Quantitative Gait Analysis in Patients with Huntington's Disease

Vision-based motion capture for the gait analysis of neurodegenerative diseases: A review

BACKGROUND

Developments in vision-based systems and human pose estimation algorithms have the potential to detect, monitor and intervene early on neurodegenerative diseases through gait analysis. However, the gap between the technology available and actual clinical practice is evident as most clinicians still rely on subjective observational gait analysis or objective marker-based analysis that is time-consuming.

RESEARCH QUESTION

This paper aims to examine the main developments of vision-based motion capture and how such advances may be integrated into clinical practice.

METHODS

The literature review was conducted in six online databases using Boolean search terms. A commercial system search was also included. A predetermined methodological criterion was then used to assess the quality of the selected articles.

RESULTS

A total of seventeen studies were evaluated, with thirteen studies focusing on gait classification systems and four studies on gait measurement systems. Of the gait classification systems, nine studies utilized artificial intelligence-assisted techniques, while four studies employed statistical techniques. The results revealed high correlations of gait features identified by classifier models with existing clinical rating scales. These systems demonstrated generally high classification accuracies and were effective in diagnosing disease severity levels. Gait measurement systems that extract spatiotemporal and kinematic joint information from video data generally found accurate measurements of gait parameters with low mean absolute errors, high intra- and inter-rater reliability.

SIGNIFICANCE

Low cost, portable vision-based systems can provide proof of concept for the quantification of gait, expansion of gait assessment tools, remote gait analysis of neurodegenerative diseases and a point of care system for orthotic evaluation. However, certain challenges, including small sample sizes, occlusion risks, and selection bias in training models, need to be addressed. Nevertheless, these systems can serve as complementary tools, equipping clinicians with essential gait information to objectively assess disease severity and tailor personalized treatment for enhanced patient care.

Estimation of Gait Parameters in Huntington's Disease Using Wearable Sensors in the Clinic and Free-living Conditions

In Huntington's disease (HD), wearable inertial sensors could capture subtle changes in motor function. However, disease-specific validation of methods is necessary. This study presents an algorithm for walking bout and gait event detection in HD using a leg-worn accelerometer, validated only in the clinic and deployed in free-living conditions. Seventeen HD participants wore shank- and thigh-worn tri-axial accelerometers, and a wrist-worn device during two-minute walk tests in the clinic, with video reference data for validation. Thirteen participants wore one of the thigh-worn tri-axial accelerometers (AP: ActivPAL4) and the wrist-worn device for 7 days under free-living conditions, with proprietary AP data used as reference. Gait events were detected from shank and thigh acceleration using the Teager-Kaiser energy operator combined with unsupervised clustering. Estimated step count (SC) and temporal gait parameters were compared with reference data. In the clinic, low mean absolute percentage errors were observed for stride (shank/thigh: 0.6/0.9%) and stance (shank/thigh: 3.3/7.1%) times, and SC (shank/thigh: 3.1%). Similar errors were observed for proprietary AP SC (3.2%), with higher errors observed for the wrist-worn device (10.9%). At home, excellent agreement was observed between the proposed algorithm and AP software for SC and time spent walking (ICC [Formula: see text]). The wrist-worn device overestimated SC by 34.2%. The presented algorithm additionally allowed stride and stance time estimation, whose variability correlated significantly with clinical motor scores. The results demonstrate a new method for accurate estimation of HD gait parameters in the clinic and free-living conditions, using a single accelerometer worn on either the thigh or shank.

