Abstract
The Hereditary Spastic Paraplegias (HSP) are a group of heterogeneous disorders with a wide spectrum of underlying neural pathology, and hence HSP patients express a variety of gait abnormalities. Classification of these phenotypes may help in monitoring disease progression and personalizing therapies. This is currently managed by measuring values of some kinematic and spatio-temporal parameters at certain moments during the gait cycle, either in the doctor´s surgery room or after very precise measurements produced by instrumental gait analysis (IGA). These methods, however, do not provide information about the whole structure of the gait cycle. Classification of the similarities among time series of IGA measured values of sagittal joint positions throughout the whole gait cycle can be achieved by hierarchical clustering analysis based on multivariate dynamic time warping (DTW). Random forests can estimate which are the most important isolated parameters to predict the classification revealed by DTW, since clinicians need to refer to them in their daily practice. We acquired time series of pelvic, hip, knee, ankle and forefoot sagittal angular positions from 26 HSP and 33 healthy children with an optokinetic IGA system. DTW revealed six gait patterns with different degrees of impairment of walking speed, cadence and gait cycle distribution and related with patient’s age, sex, GMFCS stage, concurrence of polyneuropathy and abnormal visual evoked potentials or corpus callosum. The most important parameters to differentiate patterns were mean pelvic tilt and hip flexion at initial contact. Longer time of support, decreased values of hip extension and increased knee flexion at initial contact can differentiate the mildest, near to normal HSP gait phenotype and the normal healthy one. Increased values of knee flexion at initial contact and delayed peak of knee flexion are important factors to distinguish GMFCS stages I from II-III and concurrence of polyneuropathy.
Highlights
The Hereditary Spastic Paraplegias (HSP) are a diverse, heterogeneous and large group of neurodegenerative and neurodevelopmental diseases, of which the main common feature is the retrograde degeneration of the cortico-spinal and posterior column pathways [1,2,3]
The alteration of gait is one of the most frequent clinical signs in HSP patients[1], and it probably results from the combination of a number of factors such as spasticity, hyper-reflexia, hypertonia, loss of strength and loss of selective control[4,5,6], impaired proprioception and vibratory sensitivity[7, 8], additional loss of sensation and strength caused by contingent polyneuropathy[9], ataxias, dystonia, and secondary musculoskeletal disorders[1,2,3]
One of the most useful analytical techniques to compare time series is “Dynamic Time Warping”, (DTW), which has some advantages over singular value decomposition or other linear approaches because it can detect similarities between gait cycles even if those are acquired at different velocities, as commonly occurs after instrumental gait analysis (IGA), and it is independent of non-linear variations in the time dimension [16]
Summary
The Hereditary Spastic Paraplegias (HSP) are a diverse, heterogeneous and large group of neurodegenerative and neurodevelopmental diseases, of which the main common feature is the retrograde degeneration of the cortico-spinal and posterior column pathways [1,2,3]. That can be better achieved by measuring sagittal angular positions of joints over the whole gait cycle time and comparing them as time series in one or multiple patients In this context, Wolf et al.[14] first documented the gait heterogeneity of HSP patients using cluster analysis (k-means) to classify the results of singular value decomposition, a linear method used to pre-process and simplify kinematic gait data[15]. One of the most useful analytical techniques to compare time series is “Dynamic Time Warping”, (DTW), which has some advantages over singular value decomposition or other linear approaches because it can detect similarities between gait cycles even if those are acquired at different velocities, as commonly occurs after IGA, and it is independent of non-linear variations in the time dimension [16] Another attractive feature of DTW time series analysis in IGA interpretation is the analysis of data from the whole gait cycle without a priori selection of gait parameters, avoiding biases from subjective criteria of selection[17], which makes it a reliable tool for classification. In order to combine the advantages of these two methods, we propose the use of “random forests” analysis[18]—a machine learning technique that will enable us to link patterns
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
