Gait phenotypes in paediatric hereditary spastic paraplegia revealed by dynamic time warping analysis and random forests

Spine kinematics during gait in paediatric Hereditary Spastic Paraparesis

BACKGROUND

Many studies already addressed specific gait abnormalities in children affected by Hereditary Spastic Paraparesis (HSP). Some authors investigated the contribution of the upper body to walking pattern, but simplifying trunk and pelvis as two hinged rigid bodies. Recently, we developed a method to detail spinal kinematics in terms of anatomic curvatures and length; we were thus interested in applying such protocol to HSP.

RESEARCH QUESTION

how HSP influences spinal kinematics during gait?

METHODS

we enrolled ten HSP patients (5-17 years, 8 males) and twelve Healthy Children (HC, 8-16 years, 4 males). Kinematic data were recorded with an optoelectronic system using the LAMB full body marker set, which included three physical markers placed on the spine, supplemented with a virtual one reconstructed on the coccix. Calculations included the spinal length (linear distance from C7 to coccix), the kyphosis and lordosis angles, the trunk tilt and obliquity, the pelvis and the shoulder-pelvis angles, as well as the joint angles of the lower limbs. For each variable, the average value and the range of motion (ROM) were extracted and compared between groups.

RESULTS

the ROM of spinal length, the average value and ROM of kyphosis angle and the average value of trunk tilt significantly increased in HSP vs HC. A pathologic "double bump" pattern characterized the pelvic tilt traces, the lordosis angles and, with opposite sign, the kyphosis. Both the average value and ROM of pelvic tilt significantly increased in HSP, while ROM of lower limb angles was reduced.

CONCLUSION

spine kinematics were altered in HSP, who also showed an anterior trunk tilt. Therefore, the trunk should be considered an articulated system and not simplified to a rigid body, a perspective that could be also used in treating gait abnormalities.

Identification of Subtypes of Post-Stroke and Neurotypical Gait Behaviors Using Neural Network Analysis of Gait Cycle Kinematics

Gait impairment post-stroke is highly heterogeneous. Prior studies classified heterogeneous gait patterns into subgroups using peak kinematics, kinetics, or spatiotemporal variables. A limitation of this approach is the need to select discrete features in the gait cycle. Using continuous gait cycle data, we accounted for differences in magnitude and timing of kinematics. Here, we propose a machine-learning pipeline combining supervised and unsupervised learning. We first trained a Convolutional Neural Network and a Temporal Convolutional Network to extract features that distinguish impaired from neurotypical gait. Then, we used unsupervised time-series k-means and Gaussian Mixture Models to identify gait clusters. We tested our pipeline using kinematic data of 28 neurotypical and 39 individuals post-stroke. We assessed differences between clusters using ANOVA. We identified two neurotypical gait clusters (C1, C2). C1: normative gait pattern. C2: shorter stride time. We observed three post-stroke gait clusters (S1, S2, S3). S1: mild impairment and increased bilateral knee flexion during loading response. S2: moderate impairment, slow speed, short steps, increased knee flexion during stance bilaterally, and reduced paretic knee flexion during swing. S3: mild impairment, asymmetric swing time, increased ankle abduction during the gait cycle, and reduced dorsiflexion bilaterally. Our results indicate that joint kinematics post-stroke are mostly distinct from controls, and highlight kinematic impairments in the non-paretic limb. The post-stroke clusters showed distinct impairments that would require different interventions, providing additional information for clinicians about rehabilitation targets.

Identification of distinct subtypes of post-stroke and neurotypical gait behaviors using neural network analysis of kinematic time series data

Background

Heterogeneous types of gait impairment are common post-stroke. Studies used supervised and unsupervised machine learning on discrete biomechanical features to summarize the gait cycle and identify common patterns of gait behaviors. However, discrete features cannot account for temporal variations that occur during gait. Here, we propose a novel machine-learning pipeline to identify subgroups of gait behaviors post-stroke using kinematic time series data.