Gene-dosage- and sex-dependent differences in the prodromal-Like phase of the F344tgHD rat model for Huntington disease

In Huntington disease (HD) the prodromal phase has been increasingly investigated and is currently in focus for early interventional treatments. Also, the influence of sex on disease progression and severity in patients is under discussion, as a sex-specific impact has been reported in transgenic rodent models for HD. To this end, we have been studying these aspects in Sprague Dawley rats transgenic for HD. Here, we took up on the congenic F344tgHD rat model, expressing a fragmented Htt construct with 51 CAG repeats on an inbred F344 rat background and characterized potential sexual dimorphism and gene-dosage effects in rats during the pre-symptomatic phase (1-8 months of age). Our study comprises a longitudinal phenotyping of motor function, emotion and sensorimotor gating, as well as screening of metabolic parameters with classical and automated assays in combination with investigation of molecular HD hallmarks (striatal cell number and volume estimation, appearance of HTT aggregates). Differences between sexes became apparent during middle age, particularly in the motor and sensorimotor domains. Female individuals were generally more active, demonstrated different gait characteristics than males and less anxiolytic-like behavior. Alterations in both the time course and affected behavioral domains varied between male and female F344tgHD rats. First subtle behavioral anomalies were detected in transgenic F344tgHD rats prior to striatal MSN cell loss, revealing a prodromal-like phase in this model. Our findings demonstrate that the congenic F344tgHD rat model shows high face-validity, closely resembling the human disease's temporal progression, while having a relatively low number of CAG repeats, a slowly progressing pathology with a prodromal-like phase and a comparatively subtle phenotype. By differentiating the sexes regarding HD-related changes and characterizing the prodromal-like phase in this model, these findings provide a foundation for future treatment studies.

The semicircular canal function is preserved with little impact on falls in patients with mild Parkinson's disease

INTRODUCTION

Postural instability is a cardinal symptom of Parkinson's disease (PD), which suggests the vestibular system may be affected in PD. This study aimed to determine whether vestibular dysfunction is associated with the risk of falls in PD.

METHODS

We prospectively recruited patients with de-novo PD at a tertiary medical center between December 2019 and March 2023. During initial assessment, each patient was queried about falls within the preceding year. All patients underwent evaluation of video head-impulse tests (video-HITs), motion analysis, mini-mental state examination (MMSE), and Montreal Cognitive Assessment (MOCA). We determined whether head impulse gain of the vestibulo-ocular reflex (VOR) was associated with clinical severity of PD or risk of falls.

RESULTS

Overall, 133 patients (mean age ± SD = 68 ± 10, 59 men) were recruited. The median Movement Disorder Society-Unified Parkinson's Disease Rating Scale motor part (MDS-UPDRS-III) was 23 (interquartile range = 16-31), and 81 patients (61 %) scored 2 or less on the Hoehn and Yahr scale. Fallers were older (p = 0.001), had longer disease duration (p = 0.001), slower gait velocity (p = 0.009), higher MDS-UPDRS-III (p < 0.001) and H&Y scale (p < 0.001), lower MMSE (p = 0.018) and MOCA scores (p = 0.001) than non-fallers. Multiple logistic regression showed that MDS-UPDRS-III had a positive association with falling (p = 0.004). Falling was not associated with VOR gain (p = 0.405). The VOR gain for each semicircular canal showed no correlation with the MDS-UPDRS-III or disease duration.

CONCLUSIONS

The semicircular canal function, as determined by video-HITs, is relatively spared and has little effect on the risk of falls in patients with mild-to-moderate PD.

Spatiotemporal Gait Parameters in Adults With Premanifest and Manifest Huntington's Disease: A Systematic Review

OBJECTIVE

To systematically review and critically evaluate literature on spatiotemporal gait deviations in individuals with premanifest and manifest Huntington's Disease (HD) in comparison with healthy cohorts.

METHODS

We conducted a systematic review, guided by the Joanna Briggs Institute's Manual for Evidence Synthesis and pre-registered with the International Prospective Register of Systematic Reviews. Eight electronic databases were searched. Studies comparing spatiotemporal footstep parameters in adults with premanifest and manifest HD to healthy controls were screened, included and critically appraised by independent reviewers. Data on spatiotemporal gait changes and variability were extracted and synthesised. Meta-analysis was performed on gait speed, cadence, stride length and stride length variability measures.

