our machine learning approach provides a valid measure of functional UE use. The accuracy, validity, and small footprint of this machine learning approach makes it feasible for measurement of UE recovery in stroke rehabilitation trials.
本研究旨在探讨机器学习得出的现实世界中中风患者功能性上肢（UE）使用量的有效性。我们假设，基于腕部佩戴式加速度计的机器学习分类将与逐帧视频标注（真实情况）一样准确。第二个目标是对照损伤、功能、灵巧性和自我报告的UE使用量测量指标，验证机器学习分类的准确性。采用横断面和便利抽样。在门诊康复环境中进行研究。纳入年龄大于18岁、神经影像学确诊为缺血性或出血性中风且中风时间超过6个月（n = 31）、偏瘫上肢持续存在功能障碍且上肢Fugl-Meyer（UEFM）评分为12 - 57分的个体。参与者双臂均佩戴加速度计，并在门诊康复的模拟公寓中完成包含日常生活活动和工具性活动的“活动脚本”时进行视频记录。对视频进行标注以确定功能性UE使用的真实情况量。使用基于加速度计数据训练的随机森林分类器估计现实世界中UE的使用量。采用动作研究臂测试（ARAT）、UEFM和九孔插板测试（9HPT）测量UE运动功能。使用运动活动日志（MAL）测量现实世界中UE的使用量。机器学习估计的使用比例与视频标注、ARAT、UEFM、9HPT得出的使用比例显著相关，与MAL得出的使用比例相关性稍弱。Bland-Altman图显示，视频标注计算得出的使用比例与机器学习分类计算得出的使用比例之间具有良好的一致性。因子分析表明，机器学习使用比例与ARAT、UEFM、9HPT和MAL捕捉相同的结构，并且解释了UE运动表现中83%的方差。我们的机器学习方法为功能性UE使用提供了一种有效的测量方法。这种机器学习方法的准确性、有效性和较小的占用空间使其在中风康复试验中测量UE恢复情况时具有可行性。
