Instrumental analysis of finger tapping reveals a novel early biomarker of parkinsonism in idiopathic rapid eye movement sleep behaviour disorder

What the trained eye cannot see: Quantitative kinematics and machine learning detect movement deficits in early-stage Parkinson's disease from videos

BACKGROUND

Evaluation of disease severity in Parkinson's disease (PD) relies on motor symptoms quantification. However, during early-stage PD, these symptoms are subtle and difficult to quantify by experts, which might result in delayed diagnosis and suboptimal disease management.

OBJECTIVE

To evaluate the use of videos and machine learning (ML) for automatic quantification of motor symptoms in early-stage PD.

METHODS

We analyzed videos of three movement tasks-Finger Tapping, Hand Movement, and Leg Agility- from 26 aged-matched healthy controls and 31 early-stage PD patients. Utilizing ML algorithms for pose estimation we extracted kinematic features from these videos and trained three classification models based on left and right-side movements, and right/left symmetry. The models were trained to differentiate healthy controls from early-stage PD from videos.

RESULTS

Combining left side, right side, and symmetry features resulted in a PD detection accuracy of 79 % from Finger Tap videos, 75 % from Hand Movement videos, 79 % from Leg Agility videos, and 86 % when combining the three tasks using a soft voting approach. In contrast, the classification accuracy varied between 40 % and 72 % when the movement side or symmetry were not considered.

CONCLUSIONS

Our methodology effectively differentiated between early-stage PD and healthy controls using videos of standardized motor tasks by integrating kinematic analyses of left-side, right-side, and bilateral symmetry movements. These results demonstrate that ML can detect movement deficits in early-stage PD from videos. This technology is easy-to-use, highly scalable, and has the potential to improve the management and quantification of motor symptoms in early-stage PD.

Characterizing Disease Progression in Parkinson's Disease from Videos of the Finger Tapping Test

INTRODUCTION

Parkinson's disease (PD) is characterized by motor symptoms whose progression is typically assessed using clinical scales, namely the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Despite its reliability, the scale is bounded by a 5-point scale that limits its ability to track subtle changes in disease progression and is prone to subjective interpretations. We aimed to develop an automated system to objectively quantify motor symptoms in PD using Machine Learning (ML) algorithms to analyze videos and capture nuanced features of disease progression.

METHODS

We analyzed videos of the Finger Tapping test, a component of the MDS-UPDRS, from 24 healthy controls and 66 PD patients using ML algorithms for hand pose estimation. We computed multiple movement features related to bradykinesia from videos and employed a novel tiered classification approach to predict disease severity that employed different features according to severity. We compared our video-based disease severity prediction approach against other approaches recently introduced in the literature.

RESULTS

Traditional kinematics features such as amplitude and velocity changed linearly with disease severity, while other non-traditional features displayed non-linear trends. The proposed disease severity prediction approach demonstrated superior accuracy in detecting PD and distinguishing between different levels of disease severity when compared to existing approaches.

The Motor Dysfunction Seen in Isolated REM Sleep Behavior Disorder

BACKGROUND

Isolated Rapid Eye Movement (REM) sleep Behavior Disorder (iRBD) requires quantitative tools to detect incipient Parkinson's disease (PD).

METHODS

A motor battery was designed and compared with the Movement Disorder Society-Unified Parkinson's Disease Rating Scale part III (MDS-UPDRS-III) in people with iRBD and controls. This included two keyboard-based tests (BRadykinesia Akinesia INcoordination tap test and Distal Finger Tapping) and two dual tasking tests (walking and finger tapping).

RESULTS

We included 33 iRBD patients and 29 controls. The iRBD group performed both keyboard-based tapping tests more slowly (P < 0.001, P = 0.020) and less rhythmically (P < 0.001, P = 0.006) than controls. Unlike controls, the iRBD group increased their walking duration (P < 0.001) and had a smaller amplitude (P = 0.001) and slower (P = 0.007) finger tapping with dual task. The combination of the most salient motor markers showed 90.3% sensitivity for 89.3% specificity (area under the ROC curve [AUC], 0.94), which was higher than the MDS-UPDRS-III (minus action tremor) (69.7% sensitivity, 72.4% specificity; AUC, 0.81) for detecting motor dysfunction.