RESULTS

We screened 2,721 studies, identified 1,245 studies and included 25 studies (total 1,088 participants). Sample sizes ranged from 14 to 96. Overall, the quality of the studies was assessed as good, but reporting of confounding factors was often unclear. Meta-analysis found spatiotemporal gait deviations in participants with HD compared to healthy controls, commencing in the premanifest stage. Individuals with premanifest HD walk significantly slower (-0.17 m/s; 95% confidence interval [CI] [-0.22, -0.13]), with reduced cadence (-6.63 steps/min; 95% CI [-10.62, -2.65]) and stride length (-0.09 m; 95% CI [-0.13, -0.05]). Stride length variability was also increased in premanifest cohorts by 2.18% (95% CI [0.69, 3.68]), with these changes exacerbated in participants with manifest disease.

CONCLUSION

Findings suggest individuals with premanifest and manifest HD display significant spatiotemporal footstep deviations. Clinicians could monitor individuals in the premanifest stage of disease for gait changes to identify the onset of Huntington's symptoms.

Wearable sensors and features for diagnosis of neurodegenerative diseases: A systematic review

Objective

Neurodegenerative diseases affect millions of families around the world, while various wearable sensors and corresponding data analysis can be of great support for clinical diagnosis and health assessment. This systematic review aims to provide a comprehensive overview of the existing research that uses wearable sensors and features for the diagnosis of neurodegenerative diseases.

Methods

A systematic review was conducted of studies published between 2015 and 2022 in major scientific databases such as Web of Science, Google Scholar, PubMed, and Scopes. The obtained studies were analyzed and organized into the process of diagnosis: wearable sensors, feature extraction, and feature selection.

Results

The search led to 171 eligible studies included in this overview. Wearable sensors such as force sensors, inertial sensors, electromyography, electroencephalography, acoustic sensors, optical fiber sensors, and global positioning systems were employed to monitor and diagnose neurodegenerative diseases. Various features including physical features, statistical features, nonlinear features, and features from the network can be extracted from these wearable sensors, and the alteration of features toward neurodegenerative diseases was illustrated. Moreover, different kinds of feature selection methods such as filter, wrapper, and embedded methods help to find the distinctive indicator of the diseases and benefit to a better diagnosis performance.

Conclusions

This systematic review enables a comprehensive understanding of wearable sensors and features for the diagnosis of neurodegenerative diseases.

Identification of Neurodegenerative Diseases Based on Vertical Ground Reaction Force Classification Using Time-Frequency Spectrogram and Deep Learning Neural Network Features

A novel identification algorithm using a deep learning approach was developed in this study to classify neurodegenerative diseases (NDDs) based on the vertical ground reaction force (vGRF) signal. The irregularity of NDD vGRF signals caused by gait abnormalities can indicate different force pattern variations compared to a healthy control (HC). The main purpose of this research is to help physicians in the early detection of NDDs, efficient treatment planning, and monitoring of disease progression. The detection algorithm comprises a preprocessing process, a feature transformation process, and a classification process. In the preprocessing process, the five-minute vertical ground reaction force signal was divided into 10, 30, and 60 s successive time windows. In the feature transformation process, the time-domain vGRF signal was modified into a time-frequency spectrogram using a continuous wavelet transform (CWT). Then, feature enhancement with principal component analysis (PCA) was utilized. Finally, a convolutional neural network, as a deep learning classifier, was employed in the classification process of the proposed detection algorithm and evaluated using leave-one-out cross-validation (LOOCV) and k-fold cross-validation (k-fold CV, k = 5). The proposed detection algorithm can effectively differentiate gait patterns based on a time-frequency spectrogram of a vGRF signal between HC subjects and patients with neurodegenerative diseases.

Human Gait Analysis in Neurodegenerative Diseases: a Review

This paper reviews the recent literature on technologies and methodologies for quantitative human gait analysis in the context of neurodegnerative diseases. The use of technological instruments can be of great support in both clinical diagnosis and severity assessment of these pathologies. In this paper, sensors, features and processing methodologies have been reviewed in order to provide a highly consistent work that explores the issues related to gait analysis. First, the phases of the human gait cycle are briefly explained, along with some non-normal gait patterns (gait abnormalities) typical of some neurodegenerative diseases. The work continues with a survey on the publicly available datasets principally used for comparing results. Then the paper reports the most common processing techniques for both feature selection and extraction and for classification and clustering. Finally, a conclusive discussion on current open problems and future directions is outlined.

Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques

Neurodegenerative diseases have shown an increasing incidence in the older population in recent years. A significant amount of research has been conducted to characterize these diseases. Computational methods, and particularly machine learning techniques, are now very useful tools in helping and improving the diagnosis as well as the disease monitoring process. In this paper, we provide an in-depth review on existing computational approaches used in the whole neurodegenerative spectrum, namely for Alzheimer's, Parkinson's, and Huntington's Diseases, Amyotrophic Lateral Sclerosis, and Multiple System Atrophy. We propose a taxonomy of the specific clinical features, and of the existing computational methods. We provide a detailed analysis of the various modalities and decision systems employed for each disease. We identify and present the sleep disorders which are present in various diseases and which represent an important asset for onset detection. We overview the existing data set resources and evaluation metrics. Finally, we identify current remaining open challenges and discuss future perspectives.

Rapid and robust patterns of spontaneous locomotor deficits in mouse models of Huntington's disease

Huntington's disease (HD) is an inherited neurodegenerative disorder characterized by severe disruption of cognitive and motor functions, including changes in posture and gait. A number of HD mouse models have been engineered that display behavioral and neuropathological features of the disease, but gait alterations in these models are poorly characterized. Sensitive high-throughput tests of fine motor function and gait in mice might be informative in evaluating disease-modifying interventions. Here, we describe a hypothesis-free workflow that determines progressively changing locomotor patterns across 79 parameters in the R6/2 and Q175 mouse models of HD. R6/2 mice (120 CAG repeats) showed motor disturbances as early as at 4 weeks of age. Similar disturbances were observed in homozygous and heterozygous Q175 KI mice at 3 and 6 months of age, respectively. Interestingly, only the R6/2 mice developed forelimb ataxia. The principal components of the behavioral phenotypes produced two phenotypic scores of progressive postural instability based on kinematic parameters and trajectory waveform data, which were shared by both HD models. This approach adds to the available HD mouse model research toolbox and has a potential to facilitate the development of therapeutics for HD and other debilitating movement disorders with high unmet medical need.

Cerebral dopamine neurotrophic factor (CDNF) protects against quinolinic acid-induced toxicity in in vitro and in vivo models of Huntington's disease

Huntington’s disease (HD) is a neurodegenerative disorder with a progressive loss of medium spiny neurons in the striatum and aggregation of mutant huntingtin in the striatal and cortical neurons. Currently, there are no rational therapies for the treatment of the disease. Cerebral dopamine neurotrophic factor (CDNF) is an endoplasmic reticulum (ER) located protein with neurotrophic factor (NTF) properties, protecting and restoring the function of dopaminergic neurons in animal models of PD more effectively than other NTFs. CDNF is currently in phase I–II clinical trials on PD patients. Here we have studied whether CDNF has beneficial effects on striatal neurons in in vitro and in vivo models of HD. CDNF was able to protect striatal neurons from quinolinic acid (QA)-induced cell death in vitro via increasing the IRE1α/XBP1 signalling pathway in the ER. A single intrastriatal CDNF injection protected against the deleterious effects of QA in a rat model of HD. CDNF improved motor coordination and decreased ataxia in QA-toxin treated rats, and stimulated the neurogenesis by increasing doublecortin (DCX)-positive and NeuN-positive cells in the striatum. These results show that CDNF positively affects striatal neuron viability reduced by QA and signifies CDNF as a promising drug candidate for the treatment of HD.

