Validation of a precision tremor measurement system for multiple sclerosis

Upper limb intention tremor assessment: opportunities and challenges in wearable technology

BACKGROUND

Tremors are involuntary rhythmic movements commonly present in neurological diseases such as Parkinson's disease, essential tremor, and multiple sclerosis. Intention tremor is a subtype associated with lesions in the cerebellum and its connected pathways, and it is a common symptom in diseases associated with cerebellar pathology. While clinicians traditionally use tests to identify tremor type and severity, recent advancements in wearable technology have provided quantifiable ways to measure movement and tremor using motion capture systems, app-based tasks and tools, and physiology-based measurements. However, quantifying intention tremor remains challenging due to its changing nature.

METHODOLOGY & RESULTS

This review examines the current state of upper limb tremor assessment technology and discusses potential directions to further develop new and existing algorithms and sensors to better quantify tremor, specifically intention tremor. A comprehensive search using PubMed and Scopus was performed using keywords related to technologies for tremor assessment. Afterward, screened results were filtered for relevance and eligibility and further classified into technology type. A total of 243 publications were selected for this review and classified according to their type: body function level: movement-based, activity level: task and tool-based, and physiology-based. Furthermore, each publication's methods, purpose, and technology are summarized in the appendix table.

CONCLUSIONS

Our survey suggests a need for more targeted tasks to evaluate intention tremors, including digitized tasks related to intentional movements, neurological and physiological measurements targeting the cerebellum and its pathways, and signal processing techniques that differentiate voluntary from involuntary movement in motion capture systems.

Contactless hand tremor amplitude measurement using smartphones: development and pilot evaluation

Background - Physiological tremor is defined as an involuntary and rhythmic shaking. Tremor of the hand is a key symptom of multiple neurological diseases, and its frequency and amplitude differs according to both disease type and disease progression. In routine clinical practice, tremor frequency and amplitude are assessed by expert rating using a 0 to 4 integer scale. Such ratings are subjective and have poor inter-rater reliability. There is thus a clinical need for a practical and accurate method for objectively assessing hand tremor.Objective - to develop a proof-of-principle method to measure hand tremor amplitude from smartphone videos.Methods - We created a computer vision pipeline that automatically extracts salient points on the hand and produces a 1-D time series of movement due to tremor, in pixels. Using the smartphones' depth measurement, we convert this measure into real distance units. We assessed the accuracy of the method using 60 videos of simulated tremor of different amplitudes from two healthy adults. Videos were taken at distances of 50, 75 and 100 cm between hand and camera. The participants had skin tone II and VI on the Fitzpatrick scale. We compared our method to a gold-standard measurement from a slide rule. Bland-Altman methods agreement analysis indicated a bias of 0.04 cm and 95% limits of agreement from -1.27 to 1.20 cm. Furthermore, we qualitatively observed that the method was robust to limited occlusion.Clinical relevance - We have demonstrated how tremor amplitude can be measured from smartphone videos. In conjunction with tremor frequency, this approach could be used to help diagnose and monitor neurological diseases.

The role of machine learning in developing non-magnetic resonance imaging based biomarkers for multiple sclerosis: a systematic review

Background

Multiple sclerosis (MS) is a neurological condition whose symptoms, severity, and progression over time vary enormously among individuals. Ideally, each person living with MS should be provided with an accurate prognosis at the time of diagnosis, precision in initial and subsequent treatment decisions, and improved timeliness in detecting the need to reassess treatment regimens. To manage these three components, discovering an accurate, objective measure of overall disease severity is essential. Machine learning (ML) algorithms can contribute to finding such a clinically useful biomarker of MS through their ability to search and analyze datasets about potential biomarkers at scale. Our aim was to conduct a systematic review to determine how, and in what way, ML has been applied to the study of MS biomarkers on data from sources other than magnetic resonance imaging.

Methods

Systematic searches through eight databases were conducted for literature published in 2014–2020 on MS and specified ML algorithms.

Results

Of the 1, 052 returned papers, 66 met the inclusion criteria. All included papers addressed developing classifiers for MS identification or measuring its progression, typically, using hold-out evaluation on subsets of fewer than 200 participants with MS. These classifiers focused on biomarkers of MS, ranging from those derived from omics and phenotypical data (34.5% clinical, 33.3% biological, 23.0% physiological, and 9.2% drug response). Algorithmic choices were dependent on both the amount of data available for supervised ML (91.5%; 49.2% classification and 42.3% regression) and the requirement to be able to justify the resulting decision-making principles in healthcare settings. Therefore, algorithms based on decision trees and support vector machines were commonly used, and the maximum average performance of 89.9% AUC was found in random forests comparing with other ML algorithms.

Conclusions

ML is applicable to determining how candidate biomarkers perform in the assessment of disease severity. However, applying ML research to develop decision aids to help clinicians optimize treatment strategies and analyze treatment responses in individual patients calls for creating appropriate data resources and shared experimental protocols. They should target proceeding from segregated classification of signals or natural language to both holistic analyses across data modalities and clinically-meaningful differentiation of disease.

Personalised profiling to identify clinically relevant changes in tremor due to multiple sclerosis

Background

There is growing interest in sensor-based assessment of upper limb tremor in multiple sclerosis and other movement disorders. However, previously such assessments have not been found to offer any improvement over conventional clinical observation in identifying clinically relevant changes in an individual’s tremor symptoms, due to poor test-retest repeatability.

Method

We hypothesised that this barrier could be overcome by constructing a tremor change metric that is customised to each individual’s tremor characteristics, such that random variability can be distinguished from clinically relevant changes in symptoms. In a cohort of 24 people with tremor due to multiple sclerosis, the newly proposed metrics were compared against conventional clinical and sensor-based metrics. Each metric was evaluated based on Spearman rank correlation with two reference metrics extracted from the Fahn-Tolosa-Marin Tremor Rating Scale: a task-based measure of functional disability (FTMTRS B) and the subject’s self-assessment of the impact of tremor on their activities of daily living (FTMTRS C).

Results

Unlike the conventional sensor-based and clinical metrics, the newly proposed ’change in scale’ metrics presented statistically significant correlations with changes in self-assessed impact of tremor (maxR²>0.5,p<0.05 after correction for false discovery rate control). They also outperformed all other metrics in terms of correlations with changes in task-based functional performance (R²=0.25 vs. R²=0.15 for conventional clinical observation, both p<0.05).

Conclusions

The proposed metrics achieve an elusive goal of sensor-based tremor assessment: improving on conventional visual observation in terms of sensitivity to change. Further refinement and evaluation of the proposed techniques is required, but our core findings imply that the main barrier to translational impact for this application can be overcome. Sensor-based tremor assessments may improve personalised treatment selection and the efficiency of clinical trials for new treatments by enabling greater standardisation and sensitivity to clinically relevant changes in symptoms.