CONCLUSION

Speed, rhythm, and dual task motor deterioration might be accurate indicators of incipient PD in iRBD. © 2024 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Beyond timing and step counting in 360° turning-in-place assessment: a scoping review

BACKGROUND

Turning in place is a challenging motor task and is used as a brief assessment test of lower limb function and dynamic balance. This review aims to examine how research of instrumented analysis of turning in place is implemented. In addition to reporting the studied population, we covered acquisition systems, turn detection methods, quantitative parameters, and how these parameters are computed.

METHODS

Following the development of a rigorous search strategy, the Web of Science and Scopus were systematically searched for studies involving the use of turning-in-place. From the selected articles, the study population, types of instruments used, turn detection method, and how the turning-in-place characteristics were calculated.

RESULTS

Twenty-one papers met the inclusion criteria. The subject groups involved in the reviewed studies included young, middle-aged, and older adults, stroke, multiple sclerosis and Parkinson's disease patients. Inertial measurement units (16 studies) and motion camera systems (5 studies) were employed for gathering measurement data, force platforms were rarely used (2 studies). Two studies used commercial software for turn detection, six studies referenced previously published algorithms, two studies developed a custom detector, and eight studies did not provide any details about the turn detection method. The most frequently used parameters were mean angular velocity (14 cases, 7 studies), turn duration (13 cases, 13 studies), peak angular velocity (8 cases, 8 studies), jerkiness (6 cases, 5 studies) and freezing-of-gait ratios (5 cases, 5 studies). Angular velocities were derived from sensors placed on the lower back (7 cases, 4 studies), trunk (4 cases, 2 studies), and shank (2 cases, 1 study). The rest (9 cases, 8 studies) did not report sensor placement. Calculation of the freezing-of-gait ratio was based on the acceleration of the lower limbs in all cases. Jerkiness computation employed acceleration in the medio-lateral (4 cases) and antero-posterior (1 case) direction. One study did not reported any details about jerkiness computation.

CONCLUSION

This review identified the capabilities of turning-in-place assessment in identifying movement differences between the various subject groups. The results, based on data acquired by inertial measurement units across studies, are comparable. A more in-depth analysis of tests developed for gait, which has been adopted in turning-in-place, is needed to examine their validity and accuracy.

Identifying Subtle Motor Deficits Before Parkinson's Disease is Diagnosed: What to Look for?

Motor deficits typical of Parkinson's disease (PD), such as gait and balance disturbances, tremor, reduced arm swing and finger movement, and voice and breathing changes, are believed to manifest several years prior to clinical diagnosis. Here we describe the evidence for the presence and progression of motor deficits in this pre-diagnostic phase in order to provide suggestions for the design of future observational studies for an effective, quantitatively oriented investigation. On the one hand, these future studies must detect these motor deficits in as large (potentially, population-based) cohorts as possible with high sensitivity and specificity. On the other hand, they must describe the progression of these motor deficits in the pre-diagnostic phase as accurately as possible, to support the testing of the effect of pharmacological and non-pharmacological interventions. Digital technologies and artificial intelligence can substantially accelerate this process.

