Gait Rhythm Dynamics for Neuro-Degenerative Disease Classification via Persistence Landscape- Based Topological Representation

Abstract

Neuro-degenerative disease is a common progressive nervous system disorder that leads to serious clinical consequences. Gait rhythm dynamics analysis is essential for evaluating clinical states and improving quality of life for neuro-degenerative patients. The magnitude of stride-to-stride fluctuations and corresponding changes over time—gait dynamics—reflects the physiology of gait, in quantifying the pathologic alterations in the locomotor control system of health subjects and patients with neuro-degenerative diseases. Motivated by algebra topology theory, a topological data analysis-inspired nonlinear framework was adopted in the study of the gait dynamics. Meanwhile, the topological representation–persistence landscapes were used as input of classifiers in order to distinguish different neuro-degenerative disease type from healthy. In this work, stride-to-stride time series from healthy control (HC) subjects are compared with the gait dynamics from patients with amyotrophic lateral sclerosis (ALS), Huntington’s disease (HD), and Parkinson’s disease (PD). The obtained results show that the proposed methodology discriminates healthy subjects from subjects with other neuro-degenerative diseases with relatively high accuracy. In summary, our study is the first attempt to provide a topological representation-based method into the disease classification with gait rhythms measured from the stride intervals to visualize gait dynamics and classify neuro-degenerative diseases. The proposed method could be potentially used in earlier interventions and state monitoring.

A topological data analysis-based method for gait signals with an application to the study of multiple sclerosis

“…Motion capture data has been analyzed using TDA to model bipedal walking [33] or to perform action recognition (classification between dance, jump, run sit and walk) [34]. It has also been used to study degenerative diseases by performing binary classification of time series of gait parameters (stride, stance, and swing time) between healthy and pathological subjects (suffering from either Parkinson's disease, Huntington's disease or Amyotrophic lateral sclerosis) [35,36], multi-class classification of ground reaction force time series to assess the severity of Parkinson's disease [37], or detection of freezing-of-gait episodes [38]. To the best of our knowledge, TDA was mainly used to produce features that were fed to machine learning algorithms (such as SVM, random forest, nearest neighbors or deep neural networks) [25,32,[34][35][36][37][38][39].…”

Computer-aided identification of degenerative neuromuscular diseases based on gait dynamics and ensemble decision tree classifiers

“…Before data preprocessing, the data points corresponding to the first and last 15s were eliminated to reduce artifacts caused by movement start or end, as recommended by the previous work of Hausdorffet al [ 26 , 28 ]. Extreme spike values lead by the end of hallway turn-backs were corrected using a median filter [ 21 , 29 ]. To maximize the number of available training instances, we segmented the 5min signal recordings into multiple 30s windows without overlapping.…”

“…On these grounds, an extensive class of previous studies was directed towards the binary classification of normal vs. pathological conditions [ 16 – 23 ]. Standard procedures extracted features included statistics values [ 16 – 20 ], recurrence quantification analysis parameters [ 17 ], fuzzy recurrence plots [ 18 ], topological motion analysis [ 21 , 22 ], and left/right-foot autocorrelation and cross correlation [ 23 ]. Employed machine learning and deep learning methods included support vector machine (SVM) [ 16 – 18 ], least squares SVM (LS-SVM) [ 18 ], k-nearest neighbors (KNN) [ 16 , 21 ], naive Bayes [ 21 ], random forest (RF) [ 22 ], decision trees [ 23 ], adaptive Neuro-Fuzzy Inference [ 20 ], multi-layer perceptron (MLP) [ 16 ], probabilistic neural network (PNN) [ 17 ], and convolutional neural network (CNN) [ 19 ].…”

Classification of Neurodegenerative Diseases via Topological Motion Analysis—A Comparison Study for Multiple Gait Fluctuations

“…In order to minimize startup effects, the first 20s were excluded. With a median filter, outliers brought by turnarounds at the end of the hallway were replaced with the median value described in [16], [57]. Data normalization may improve pattern recognition and reduce computational time [58], for each time series a Z-score normalization was implemented before further processing [59].…”