Evaluation of Vertical Ground Reaction Forces Pattern Visualization in Neurodegenerative Diseases Identification Using Deep Learning and Recurrence Plot Image Feature Extraction

To diagnose neurodegenerative diseases (NDDs), physicians have been clinically evaluating symptoms. However, these symptoms are not very dependable—particularly in the early stages of the diseases. This study has therefore proposed a novel classification algorithm that uses a deep learning approach to classify NDDs based on the recurrence plot of gait vertical ground reaction force (vGRF) data. The irregular gait patterns of NDDs exhibited by vGRF data can indicate different variations of force patterns compared with healthy controls (HC). The classification algorithm in this study comprises three processes: a preprocessing, feature transformation and classification. In the preprocessing process, the 5-min vGRF data divided into 10-s successive time windows. In the feature transformation process, the time-domain vGRF data are modified into an image using a recurrence plot. The total recurrence plots are 1312 plots for HC (16 subjects), 1066 plots for ALS (13 patients), 1230 plots for PD (15 patients) and 1640 plots for HD (20 subjects). The principal component analysis (PCA) is used in this stage for feature enhancement. Lastly, the convolutional neural network (CNN), as a deep learning classifier, is employed in the classification process and evaluated using the leave-one-out cross-validation (LOOCV). Gait data from HC subjects and patients with amyotrophic lateral sclerosis (ALS), Huntington’s disease (HD) and Parkinson’s disease (PD) obtained from the PhysioNet Gait Dynamics in Neurodegenerative disease were used to validate the proposed algorithm. The experimental results included two-class and multiclass classifications. In the two-class classification, the results included classification of the NDD and the HC groups and classification among the NDDs. The classification accuracy for (HC vs. ALS), (HC vs. HD), (HC vs. PD), (ALS vs. PD), (ALS vs. HD), (PD vs. HD) and (NDDs vs. HC) were 100%, 98.41%, 100%, 95.95%, 100%, 97.25% and 98.91%, respectively. In the multiclass classification, a four-class gait classification among HC, ALS, PD and HD was conducted and the classification accuracy of HC, ALS, PD and HD were 98.99%, 98.32%, 97.41% and 96.74%, respectively. The proposed method can achieve high accuracy compare to the existing results, but with shorter length of input signal (Input of existing literature using the same database is 5-min gait signal, but the proposed method only needs 10-s gait signal).

Gait variability as digital biomarker of disease severity in Huntington's disease

BACKGROUND

Impaired gait plays an important role for quality of life in patients with Huntington's disease (HD). Measuring objective gait parameters in HD might provide an unbiased assessment of motor deficits in order to determine potential beneficial effects of future treatments.

OBJECTIVE

To objectively identify characteristic features of gait in HD patients using sensor-based gait analysis. Particularly, gait parameters were correlated to the Unified Huntington's Disease Rating Scale, total motor score (TMS), and total functional capacity (TFC).

METHODS

Patients with manifest HD at two German sites (n = 43) were included and clinically assessed during their annual ENROLL-HD visit. In addition, patients with HD and a cohort of age- and gender-matched controls performed a defined gait test (4 × 10 m walk). Gait patterns were recorded by inertial sensors attached to both shoes. Machine learning algorithms were applied to calculate spatio-temporal gait parameters and gait variability expressed as coefficient of variance (CV).

RESULTS

Stride length (- 15%) and gait velocity (- 19%) were reduced, while stride (+ 7%) and stance time (+ 2%) were increased in patients with HD. However, parameters reflecting gait variability were substantially altered in HD patients (+ 17% stride length CV up to + 41% stride time CV with largest effect size) and showed strong correlations to TMS and TFC (0.416 ≤ r_Sp ≤ 0.690). Objective gait variability parameters correlated with disease stage based upon TFC.

CONCLUSIONS

Sensor-based gait variability parameters were identified as clinically most relevant digital biomarker for gait impairment in HD. Altered gait variability represents characteristic irregularity of gait in HD and reflects disease severity.

