Jeter Russell, Greenfield Raymond, Housley Stephen N, Belykh Igor
Department of Mathematics and Statistics, Georgia State University, Atlanta, GA, United States.
Motus Nova, LLC, Atlanta, GA, United States.
JMIR Biomed Eng. 2024 Oct 7;9:e56980. doi: 10.2196/56980.
Stroke therapy is essential to reduce impairments and improve motor movements by engaging autogenous neuroplasticity. Traditionally, stroke rehabilitation occurs in inpatient and outpatient rehabilitation facilities. However, recent literature increasingly explores moving the recovery process into the home and integrating technology-based interventions. This study advances this goal by promoting in-home, autonomous recovery for patients who experienced a stroke through robotics-assisted rehabilitation and classifying stroke residual severity using machine learning methods.
Our main objective is to use kinematics data collected during in-home, self-guided therapy sessions to develop supervised machine learning methods, to address a clinician's autonomous classification of stroke residual severity-labeled data toward improving in-home, robotics-assisted stroke rehabilitation.
In total, 33 patients who experienced a stroke participated in in-home therapy sessions using Motus Nova robotics rehabilitation technology to capture upper and lower body motion. During each therapy session, the Motus Hand and Motus Foot devices collected movement data, assistance data, and activity-specific data. We then synthesized, processed, and summarized these data. Next, the therapy session data were paired with clinician-informed, discrete stroke residual severity labels: "no range of motion (ROM)," "low ROM," and "high ROM." Afterward, an 80%:20% split was performed to divide the dataset into a training set and a holdout test set. We used 4 machine learning algorithms to classify stroke residual severity: light gradient boosting (LGB), extra trees classifier, deep feed-forward neural network, and classical logistic regression. We selected models based on 10-fold cross-validation and measured their performance on a holdout test dataset using F-score to identify which model maximizes stroke residual severity classification accuracy.
We demonstrated that the LGB method provides the most reliable autonomous detection of stroke severity. The trained model is a consensus model that consists of 139 decision trees with up to 115 leaves each. This LGB model boasts a 96.70% F-score compared to logistic regression (55.82%), extra trees classifier (94.81%), and deep feed-forward neural network (70.11%).
We showed how objectively measured rehabilitation training paired with machine learning methods can be used to identify the residual stroke severity class, with efforts to enhance in-home self-guided, individualized stroke rehabilitation. The model we trained relies only on session summary statistics, meaning it can potentially be integrated into similar settings for real-time classification, such as outpatient rehabilitation facilities.
中风治疗对于通过激发自身神经可塑性来减少损伤和改善运动功能至关重要。传统上，中风康复在住院和门诊康复机构进行。然而，最近的文献越来越多地探索将康复过程转移到家庭中，并整合基于技术的干预措施。本研究通过机器人辅助康复促进中风患者在家中自主康复，并使用机器学习方法对中风残留严重程度进行分类，从而推进了这一目标。
我们的主要目标是利用在家中自我指导治疗期间收集的运动学数据来开发监督机器学习方法，以解决临床医生对中风残留严重程度标记数据的自主分类问题，从而改善在家中进行的机器人辅助中风康复。
共有33名中风患者参加了使用Motus Nova机器人康复技术的家庭治疗课程，以捕捉上半身和下半身的运动。在每次治疗课程中，Motus Hand和Motus Foot设备收集运动数据、辅助数据和特定活动数据。然后我们对这些数据进行了合成、处理和汇总。接下来，将治疗课程数据与临床医生告知的离散中风残留严重程度标签配对：“无活动范围（ROM）”、“低ROM”和“高ROM”。之后，进行80%:20%的划分，将数据集分为训练集和保留测试集。我们使用4种机器学习算法对中风残留严重程度进行分类：轻梯度提升（LGB）、极端随机树分类器、深度前馈神经网络和经典逻辑回归。我们基于10折交叉验证选择模型，并使用F分数在保留测试数据集上测量它们的性能，以确定哪种模型能最大化中风残留严重程度分类的准确性。
我们证明LGB方法提供了最可靠的中风严重程度自主检测。训练后的模型是一个共识模型，由139个决策树组成，每个决策树最多有115个叶子节点。与逻辑回归（55.82%）、极端随机树分类器（94.81%）和深度前馈神经网络（70.11%）相比，这个LGB模型的F分数为96.70%。
我们展示了如何将客观测量的康复训练与机器学习方法相结合，以识别中风残留严重程度类别，努力加强在家中自我指导的个性化中风康复。我们训练的模型仅依赖于课程汇总统计数据，这意味着它有可能被整合到类似的实时分类环境中，如门诊康复机构。