Methods

We analyzed ankle and knee kinematic data during treadmill walking data in 39 individuals post-stroke and 28 neurotypical controls. The data were first input into a supervised dual-stage Convolutional Neural Network-Temporal Convolutional Network, trained to extract temporal and spatial gait features. Then, we used these features to find clusters of different gait behaviors using unsupervised time series k-means. We repeated the clustering process using 10,000 bootstrap training data samples and a Gaussian Mixture Model to identify stable clusters representative of our dataset. Finally, we assessed the kinematic differences between the identified clusters using 1D statistical parametric mapping ANOVA. We then compared gait spatiotemporal and clinical characteristics between clusters using one-way ANOVA.

Results

We obtained five clusters: two clusters of neurotypical individuals (C1 and C2) and three clusters of individuals post-stroke (S1, S2, S3). C1 had kinematics that resembled the normative gait pattern. Individuals in C2 had a shorter stride time than C1. Individuals in S1 had mild impairment and walked with increased bilateral knee flexion during the loading response. Individuals in S2 had moderate impairment, were the slowest among the clusters, took shorter steps, had increased knee flexion during stance bilaterally and reduced paretic knee flexion during swing. Individuals in S3 had mild impairment, asymmetric swing time, had increased ankle abduction during the gait cycle and reduced dorsiflexion bilaterally during loading response and stance. Every individual was assigned to a cluster with a cluster membership likelihood above 93%.

Conclusions

Our results indicate that joint kinematics in individuals post-stroke are distinct from controls, even in those individuals with mild impairment. The three subgroups post-stroke showed distinct kinematic impairments during specific phases in the gait cycle, providing additional information to clinicians for gait retraining interventions.

Application of Dynamic Mode Decomposition to Characterize Temporal Evolution of Plantar Pressures from Walkway Sensor Data in Women with Cancer

Pressure sensor-impregnated walkways transform a person's footfalls into spatiotemporal signals that may be sufficiently complex to inform emerging artificial intelligence (AI) applications in healthcare. Key consistencies within these plantar signals show potential to uniquely identify a person, and to distinguish groups with and without neuromotor pathology. Evidence shows that plantar pressure distributions are altered in aging and diabetic peripheral neuropathy, but less is known about pressure dynamics in chemotherapy-induced peripheral neuropathy (CIPN), a condition leading to falls in cancer survivors. Studying pressure dynamics longitudinally as people develop CIPN will require a composite model that can accurately characterize a survivor's gait consistencies before chemotherapy, even in the presence of normal step-to-step variation. In this paper, we present a state-of-the-art data-driven learning technique to identify consistencies in an individual's plantar pressure dynamics. We apply this technique to a database of steps taken by each of 16 women before they begin a new course of neurotoxic chemotherapy for breast or gynecologic cancer. After extracting gait features by decomposing spatiotemporal plantar pressure data into low-rank dynamic modes characterized by three features: frequency, a decay rate, and an initial condition, we employ a machine-learning model to identify consistencies in each survivor's walking pattern using the centroids for each feature. In this sample, our approach is at least 86% accurate for identifying the correct individual using their pressure dynamics, whether using the right or left foot, or data from trials walked at usual or fast speeds. In future work, we suggest that persistent deviation from a survivor's pre-chemotherapy step consistencies could be used to automate the identification of peripheral neuropathy and other chemotherapy side effects that impact mobility.

Gait analysis patterns and rehabilitative interventions to improve gait in persons with hereditary spastic paraplegia: a systematic review and meta-analysis

Background

Hereditary spastic paraplegias (HSPs) are a group of inheritance diseases resulting in gait abnormalities, which may be detected using instrumented gait analysis. The aim of this systematic review was 2-fold: to identify specific gait analysis patterns and interventions improving gait in HSP subjects.

Methods

A systematic review was conducted in PubMed, Cochrane Library, REHABDATA, and PEDro databases, in accordance with reporting guidelines of PRISMA statement and Cochrane's recommendation. The review protocol was recorded on the PROSPERO register. Patients with pure and complicated HSP of any age were included. All types of studies were included. Risk of bias, quality assessment, and meta-analysis were performed.

