Hold that pose: capturing cervical dystonia's head deviation severity from video

Head movement dynamics in dystonia: a multi-centre retrospective study using visual perceptive deep learning

Dystonia is a neurological movement disorder characterised by abnormal involuntary movements and postures, particularly affecting the head and neck. However, current clinical assessment methods for dystonia rely on simplified rating scales which lack the ability to capture the intricate spatiotemporal features of dystonic phenomena, hindering clinical management and limiting understanding of the underlying neurobiology. To address this, we developed a visual perceptive deep learning framework that utilizes standard clinical videos to comprehensively evaluate and quantify disease states and the impact of therapeutic interventions, specifically deep brain stimulation. This framework overcomes the limitations of traditional rating scales and offers an efficient and accurate method that is rater-independent for evaluating and monitoring dystonia patients. To evaluate the framework, we leveraged semi-standardized clinical video data collected in three retrospective, longitudinal cohort studies across seven academic centres. We extracted static head angle excursions for clinical validation and derived kinematic variables reflecting naturalistic head dynamics to predict dystonia severity, subtype, and neuromodulation effects. The framework was also applied to a fully independent cohort of generalised dystonia patients for comparison between dystonia sub-types. Computer vision-derived measurements of head angle excursions showed a strong correlation with clinically assigned scores. Across comparisons, we identified consistent kinematic features from full video assessments encoding information critical to disease severity, subtype, and effects of neural circuit interventions, independent of static head angle deviations used in scoring. Our visual perceptive machine learning framework reveals kinematic pathosignatures of dystonia, potentially augmenting clinical management, facilitating scientific translation, and informing personalized precision neurology approaches.

Motor assessment of X-linked dystonia parkinsonism via machine-learning-based analysis of wearable sensor data

X-linked dystonia parkinsonism (XDP) is a neurogenetic combined movement disorder involving both parkinsonism and dystonia. Complex, overlapping phenotypes result in difficulties in clinical rating scale assessment. We performed wearable sensor-based analyses in XDP participants to quantitatively characterize disease phenomenology as a potential clinical trial endpoint. Wearable sensor data was collected from 10 symptomatic XDP patients and 3 healthy controls during a standardized examination. Disease severity was assessed with the Unified Parkinson's Disease Rating Scale Part 3 (MDS-UPDRS) and Burke-Fahn-Marsden dystonia scale (BFM). We collected sensor data during the performance of specific MDS-UPDRS/BFM upper- and lower-limb motor tasks, and derived data features suitable to estimate clinical scores using machine learning (ML). XDP patients were at varying stages of disease and clinical severity. ML-based algorithms estimated MDS-UPDRS scores (parkinsonism) and dystonia-specific data features with a high degree of accuracy. Gait spatio-temporal parameters had high discriminatory power in differentiating XDP patients with different MDS-UPDRS scores from controls, XDP freezing of gait, and dystonic/non-dystonic gait. These analyses suggest the feasibility of using wearable sensor data for deriving reliable clinical score estimates associated with both parkinsonian and dystonic features in a complex, combined movement disorder and the utility of motion sensors in quantifying clinical examination.

Interdisciplinary insights into tremor in dystonia: Navigating clinical controversies, definitional challenges, and pathophysiological complexities

This review delves into the historical evolution and ongoing controversy surrounding the relationship between tremor and dystonia. The Dystonia Consensus Panel and the International Parkinson's and Movement Disorders Society's Tremor Taskforce have attempted to define these entities, but the complexity arises when patients have a combination of both dystonia and tremor. The term "dystonic tremor" has sparked diverse interpretations, with debates over its clinical features and the need for more objectively defined characteristics. Logistic regression analyses in a large cohort of dystonia patients identified determinants such as body region affected by dystonia, dystonia severity, age, and recruitment site, with unexpected associations emphasizing the subjectivity in detecting and classifying tremor. The study further discovered diverse prevalence of "dystonic tremor" based on different definitions, revealing substantial variability among investigators. The recently convened Dystonia-Tremor panel aimed to address these challenges by proposing a more uniform nomenclature, emphasizing precise and descriptive terms. Despite the complexity, instrumented measures, such as electromyography, temporal discrimination threshold, blink reflex, and trajectory shape analysis, seem to be useful in distinguishing between tremor and dystonia. The pathophysiology debate centers around the involvement of the cerebello-thalamo-cortical and basal ganglia-thalamo-cortical circuits. Evidence supports the role of both circuits in driving the pathophysiology of dystonic tremor, challenging the notion of a clear dichotomy. The review concludes by emphasizing the need for a nuanced understanding, highlighting the intricate interplay between tremor and dystonia, and the potential of instrumental measures in advancing diagnostic accuracy.

Cervical motion alterations and brain functional connectivity in cervical dystonia

INTRODUCTION

Evaluating the neural correlates of sensorimotor control deficits in cervical dystonia (CD) is fundamental to plan the best treatment. This study aims to assess kinematic and resting-state functional connectivity (RS-FC) characteristics in CD patients relative to healthy controls.

