Deep learning of Parkinson's movement from video, without human-defined measures.

BACKGROUND: The core clinical sign of Parkinson's disease (PD) is bradykinesia, for which a standard test is finger tapping: the clinician observes a person repetitively tap finger and thumb together. That requires an expert eye, a scarce resource, and even experts show variability and inaccuracy. Existing applications of technology to finger tapping reduce the tapping signal to one-dimensional measures, with researcher-defined features derived from those measures. OBJECTIVES: (1) To apply a deep learning neural network directly to video of finger tapping, without human-defined measures/features, and determine classification accuracy for idiopathic PD versus controls. (2) To visualise the features learned by the model. METHODS: 152 smartphone videos of 10s finger tapping were collected from 40 people with PD and 37 controls. We down-sampled pixel dimensions and videos were split into 1 s clips. A 3D convolutional neural network was trained on these clips. RESULTS: For discriminating PD from controls, our model showed training accuracy 0.91, and test accuracy 0.69, with test precision 0.73, test recall 0.76 and test AUROC 0.76. We also report class activation maps for the five most predictive features. These show the spatial and temporal sections of video upon which the network focuses attention to make a prediction, including an apparent dropping thumb movement distinct for the PD group. CONCLUSIONS: A deep learning neural network can be applied directly to standard video of finger tapping, to distinguish PD from controls, without a requirement to extract a one-dimensional signal from the video, or pre-define tapping features.

Does serum neurofilament light help predict accelerated cognitive ageing in unimpaired older adults?

Introduction: Neurofilament light (NfL) is a blood biomarker of neurodegeneration. While serum NfL levels have been demonstrated to increase with normal ageing, the relationship between serum NfL levels and normal age-related changes in cognitive functions is less well understood. Methods: The current study investigated whether cross-sectional serum NfL levels measured by single molecule array technology (Simoa®) mediated the effect of age on cognition, measured by a battery of neuropsychological tests administered biannually for 8 years, in a cohort of 174 unimpaired older adults (≥50 years) from the Tasmanian Healthy Brain Project. Mediation analysis was conducted using latent variables representing cognitive test performance on three cognitive domains - episodic memory, executive function, and language (vocabulary, comprehension, naming). Cognitive test scores for the three domains were estimated for each participant, coincident with blood collection in 2018 using linear Bayesian hierarchical models. Results: Higher serum NfL levels were significantly positively associated with age (p < 0.001 for all domains). Cognitive test scores were significantly negatively associated with age across the domains of executive function (p < 0.001), episodic memory (p < 0.001) and language (p < 0.05). However, serum NfL levels did not significantly mediate the relationship between age and cognitive test scores across any of the domains. Discussion: This study adds to the literature on the relationship between serum NfL levels and cognition in unimpaired older adults and suggests that serum NfL is not a pre-clinical biomarker of ensuing cognitive decline in unimpaired older adults.

Parkinsonian Hand or Clinician's Eye? Finger Tap Bradykinesia Interrater Reliability for 21 Movement Disorder Experts.

BACKGROUND: Bradykinesia is considered the fundamental motor feature of Parkinson's disease (PD). It is central to diagnosis, monitoring, and research outcomes. However, as a clinical sign determined purely by visual judgement, the reliability of humans to detect and measure bradykinesia remains unclear. OBJECTIVE: To establish interrater reliability for expert neurologists assessing bradykinesia during the finger tapping test, without cues from additional examination or history. METHODS: 21 movement disorder neurologists rated finger tapping bradykinesia, by Unified Parkinson's Disease Rating Scale (MDS-UPDRS) and Modified Bradykinesia Rating Scale (MBRS), in 133 videos of hands: 73 from 39 people with idiopathic PD, 60 from 30 healthy controls. Each neurologist rated 30 randomly-selected videos. 19 neurologists were also asked to judge whether the hand was PD or control. We calculated intraclass correlation coefficients (ICC) for absolute agreement and consistency of MDS-UPDRS ratings, using standard linear and cumulative linked mixed models. RESULTS: There was only moderate agreement for finger tapping MDS-UPDRS between neurologists, ICC 0.53 (standard linear model) and 0.65 (cumulative linked mixed model). Among control videos, 53% were rated > 0 by MDS-UPDRS, and 24% were rated as bradykinesia by MBRS subscore combination. Neurologists correctly identified PD/control status in 70% of videos, without strictly following bradykinesia presence/absence. CONCLUSION: Even experts show considerable disagreement about the level of bradykinesia on finger tapping, and frequently see bradykinesia in the hands of those without neurological disease. Bradykinesia is to some extent a phenomenon in the eye of the clinician rather than simply the hand of the person with PD.

