Department of Neurology, University Medical Center Groningen, University of Groningen, 9713 GZ Groningen, The Netherlands.
Department of Paediatrics, Beatrix Children's Hospital, University Medical Center Groningen, University of Groningen, 9713 GZ Groningen, The Netherlands.
Sensors (Basel). 2023 Oct 12;23(20):8410. doi: 10.3390/s23208410.
Early onset ataxia (EOA) and developmental coordination disorder (DCD) both affect cerebellar functioning in children, making the clinical distinction challenging. We here aim to derive meaningful features from quantitative SARA-gait data (i.e., the gait test of the scale for the assessment and rating of ataxia (SARA)) to classify EOA and DCD patients and typically developing (CTRL) children with better explainability than previous classification approaches. We collected data from 18 EOA, 14 DCD and 29 CTRL children, while executing both SARA gait tests. Inertial measurement units were used to acquire movement data, and a gait model was employed to derive meaningful features. We used a random forest classifier on 36 extracted features, leave-one-out-cross-validation and a synthetic oversampling technique to distinguish between the three groups. Classification accuracy, probabilities of classification and feature relevance were obtained. The mean classification accuracy was 62.9% for EOA, 85.5% for DCD and 94.5% for CTRL participants. Overall, the random forest algorithm correctly classified 82.0% of the participants, which was slightly better than clinical assessment (73.0%). The classification resulted in a mean precision of 0.78, mean recall of 0.70 and mean F1 score of 0.74. The most relevant features were related to the range of the hip flexion-extension angle for gait, and to movement variability for tandem gait. Our results suggest that classification, employing features representing different aspects of movement during gait and tandem gait, may provide an insightful tool for the differential diagnoses of EOA, DCD and typically developing children.
早发性共济失调（EOA）和发育性协调障碍（DCD）都会影响儿童的小脑功能，这使得临床区分具有挑战性。我们旨在从定量 SARA 步态数据（即共济失调评估和评定量表（SARA）的步态测试）中提取有意义的特征，以便比以前的分类方法更好地对 EOA、DCD 和典型发育（CTRL）儿童进行分类和解释。我们收集了 18 名 EOA、14 名 DCD 和 29 名 CTRL 儿童的数据，同时执行了 SARA 步态测试。惯性测量单元用于获取运动数据，并采用步态模型来提取有意义的特征。我们在 36 个提取的特征上使用随机森林分类器、留一法交叉验证和合成过采样技术来区分这三组。获取了分类准确性、分类概率和特征相关性。EOA 的平均分类准确率为 62.9%，DCD 为 85.5%，CTRL 参与者为 94.5%。总体而言，随机森林算法正确分类了 82.0%的参与者，略高于临床评估（73.0%）。分类结果的平均精度为 0.78，平均召回率为 0.70，平均 F1 评分为 0.74。最相关的特征与步态和串联步态中髋关节屈伸角度的范围以及运动可变性有关。我们的研究结果表明，分类方法采用代表步态和串联步态中运动不同方面的特征，可能为 EOA、DCD 和典型发育儿童的鉴别诊断提供一种有价值的工具。