Results

Forty-two studies were included: 19 were related to gait analysis patterns, and 24 were intervention studies. The latter ones were limited to adults. HSP gait patterns were similar to cerebral palsy in younger subjects and stroke in adults. Knee hyperextension, reduced range of motion at knee, ankle, and hip, reduced foot lift, and increased rapid trunk and arm movements were reported. Botulinum injections reduced spasticity but uncovered weakness and improved gait velocity at follow-up. Weak evidence supported intrathecal baclofen, active intensive physical therapy (i.e., robot-assisted gait training, functional exercises, and hydrotherapy), and functional electrical stimulation. Some improvements but adverse events were reported after transcranial magnetic stimulation, transcutaneous spinal direct current stimulation, and spinal cord stimulation implant.

Conclusion

Knee hyperextension, non-sagittal pelvic movements, and reduced ROM at the knee, ankle, and hip represent the most peculiar patterns in HSP, compared to diplegic cerebral palsy and stroke. Botulinum improved comfortable gait velocity after 2 months. Nonetheless, interventions reducing spasticity might result in ineffective functional outcomes unveiling weakness. Intensive active physical therapy and FES might improve gait velocity in the very short term.

Semi-supervised clustering of quaternion time series: Application to gait analysis in multiple sclerosis using motion sensor data

Recent approaches in gait analysis involve the use of wearable motion sensors to extract spatio-temporal parameters that characterize multiple aspects of an individual's gait. In particular, the medical community could largely benefit from this type of devices as they could provide the clinicians with a valuable tool for assessing gait impairment. Motion sensor data are however complex and there is an urgent unmet need to develop sound statistical methods for analyzing such data and extracting clinically relevant information. In this article, we measure gait by following the hip rotation over time and the resulting statistical unit is a time series of unit quaternions. We explore the possibility to form groups of patients with similar walking impairment by taking into account their walking data and their global decease severity with semi-supervised clustering. We generalize a compromise-based method named hclustcompro to unit quaternion time series by combining it with the proper dissimilarity quaternion dynamic time warping. We apply this method on patients diagnosed with multiple sclerosis to form groups of patients with similar walking deficiencies while accounting for the clinical assessment of their overall disability. We also compare the compromise-based clustering approach with the method mergeTrees that falls into a sub-class of ensemble clustering named collaborative clustering. The results provide a first proof of both the interest of using wearable motion sensors for assessing gait impairment and the use of prior knowledge to guide the clustering process. It also demonstrates that compromise-based clustering is a more appropriate approach in this context.

Normalization and possibility of classification analysis using the optimal warping paths of dynamic time warping in gait analysis

The purpose of this study was to verify classification performance and the difference analysis between gender using optimal warping paths of dynamic time warping (DTW) and to examine the usefulness of root mean square error (RMSE) represented by the perpendicular distance from the optimal warping path to the diagonal. A 3-dimensional motion analysis experiment was performed with 24 healthy adults (male=12, female=12) in their 20s of age without gait-related diseases or injuries for the past 6 months to collect gait data. This study performed a DTW 132 times in total (male=62, female=62) for the flexion angle of the right leg's hip, knee, and ankle joints. Then, the global cost and the RMSE of the optimal warping paths were calculated and normalized. The difference analysis was performed by independent t-test. Machine learning was performed to test the classification performance using the neural network, support vector machine, and logistic regression model among the supervised models. Results analyzed using global cost and RMSE for hip, knee, and ankle joints showed a statistically significant difference between genders in global cost and RMSE for hip and knee joints but not for ankle joints using RMSE. Considering both area under the receiver operating characteristic curve and F1-score, the logistic regression model has been evaluated as the most suitable for gender classification using the global cost or RMSE. This study demonstrated that optimal warping paths could be used for statistical difference analysis and classification analysis.

Computer Vision and Machine Learning-Based Gait Pattern Recognition for Flat Fall Prediction

BACKGROUND

Gait recognition has been applied in the prediction of the probability of elderly flat ground fall, functional evaluation during rehabilitation, and the training of patients with lower extremity motor dysfunction. Gait distinguishing between seemingly similar kinematic patterns associated with different pathological entities is a challenge for the clinician. How to realize automatic identification and judgment of abnormal gait is a significant challenge in clinical practice. The long-term goal of our study is to develop a gait recognition computer vision system using artificial intelligence (AI) and machine learning (ML) computing. This study aims to find an optimal ML algorithm using computer vision techniques and measure variables from lower limbs to classify gait patterns in healthy people. The purpose of this study is to determine the feasibility of computer vision and machine learning (ML) computing in discriminating different gait patterns associated with flat-ground falls.