The effects of dual-task cognitive interference on gait and turning in Huntington's disease

Huntington’s disease (HD) is characterized by motor, cognitive, and psychiatric dysfunction. HD progression causes loss of automaticity, such that previously automatic tasks require greater attentional resources. Dual-task (DT) paradigms and fast-paced gait may stress the locomotor system, revealing deficits not seen under single-task (ST). However, the impact of gait “stress tests” on HD individuals needs further investigation. Therefore, the aims of this study were to investigate whether: 1) fast-paced and dual-task walking uncover deficits in gait and turning not seen under single-task, 2) cognitive and gait outcomes relate to fall incidence, and 3) gait deficits measured with wearable inertial sensors correlate with motor symptom severity in HD as measured by the Unified Huntington’s disease Rating Scale-total motor score (UHDRS-TMS). Seventeen HD (55 ± 9.7 years) and 17 age-matched controls (56.5 ± 9.3 years) underwent quantitative gait testing via a 25m, two-minute walk test with APDM^TM inertial sensors. Gait was assessed under a 1) ST, self-selected pace, 2) fast-as-possible (FAP) pace, and 3) verbal fluency DT. The UHDRS-TMS and a cognitive test battery were administered, and a retrospective fall history was obtained. During ST, DT, and FAP conditions, HD participants demonstrated slower gait, shorter stride length, and greater lateral step and stride length variability compared to controls (p<0.00001 to 0.034). Significant dual-task costs (DTC) were observed for turns; HD participants took more time (p = 0.013) and steps (p = 0.028) to complete a turn under DT compared to controls. Higher UHDRS-TMS correlated with greater stride length variability, less double-support, and more swing-phase time under all conditions. Decreased processing speed was associated with increased gait variability under ST and FAP conditions. Unexpectedly, participant’s self-reported falls did not correlate with any gait or turn parameters. HD participants demonstrated significantly greater DTC for turning, which is less automatic than straight walking, requiring coordination of body segments, anticipatory control, and cortical regulation. Turn complexity likely makes it more susceptible to cognitive interference in HD.

Gait Biomarkers Classification by Combining Assembled Algorithms and Deep Learning: Results of a Local Study

Machine learning, one of the core disciplines of artificial intelligence, is an approach whose main emphasis is analytical model building. In other words, machine learning enables an automaton to make its own decisions based on a previous training process. Machine learning has revolutionized every research sector, including health care, by providing precise and accurate decisions involving minimal human interventions through pattern recognition. This is emphasized in this research, which addresses the issue of “support for diabetic neuropathy (DN) recognition.” DN is a disease that affects a large proportion of the global population. In this research, we have used gait biomarkers of subjects representing a particular sector of population located in southern Mexico to identify persons suffering from DN. To do this, we used a home-made body sensor network to capture raw data of the walking pattern of individuals with and without DN. The information was then processed using three sampling criteria and 23 assembled classifiers, in combination with a deep learning algorithm. The architecture of the best combination was chosen and reconfigured for better performance. The results revealed a highly acceptable classification with greater than 85% accuracy when using these combined approaches.

Discovery of Arginine Ethyl Ester as Polyglutamine Aggregation Inhibitor: Conformational Transitioning of Huntingtin N-Terminus Augments Aggregation Suppression

Huntington's disease (HD) is a genetic disorder caused by a CAG expansion mutation in the huntingtin gene leading to polyglutamine (polyQ) expansion in the N-terminal part of huntingtin (Httex1). Expanded polyQ, through a complex aggregation pathway, forms aggregates in neurons and presents a potential therapeutic target. Here we show Httex1 aggregation suppression by arginine and arginine ethyl ester (AEE) in vitro, as well as in yeast and mammalian cell models of HD, bearing expanded polyQ. These molecules also rescue locomotion dysfunction in HD Drosophila model. Both molecules alter the hydrogen bonding network of polyQ to enhance its aqueous solubility and delay aggregation. AEE shows direct binding with the NT₁₇ part of Httex1 to induce structural changes to impart an enhanced inhibitory effect. This study provides a platform for the development of better arginine based therapeutic molecules against polyQ-rich Httex1 aggregation.