Search

Motor behaviour analysis is essential to biomedical research and clinical diagnostics as it provides a non-invasive strategy for identifying motor impairment and its change caused by interventions. State-of-the-art instrumented movement analysis is time- and cost-intensive, because it requires the placement of physical or virtual markers. As well as the effort required for marking the keypoints or annotations necessary for training or fine-tuning a detector, users need to know the interesting behaviour beforehand to provide meaningful keypoints. Here, we introduce unsupervised behaviour analysis and magnification (uBAM), an automatic deep learning algorithm for analysing behaviour by discovering and magnifying deviations. A central aspect is unsupervised learning of posture and behaviour representations to enable an objective comparison of movement. Besides discovering and quantifying deviations in behaviour, we also propose a generative model for visually magnifying subtle behaviour differences directly in a video without requiring a detour via keypoints or annotations. Essential for this magnification of deviations, even across different individuals, is a disentangling of appearance and behaviour. Evaluations on rodents and human patients with neurological diseases demonstrate the wide applicability of our approach. Moreover, combining optogenetic stimulation with our unsupervised behaviour analysis shows its suitability as a non-invasive diagnostic tool correlating function to brain plasticity. Being able to precisely analyse behaviour is essential for the study of motor behaviour in health and disease, but is often time- and labour-intensive. Brattoli et al. develop an automatic approach based on deep learning for analysing motor behaviour and evaluate it on different species and diverse motor functions.

Background: Walking impairment is a common and highly disabling symptom in people with MS (PwMS). Ambulatory deterioration is poorly characterized in PwMS and reliable prognosis that may guide clinical decisions is elusive. This study aimed to objectively track the progression of clinical walking performance and kinematic gait patterns in PwMS over 4 years, thereby revealing potential prognostic markers for deterioration of ambulatory function. Methods: Twenty-two PwMS (48.8 ± 9.9 years, 14 females; expanded disability status scale [EDSS]: 4.5 ± 0.9 points) with gait impairments were recruited at the University Hospital Zurich, Switzerland. Gait function was monitored over a period of 4 years using a set of standardized clinical walking tests (timed 25-foot walk [T25FW], 6 min walk test [6MWT], 12-item MS walking scale [MSWS-12]) and comprehensive 3D kinematic gait analysis. Walking decline was assessed in the full patient cohort and in patient sub-groups that were built according to MS type (relapsing-remitting [RRMS], progressive [PMS]) and subjects' pathological gait signature (cluster groups 1–3). Results: In the total cohort (n = 22), we found a significant worsening in the 6MWT (BL vs. 4y: -41.1 m; P = 0.0053), while the performance in the T25FW, MSWS-12 and the EDSS remained unchanged over 4 years. Subjects with PMS (n = 12) showed a significant worsening in the EDSS (BL vs. 4y: +0.6 points; P = 0.0053), which was not observed in participants with RRMS (n = 10). Whereas deterioration of clinical walking function was not different between subjects with RRMS and PMS, we identified differences in clinical walking deterioration between PwMS with varying gait pattern pathologies: Subjects with spastic-paretic gait impairments (cluster 1; n = 9) demonstrated a marked worsening in the T25FW (BL vs. 4y: +2 s; P = 0.0020) and 6MWT (BL vs. 4y: -92.9 m; P < 0.0001) which was not seen in PwMS with an ataxia-like (cluster 2; n = 8) or unstable walking pattern (cluster 3; n = 5). Deterioration of clinical walking performance in cluster 1 was accompanied by a specific worsening of gait deficits that were characteristic of this cluster at baseline, a phenomenon not found in the other sub-groups. Accordingly, aggravation of cluster 1-specific gait impairments over 4 years predicted deterioration of the 6MWT in the total cohort (n = 22) with an accuracy of 90.9% (sensitivity: 90.9%; specificity: 90.9%; Nagelkerkes coefficient of determination R2: 0.721), unveiling key determinants of MS-related walking decline. Conclusions: Our findings highlight the potential of quantitative, functional outcomes for objective tracking of disease progression in PwMS. Gait pattern analysis can provide valuable information on the underlying pathomechanisms of gait deterioration and may represent a complementary prognostic tool for walking function in PwMS. Clinical trial: clinicaltrials.gov, NCT01576354, Multiple Sclerosis and Related Disorders, 63