METHODS

We used the Kinect® Motion system to capture the spatiotemporal gait data from seven healthy subjects in three walking trials, including normal gait, pelvic-obliquity-gait, and knee-hyperextension-gait walking. Four different classification methods including convolutional neural network (CNN), support vector machine (SVM), K-nearest neighbors (KNN), and long short-term memory (LSTM) neural networks were used to automatically classify three gait patterns. Overall, 750 sets of data were collected, and the dataset was divided into 80% for algorithm training and 20% for evaluation.

RESULTS

The SVM and KNN had a higher accuracy than CNN and LSTM. The SVM (94.9 ± 3.36%) had the highest accuracy in the classification of gait patterns, followed by KNN (94.0 ± 4.22%). The accuracy of CNN was 87.6 ± 7.50% and that of LSTM 83.6 ± 5.35%.

CONCLUSIONS

This study revealed that the proposed AI machine learning (ML) techniques can be used to design gait biometric systems and machine vision for gait pattern recognition. Potentially, this method can be used to remotely evaluate elderly patients and help clinicians make decisions regarding disposition, follow-up, and treatment.

Inertial Gait Sensors to Measure Mobility and Functioning in Hereditary Spastic Paraplegia: A Cross-sectional Multicenter Clinical Study

BACKGROUND AND OBJECTIVES

Hereditary spastic paraplegia (HSP) causes progressive spasticity and weakness of the lower limbs. As neurologic examination and the clinical Spastic Paraplegia Rating Scale (SPRS) are subject to potential patient-dependent and clinician-dependent bias, instrumented gait analysis bears the potential to objectively quantify impaired gait. The aim of this study was to investigate gait cyclicity parameters by application of a mobile gait analysis system in a cross-sectional cohort of patients with HSP and a longitudinal fast progressing subcohort.

METHODS

Using wearable sensors attached to the shoes, patients with HSP and controls performed a 4 × 10 m walking test during regular visits in 3 outpatient centers. Patients were also rated according to the SPRS, and in a subset, questionnaires on quality of life and fear of falling were obtained. An unsupervised segmentation algorithm was used to extract stride parameters and respective coefficients of variation.

RESULTS

Mobile gait analysis was performed in a total of 112 ambulatory patients with HSP and 112 age-matched and sex-matched controls. Although swing time was unchanged compared with controls, there were significant increases in the duration of the total stride phase and the duration of the stance phase, both regarding absolute values and coefficients of variation values. Although stride parameters did not correlate with age, weight, or height of the patients, there were significant associations of absolute stride parameters with single SPRS items reflecting impaired mobility (|r| > 0.50), with patients' quality of life (|r| > 0.44), and notably with disease duration (|r| > 0.27). Sensor-derived coefficients of variation, on the other hand, were associated with patient-reported fear of falling (|r| > 0.41) and cognitive impairment (|r| > 0.40). In a small 1-year follow-up analysis of patients with complicated HSP and fast progression, the absolute values of mobile gait parameters had significantly worsened compared with baseline.

DISCUSSION

The presented wearable sensor system provides parameters of stride characteristics which seem clinically valid to reflect gait impairment in HSP. Owing to the feasibility regarding time, space, and costs, this study forms the basis for larger scale longitudinal and interventional studies in HSP.

A Survey of Human Gait-Based Artificial Intelligence Applications

We performed an electronic database search of published works from 2012 to mid-2021 that focus on human gait studies and apply machine learning techniques. We identified six key applications of machine learning using gait data: 1) Gait analysis where analyzing techniques and certain biomechanical analysis factors are improved by utilizing artificial intelligence algorithms, 2) Health and Wellness, with applications in gait monitoring for abnormal gait detection, recognition of human activities, fall detection and sports performance, 3) Human Pose Tracking using one-person or multi-person tracking and localization systems such as OpenPose, Simultaneous Localization and Mapping (SLAM), etc., 4) Gait-based biometrics with applications in person identification, authentication, and re-identification as well as gender and age recognition 5) “Smart gait” applications ranging from smart socks, shoes, and other wearables to smart homes and smart retail stores that incorporate continuous monitoring and control systems and 6) Animation that reconstructs human motion utilizing gait data, simulation and machine learning techniques. Our goal is to provide a single broad-based survey of the applications of machine learning technology in gait analysis and identify future areas of potential study and growth. We discuss the machine learning techniques that have been used with a focus on the tasks they perform, the problems they attempt to solve, and the trade-offs they navigate.