Considering REM Sleep Behavior Disorder in the Management of Parkinson's Disease

Rapid eye movement (REM) sleep behavior disorder (RBD) is the result of the loss of physiological inhibition of muscle tone during REM sleep, characterized by dream-enacting behavior and widely recognized as a prodromal manifestation of alpha-synucleinopathies. Indeed, patients with isolated RBD (iRBD) have an extremely high estimated risk to develop a neurodegenerative disease after a long follow up. Nevertheless, in comparison with PD patients without RBD (PDnoRBD), the occurrence of RBD in the context of PD (PDRBD) seems to identify a unique, more malignant phenotype, characterized by a more severe burden of disease in terms of both motor and non-motor symptoms and increased risk for cognitive decline. However, while some medications (eg, melatonin, clonazepam, etc.) and non-pharmacological options have been found to have some therapeutic benefits on RBD there is no available treatment able to modify the disease course or, at least, slow down the neurodegenerative process underlying phenoconversion. In this scenario, the long prodromal phase may allow an early therapeutic window and, therefore, the identification of multimodal biomarkers of disease onset and progression is becoming increasingly crucial. To date, several clinical (motor, cognitive, olfactory, visual, and autonomic features) neurophysiological, neuroimaging, biological (biofluids or tissue biopsy), and genetic biomarkers have been identified and proposed, also in combination, as possible diagnostic or prognostic markers, along with a potential role for some of them as outcome measures and index of treatment response. In this review, we provide an insight into the present knowledge on both existing and future biomarkers of iRBD and highlight the difference with PDRBD and PDnoRBD, including currently available treatment options.

Exploring the Complex Phenotypes of Impaired Finger Dexterity in Mild-to-moderate Stage Parkinson's Disease: A Time-Series Analysis

BACKGROUND

Impaired dexterity is an early motor symptom in Parkinson's disease (PD) that significantly impacts the daily activity of patients; however, what constitutes complex dexterous movements remains controversial.

OBJECTIVE

To explore the characteristics of finger dexterity in mild-to-moderate stage PD.

METHODS

We quantitatively assessed finger dexterity in 48 mild-to-moderate stage PD patients and 49 age-matched controls using a simple alternating two-finger typing test for 15 seconds. Time-series analyses of various kinematic parameters with machine learning were compared between sides and groups.

RESULTS

Both the more and less affected hands of patients with PD had significantly lower typing frequency and slower typing velocity than the non-dominant and the dominant hands of controls (p = 0.019, p = 0.016, p < 0.001, p < 0.001). The slope of the typing velocity decreased with time, indicating a sequence effect in the PD group. A typing duration of 6 seconds was determined sufficient to discriminate PD patients from controls. Typing error, repetition, and repetition rate were significantly higher in the more affected hands of patients with PD than in the non-dominant hand of controls (p < 0.001, p = 0.03, p < 0.001). The error rate was constant, whereas the repetition rate was steep during the initiation of typing. A predictive model of the more affected hand demonstrated an accuracy of 70% in differentiating PD patients from controls.

CONCLUSION

Our study demonstrated complex components of impaired finger dexterity in mild-to-moderate stage PD, namely bradykinesia with sequence effects, error, and repetition at the initiation of movement, suggesting that multiple neural networks may be involved in dexterity deficits in PD.

Deep Clinical Phenotyping of Parkinson's Disease: Towards a New Era of Research and Clinical Care

Despite recent advances in technology, clinical phenotyping of Parkinson's disease (PD) has remained relatively limited as current assessments are mainly based on empirical observation and subjective categorical judgment at the clinic. A lack of comprehensive, objective, and quantifiable clinical phenotyping data has hindered our capacity to diagnose, assess patients' conditions, discover pathogenesis, identify preclinical stages and clinical subtypes, and evaluate new therapies. Therefore, deep clinical phenotyping of PD patients is a necessary step towards understanding PD pathology and improving clinical care. In this review, we present a growing community consensus and perspective on how to clinically phenotype this disease, that is, to phenotype the entire course of disease progression by integrating capacity, performance, and perception approaches with state-of-the-art technology. We also explore the most studied aspects of PD deep clinical phenotypes, namely, bradykinesia, tremor, dyskinesia and motor fluctuation, gait impairment, speech impairment, and non-motor phenotypes.