Myotonic Dystrophy Type 1 (DM1) is the most frequent hereditary, adult-onset muscular dystrophy. Nevertheless, DM1-associated cognitive-motor impairments have not been fully characterized so far. This study aimed at profiling cognitive and locomotor dysfunctions in these patients. In addition, cognitive-motor interactions were assessed using a dual-task paradigm. Comprehensive cognitive-motor impairment profiles were generated for 19 patients with DM1 and 19 healthy subjects by thorough clinical, biomechanical and neuropsychological examinations. Detailed gait analysis was performed using a 3D motion capture system, whereas cognitive function was assessed using a standardized neuropsychological test battery. Patients with DM1 showed impaired functional mobility, gait velocity and endurance. DM1-related gait pathology was mainly characterized by enhanced dynamic instability, gait variability, and restricted ankle dorsiflexion. Patients' cognitive impairments particularly concerned attentional functions. Dual-task conditions induced gait deviations that slightly differed between patients and controls. DM1-associated cognitive impairments correlated with reduced functional mobility and impaired ankle dorsiflexion. Patients with DM1 revealed significant impairments of walking function, balance and cognitive performance. Differential cognitive-motor interference and significant interactions between cognitive and motor dysfunctions point towards a prominent role of cognition in gait performance of patients with DM1.

Gait dysfunction is a common and relevant symptom in multiple sclerosis (MS). This study aimed to profile gait pathology in gait-impaired patients with MS using comprehensive 3D gait analysis and clinical walking tests. Thirty-seven patients with MS walked on the treadmill at their individual, sustainable speed while 20 healthy control subjects walked at all the different patient’s paces, allowing for comparisons independent of walking velocity. Kinematic analysis revealed pronounced restrictions in knee and ankle joint excursion, increased gait variability and asymmetry along with impaired dynamic stability in patients. The most discriminative single gait parameter, differentiating patients from controls with an accuracy of 83.3% (χ2 test; p = 0.0001), was reduced knee range of motion. Based on hierarchical cluster and principal component analysis, three principal pathological gait patterns were identified: a spastic-paretic, an ataxia-like, and an unstable gait. Follow-up assessments after 1 year indicated deterioration of walking function, particularly in patients with spastic-paretic gait patterns. Our findings suggest that impaired knee/ankle control is common in patients with MS. Personalised gait profiles and clustering algorithms may be promising tools for stratifying patients and to inform patient-tailored exercise programs. Responsive, objective outcome measures are important for monitoring disease progression and treatment effects in MS trials.

Walking dysfunction is common in people with multiple sclerosis (MS). Besides walking speed or endurance, one crucial feature of ambulatory function is the ability to adjust the gait pattern according to walking speed which relies on the integrity of spinal motor centres, their reciprocal connections to supraspinal networks and peripheral sensory input. To investigate the capacity of people with MS to modify their gait pattern in response to changes in walking speed. 3D gait analysis during free treadmill walking was performed in 35 people with MS and 20 healthy controls. Twelve kinematic parameters ranging from basic spatiotemporal measures to complex indicators of intralimb coordination were assessed at different absolute and relative walking speeds. Cadence, double-limb support time, trunk movements and especially measures of intralimb coordination demonstrated significantly less speed-dependent modifications in MS than in controls. These limitations were more prominent in subjects with stronger MS-related impairment (worse outcome in clinical walking tests, higher Expanded Disability Status Scale). The incapacity to modify specific elements of the walking pattern according to walking speed contributes to gait dysfunction in people with MS limiting activities of daily living. Gait modulation may serve as sensitive marker of walking function in MS. Clinicaltrials.gov, NCT01576354; first posted April 12, 2012.

Locomotor recovery after incomplete spinal cord injury (iSCI) is influenced by spinal and supraspinal networks. Conventional clinical gait analysis fails to differentiate between these components. There is evidence that corticospinal control is enhanced during targeted walking, where each foot must be continuously placed on visual targets in randomized order. This study investigates the potential of targeted walking in the functional assessment of corticospinal integrity. Twenty-one controls and 16 individuals with chronic iSCI performed normal and targeted walking on a treadmill while electromyograms (EMGs) and kinematics were recorded. Precision (% of accurate foot placements) in targeted walking was significantly lower in individuals with iSCI (82.9 ± 14.7%, controls: 94.9 ± 4.0%). Although the overall kinematic pattern was comparable between walking conditions, controls showed significantly higher semitendinosus (ST) activity before heel-strike during targeted walking. This was accompanied by a shift of relative EMG intensity from 90-120 Hz to lower frequencies of 20-60 Hz, previously associated with corticospinal control of muscle activity. Targeted walking in individuals with iSCI evoked smaller EMG changes, suggesting that the switch to more corticospinal control is impaired. Accordingly, mildly impaired iSCI individuals revealed higher adaptations to the targeted walking task than more-impaired individuals. Recording of EMGs during targeted walking holds potential as a research tool to reveal further insights into the neuromuscular control of locomotion. It also complements findings of pre-clinical studies and is a promising novel surrogate marker of integrity of corticospinal control in individuals with iSCI and other neurological impairments. Future studies should investigate its potential for diagnosis or tracking recovery during rehabilitation.