Functional gait measures correlate to fear of falling, and quality of life in patients with Hereditary Spastic Paraplegia: A cross-sectional study

OBJECTIVE

Gait impairment is the cardinal motor symptom in hereditary spastic paraplegias (HSPs) possibly linked to increased fear of falling and reduced quality of life (QoL). Disease specific symptoms in HSP are rated using the Spastic Paraplegia Rating Scale (SPRS). However, limited studies evaluated more objectively easy-to-apply gait measures by comparing these standardized assessments with patients' self-perceived impairment and clinically established scores. Therefore, the aim of this study was to correlate functional gait measures with self-rating questionnaires for fear of falling and QoL, and with the SPRS as clinical gold standard.

METHODS

HSP patients ("pure" phenotype, n = 22) fulfilling the clinical diagnostic criteria for HSP and age-and gender-matched healthy subjects (n = 22) were included in this study. Motor impairment was evaluated using the SPRS, fear of falling by the Falls Efficacy Scale-International (FES-I), and QoL by SF-12. Functional gait measures included gait speed and step length (10-meter-walk-test), the Timed up and go test (TUG), and maximum walking distance (2-min-walking-test).

RESULTS

Functional gait measures correlated to fear of falling (gait speed: r = -0.726; step length: r = -0.689; TUG: r = 0.721; 2-min: r = -0.709) and the physical component of QoL (gait speed: r = 0.541; step length: r = 0.531; TUG: r = -0.512; 2-min: r = 0.548). Furthermore, FES-I (r = 0.767) and QoL (r = -0.728) correlated with the clinical gold standard (SPRS). Gait measures strongly correlated with SPRS (gait speed: r = -0.787; step length: r = -0.821; TUG: r = 0.756; 2-min: r = -0.791).

CONCLUSION

Functional gait measures reflect fear of falling, QoL, and mobility in HSP. The metric, semi-quantitative gait measures complement the clinician's evaluation and support the clinical workup by more objective parameters.

Gait Symmetry Analysis Based on Dynamic Time Warping

Background: Gait deviations may negatively affect the articular surfaces of the lower extremity joints and lead to some minor degenerative changes. The simplest method for gait evaluation is to assess the symmetry of its parameters, assuming that each undisturbed gait should be symmetrical. This study aims to quantify the degree of asymmetry of kinematic and kinetic parameters caused by the presence of different ankle orthosis settings using Dynamic Time Warping (DTW). Methods: Barefoot gait and gait with four different walker settings were investigated in eighteen healthy persons. Kinematic and kinetic parameters were measured using the Vicon system and Kistler plates. Symmetry was assessed using the DTW method. Results: It was shown that the presence of different ankle orthosis settings significantly disturbs the symmetry of all lower limb kinematic parameters and only knee and hip torques. The highest values of asymmetry were noted for the walker set at 15° of dorsiflexion (15DF). Conclusions: The DTW method allowed us to quantify the degree of asymmetry throughout the gait cycle in relation to barefoot walking. Our results suggest that each orthosis position analysed in this study fulfills its protective function, but gait 15DF can lead to the overload of knee and hip joints.

Pelvic Symmetry Is Influenced by Asymmetrical Tonic Neck Reflex during Young Children's Gait

Gait is one of the examined functions in child development. It should be economical and symmetrical. One test increasingly used by physiotherapists and pediatricians is asymmetrical tonic neck reflex (ATNR). Physiologically, it is observed from in utero up to six postnatal months. This reaction is inhibited with the growing maturation of the central nervous system (CNS). In some children, when the natural process of development is incorrect, ATNR manifests later in life, when it is observed as an automatic response of muscle tension to head rotation. Analysis of pelvis symmetry in the gait of children with active ATNR is important for better understanding their specific movements. In the gait of children with persistent ATNR, some variations are observed. The aim of the study was to investigate the gait symmetry of preschool children and the influence of persistent ATNR. Fifty preschool children with a trace form of ATNR were examined. The distribution of the gait parameters was determined using a BTS G-SENSOR measurement instrument. ATNR negatively influences pelvic obliquity and pelvic rotation (p < 0.01). Younger children have a statistically higher symmetry index of pelvis obliquity in the examined group (p = 0.015). Boys obtain a higher result of symmetry in pelvic tilt than girls in the group (p = 0.027). ATNR affects walking symmetry in preschool children, thus evaluation of the reflex activity and then proper therapy is required to support proper development.