METHODS

Seventeen CD patients and 14 age-/sex-matched healthy controls were recruited. Electromagnetic sensors were used to evaluate dystonic pattern, mean/maximal cervical movement amplitude and joint position error with eyes open and closed, and movement quality during target reaching with the head. RS-fMRI was acquired to compare the FC of brain sensorimotor regions between patients and controls. In patients, correlations between motion analysis and FC data were assessed.

RESULTS

CD patients relative to controls showed reduced mean and maximal cervical range of motion (RoM) in rotation both towards and against dystonia pattern and reduced total RoM in rotation both with eyes open and closed. They had less severe dystonia pattern with eyes open vs eyes closed. CD patients showed an altered movement quality and sensorimotor control during target reaching and a higher joint position error. Compared to controls, CD patients showed reduced FC between supplementary motor area (SMA), occipital and cerebellar areas, which correlated with lower cervical RoM in rotation both with eyes open and closed and with worse movement quality during target reaching.

CONCLUSIONS

FC alterations between SMA and occipital and cerebellar areas may represent the neural basis of cervical sensorimotor control deficits in CD patients. Electromagnetic sensors and RS-fMRI might be promising tools to monitor CD and assess the efficacy of rehabilitative interventions.

The use of digital outcome measures in clinical trials in rare neurological diseases: a systematic literature review

Developing drugs for rare diseases is challenging, and the precision and objectivity of outcome measures is critical to this process. In recent years, a number of technologies have increasingly been used for remote monitoring of patient health. We report a systematic literature review that aims to summarize the current state of progress with regard to the use of digital outcome measures for real-life motor function assessment of patients with rare neurological diseases. Our search of published literature identified 3826 records, of which 139 were included across 27 different diseases. This review shows that use of digital outcome measures for motor function outside a clinical setting is feasible and employed in a broad range of diseases, although we found few outcome measures that have been robustly validated and adopted as endpoints in clinical trials. Future research should focus on validation of devices, variables, and algorithms to allow for regulatory qualification and widespread adoption.

Improving the Efficacy of Botulinum Toxin for Cervical Dystonia: A Scoping Review

Cervical dstonia (CD) is a chronic disorder with a significant detrimental impact on quality of life, requiring long-term treatment. Intramuscular injections of botulinum neurotoxin (BoNT) every 12 to 16 weeks have become the first-line option for CD. Despite the remarkable efficacy of BoNT as a treatment for CD, a significantly high proportion of patients report poor outcomes and discontinue the treatment. The reasons that drive sub-optimal response or treatment failure in a proportion of patients include but are not limited to inappropriate muscle targets and/or BoNT dosing, improper method of injections, subjective feeling of inefficacy, and the formation of neutralizing antibodies against the neurotoxin. The current review aims to complement published research focusing on the identification of the factors that might explain the failure of BoNT treatment in CD, highlighting possible solutions to improve its outcomes. Thus, the use of the new phenomenological classification of cervical dystonia known as COL-CAP might improve the identification of the muscle targets, but more sensitive information might come from the use of kinematic or scintigraphic techniques and the use of electromyographic or ultrasound guidance might ensure the accuracy of the injections. Suggestions are made for the development of a patient-centered model for the management of cervical dystonia and to emphasize that unmet needs in the field are to increase awareness about the non-motor spectrum of CD, which might influence the perception of the efficacy from BoNT injections, and the development of dedicated rehabilitation programs for CD that might enhance its effectiveness.

Evaluation of Various State of the Art Head Pose Estimation Algorithms for Clinical Scenarios

Head pose assessment can reveal important clinical information on human motor control. Quantitative assessment have the potential to objectively evaluate head pose and movements' specifics, in order to monitor the progression of a disease or the effectiveness of a treatment. Optoelectronic camera-based motion-capture systems, recognized as a gold standard in clinical biomechanics, have been proposed for head pose estimation. However, these systems require markers to be positioned on the person's face which is impractical for everyday clinical practice. Furthermore, the limited access to this type of equipment and the emerging trend to assess mobility in natural environments support the development of algorithms capable of estimating head orientation using off-the-shelf sensors, such as RGB cameras. Although artificial vision is a popular field of research, limited validation of human pose estimation based on image recognition suitable for clinical applications has been performed. This paper first provides a brief review of available head pose estimation algorithms in the literature. Current state-of-the-art head pose algorithms designed to capture the facial geometry from videos, OpenFace 2.0, MediaPipe and 3DDFA_V2, are then further evaluated and compared. Accuracy is assessed by comparing both approaches to a baseline, measured with an optoelectronic camera-based motion-capture system. Results reveal a mean error lower or equal to 5.6∘ for 3DDFA_V2 depending on the plane of movement, while the mean error reaches 14.1∘ and 11.0∘ for OpenFace 2.0 and MediaPipe, respectively. This demonstrates the superiority of the 3DDFA_V2 algorithm in estimating head pose, in different directions of motion, and suggests that this algorithm can be used in clinical scenarios.