Systematic quantitative assessment of motor function in clinically isolated REM sleep behaviour disorder: A diagnostic window into early alpha-synucleinopathies

Mild motor abnormalities can herald the beginning of Parkinson´s disease but their diagnostic value is limited by multifactorial ageing-related influences on motor function. We characterized mild motor abnormalities in different motor domains by conducting a systematic motor assessment in 20 patients with clinically isolated REM sleep behaviour disorder (iRBD) without parkinsonian motor signs and 20 healthy controls. We addressed the influence of lifestyle factors and age on motor function, which needs to be distinguished from neurodegenerative motor features, and assessed the diagnostic value of innovative and established quantitative motor tests in iRBD. Patients with iRBD showed abnormalities in perceptual motor speed (falling stick test), trunk movement coordination (bend, twist and touch test) and dynamic balance (line walk test) without alterations in simple motor speed (alternate tap test), dexterity (grooved pegboard), static balance (force plate) and gait (timed up and go test). The falling stick test showed the highest diagnostic accuracy in identifying subjects with RBD (ROC-AUC 0.85, p ≤ 0.001). Multivariate analysis revealed physical activity and age as additional determinants of motor test performance. iRBD comprises a wide spectrum of mild motor abnormalities which cannot be verified by established tests for motor speed, gait and balance. The falling stick test, an innovative screening test for perceptual motor speed, provides high diagnostic potential in identifying subjects with subclinical neurodegenerative symptoms before parkinsonian motor signs become apparent. Normative data for physical activity and age need to be obtained to ensure correct interpretation of motor test results in prodromal Parkinson-related disease.

Biomarkers of conversion to α-synucleinopathy in isolated rapid-eye-movement sleep behaviour disorder

Patients with isolated rapid-eye-movement sleep behaviour disorder (RBD) are commonly regarded as being in the early stages of a progressive neurodegenerative disease involving α-synuclein pathology, such as Parkinson's disease, dementia with Lewy bodies, or multiple system atrophy. Abnormal α-synuclein deposition occurs early in the neurodegenerative process across the central and peripheral nervous systems and might precede the appearance of motor symptoms and cognitive decline by several decades. These findings provide the rationale to develop reliable biomarkers that can better predict conversion to clinically manifest α-synucleinopathies. In addition, biomarkers of disease progression will be essential to monitor treatment response once disease-modifying therapies become available, and biomarkers of disease subtype will be essential to enable prediction of which subtype of α-synucleinopathy patients with isolated RBD might develop.

Motor Dysfunction in REM Sleep Behavior Disorder: A Rehabilitation Framework for Prodromal Synucleinopathy

Parkinson disease (PD) and other related diseases with α-synuclein pathology are associated with a long prodromal or preclinical stage of disease. Predictive models based on diagnosis of idiopathic rapid eye movement (REM) sleep behavior disorder (iRBD) make it possible to identify people in the prodromal stage of synucleinopathy who have a high probability of future disease and provide an opportunity to implement neuroprotective therapies. However, rehabilitation providers may be unaware of iRBD and the motor abnormalities that indicate early motor system dysfunction related to α-synuclein pathology. Furthermore, there is no existing rehabilitation framework to guide early interventions for people with iRBD. The purpose of this work is to (1) review extrapyramidal signs of motor system dysfunction in people with iRBD and (2) propose a framework for early protective or preventive therapies in prodromal synucleinopathy using iRBD as a predictive marker. Longitudinal and cross-sectional studies indicate that the earliest emerging motor deficits in iRBD are bradykinesia, deficits performing activities of daily living, and abnormalities in speech, gait, and posture. These deficits may emerge up to 12 years before a diagnosis of synucleinopathy. The proposed rehabilitation framework for iRBD includes early exercise-based interventions of aerobic exercise, progressive resistance training, and multimodal exercise with rehabilitation consultations to address exercise prescription, progression, and monitoring. This rehabilitation framework may be used to implement neuroprotective, multidisciplinary, and proactive clinical care in people with a high likelihood of conversion to PD, dementia with Lewy bodies, or multiple systems atrophy.