Permutation Entropy and Irreversibility in Gait Kinematic Time Series from Patients with Mild Cognitive Decline and Early Alzheimer’s Dementia

Gait is a basic cognitive purposeful action that has been shown to be altered in late stages of neurodegenerative dementias. Nevertheless, alterations are less clear in mild forms of dementia, and the potential use of gait analysis as a biomarker of initial cognitive decline has hitherto mostly been neglected. Herein, we report the results of a study of gait kinematic time series for two groups of patients (mild cognitive impairment and mild Alzheimer’s disease) and a group of matched control subjects. Two metrics based on permutation patterns are considered, respectively measuring the complexity and irreversibility of the time series. Results indicate that kinematic disorganisation is present in early phases of cognitive impairment; in addition, they depict a rich scenario, in which some joint movements display an increased complexity and irreversibility, while others a marked decrease. Beyond their potential use as biomarkers, complexity and irreversibility metrics can open a new door to the understanding of the role of the nervous system in gait, as well as its adaptation and compensatory mechanisms.

Application of dynamic time warping algorithm for pattern similarity of gait

The purpose of this study was to investigate the effectiveness of dynamic time warping (DTW) in gait research. Participants in this study were consist of 10 males and 10 females. Equipment used for collecting the gait data of participants in this study was three-dimensional (3D) motion analysis system consisted of 8 infrared CCD cameras operated with a sampling frequency of 120 frames/sec. DTW program used in this study was made using the MATLAB and the normal operation of the DTW program was verified by comparison of result manually calculated and output by the DTW program. Flexion angle of the knee joint of both feet obtained by 3D motion analysis system was analyzed by the DTW program and symmetry index (SI) equation. Statistical analysis of the values obtained by DTW was performed by one-sample t-test in confidence interval (CI) 99%, 95%, 90%, 85%, and 80% each using the SPSS. The subjects’ left and right legs were compared 20 times, and other steps of the same foot were compared 20 times. In this study, DTW showed different results from SI which is generally used to test the similarity of gait. Compared to that of DTW, the threshold figure for similarity evaluation in SI, 10%, is considered too large/high. When the CI threshold figure of 95% was adopted in statistical analysis, DTW demonstrated a lower rate of judging two sequences as similar even in the case of normal gait. This study suggests that DTW can be used for the similarity test of gait research.

Technical Validation of an Automated Mobile Gait Analysis System for Hereditary Spastic Paraplegia Patients

Hereditary spastic paraplegias (HSP) represents a group of orphan neurodegenerative diseases with gait disturbance as the predominant clinical feature. Due to its rarity, research within this field is still limited. Aside from clinical analysis using established scales, gait analysis has been employed to enhance the understanding of the mechanisms behind the disease. However, state of the art gait analysis systems are often large, immobile and expensive. To overcome these limitations, this paper presents the first clinically relevant mobile gait analysis system for HSP patients. We propose an unsupervised model based on local cyclicity estimation and hierarchical hidden Markov models (LCE-hHMM). The system provides stride time, swing time, stance time, swing duration and cadence. These parameters are validated against a GAITRite system and manual sensor data labelling using a total of 24 patients within 2 separate studies. The proposed system achieves a stride time error of -0.00  ± 0.09 s (correlation coefficient, r = 1.00) and a swing duration error of -0.67  ± 3.27 % (correlation coefficient, r = 0.93) with respect to the GAITRite system. We show that these parameters are also correlated to the clinical spastic paraplegia rating scale (SPRS) in a similar manner to other state of the art gait analysis systems, as well as to supervised and general versions of the proposed model. Finally, we show a proof of concept for this system to be used to analyse alterations in the gait of individual patients. Thus, with further clinical studies, due to its automated approach and mobility, this system could be used to determine treatment effects in future clinical trials.