Falls are common in patients with neurological disorders and are a primary cause of injuries. Nonetheless, fall-associated gait characteristics are poorly understood in these patients. Objective, quantitative gait analysis is an important tool to identify the principal fall-related motor characteristics and to advance fall prevention in patients with neurological disorders. Fall incidence was assessed in 60 subjects with different neurological disorders. Patients underwent a comprehensive set of functional assessments including instrumented gait analysis, computerized postural assessments and clinical walking tests. Determinants of falls were assessed by binary logistic regression analysis and receiver operator characteristics (ROC). The best single determinant of fallers was a step length reduction at slow walking speed reaching an accuracy of 67.2% (ROC AUC: 0.669; p = 0.027). The combination of 4 spatio-temporal gait parameters including step length and parameters of variability and asymmetry were able to classify fallers and non-fallers with an accuracy of 81.0% (ROC AUC: 0.882; p

BACKGROUND Fampridine leads to significant walking improvements in many persons with multiple sclerosis (PwMS). However, a relevant proportion of PwMS does not respond to fampridine and predictors of initial drug responsiveness are unknown. METHODS Drug response to prolonged-release (PR)-fampridine was assessed in 55 PwMS using the timed 25-foot walk (T25FW), the 6-minute walk test (6MWT) and the 12-item multiple sclerosis walking scale (MSWS-12) as outcome parameters. Patients were treated with PR-fampridine and placebo each for 6 weeks in a randomised, double-blind, placebo-controlled trial with cross-over design (NCT01576354). Possible predictors of drug responsiveness were investigated by multiple correlation analysis and binary logistic regression models. An additional longitudinal analysis followed drug responses of 32 patients treated with PR-fampridine over 3 years to identify potential predictors of long-term drug responsiveness. RESULTS Severity of walking disability was positively correlated with enhanced responses to PR-fampridine. The strongest single predictor of drug responsiveness was poor 6MWT performance at baseline, which was positively correlated with enhanced drug response in the 6MWT (R=-0.541; P

IntroductionSpinal cord injury (SCI) is a devastating condition with immediate impact on the individual’s health and quality of life. Major functional recovery reaches a plateau 3–4 months after injury despite intensive rehabilitative training. To enhance training efficacy and improve long-term outcomes, the combination of rehabilitation with electrical modulation of the spinal cord and brain has recently aroused scientific interest with encouraging results. The mesencephalic locomotor region (MLR), an evolutionarily conserved brainstem locomotor command and control centre, is considered a promising target for deep brain stimulation (DBS) in patients with SCI. Experiments showed that MLR-DBS can induce locomotion in rats with spinal white matter destructions of >85%.Methods and analysisIn this prospective one-armed multi-centre study, we investigate the safety, feasibility, and therapeutic efficacy of MLR-DBS to enable and enhance locomotor training in severely affected, subchronic and chronic American Spinal Injury Association Impairment Scale C patients in order to improve functional recovery. Patients undergo an intensive training programme with MLR-DBS while being regularly followed up until 6 months post-implantation. The acquired data of each timepoint are compared with baseline while the primary endpoint is performance in the 6-minute walking test. The clinical trial protocol was written in accordance with the Standard Protocol Items: Recommendations for Interventional Trials checklist.Ethics and disseminationThis first in-man study investigates the therapeutic potential of MLR-DBS in SCI patients. One patient has already been implanted with electrodes and underwent MLR stimulation during locomotion. Based on the preliminary results which promise safety and feasibility, recruitment of further patients is currently ongoing. Ethical approval has been obtained from the Ethical Committee of the Canton of Zurich (case number BASEC 2016-01104) and Swissmedic (10000316). Results will be published in peer-reviewed journals and presented at conferences.Trial registration numberNCT03053791.