Sex-Specific Protective Effects of Cognitive Reserve on Age-Related Cognitive Decline: A 5-Year Prospective Cohort Study.

BACKGROUND AND OBJECTIVES: Females have a higher age-adjusted incidence of Alzheimer disease than males but the reasons for this remain unclear. One proposed contributing factor is that, historically, females had less access to education and, therefore, may accumulate less cognitive reserve. However, educational attainment is confounded by IQ, which in itself is a component of cognitive reserve and does not differ between sexes. Steeper age-related cognitive declines are associated with increased risk of dementia. We, therefore, evaluated the moderating effects of 2 proxies for cognitive reserve, education and IQ, on the steepness of age-related declining cognitive trajectories in unimpaired older males and females. METHODS: The Tasmanian Healthy Brain Project, a long-term cohort study, recruited healthy Australians aged 50-80 years without cognitive impairment. Baseline cognitive reserve was measured using educational history and IQ, measured by the Wechsler Test of Adult Reading, Full Scale Predicted IQ (WTAR-FSIQ). Cognitive trajectories for language, executive function, and episodic and working memory over 5 years were extracted from neuropsychological assessments. The adjusted effects of education, estimated IQ, and APOE allelic variant on cognitive trajectories were compared between males and females. RESULTS: Five hundred sixty-two individuals (mean [SD] age 60 [6.7] years; 68% male; 33% APOE ε4+) were followed up over 5 years with 1,924 assessments and 24,946 cognitive test scores (annualized attrition rate 6.6% per year). Estimated IQ correlated with years of education (p < 0.001). Estimated IQ interacted with sex to moderate age-related cognitive trajectories (p = 0.03; adjusted for education); lower IQ males experienced steeper declining trajectories than higher IQ males, but lower IQ females had similar steepness of declining trajectories to higher IQ females. Education was not associated with rate of cognitive decline (p = 0.67; adjusted for WTAR-FSIQ). There were no significant differences in age-related cognitive trajectories between APOE genotypes in either sex. DISCUSSION: IQ, a measure of cognitive reserve, predicted the steepness of declining cognitive trajectories in males only. Education did not explain as much variation in cognitive trajectories as IQ. Our findings do not support the hypothesis that historical sex disparities in access to education contribute to the higher female incidence of Alzheimer disease.

To the emergency room and back again: Circular healthcare pathways for acute functional neurological disorders.

BACKGROUND AND OBJECTIVES: Studies of Functional Neurological Disorders (FND) are usually outpatient-based. To inform service development, we aimed to describe patient pathways through healthcare events, and factors affecting risk of emergency department (ED) reattendance, for people presenting acutely with FND. METHODS: Acute neurology/stroke teams at a UK city hospital were contacted regularly over 8 months to log FND referrals. Electronic documentation was then reviewed for hospital healthcare events over the preceding 8 years. Patient pathways through healthcare events over time were mapped, and mixed effects logistic regression was performed for risk of ED reattendance within 1 year. RESULTS: In 8 months, 212 patients presented acutely with an initial referral suggesting FND. 20% had subsequent alternative diagnoses, but 162 patients were classified from documentation review as possible (17%), probable (28%) or definite (55%) FND. In the preceding 8 years, these 162 patients had 563 ED attendances and 1693 inpatient nights with functional symptoms, but only 26% were referred for psychological therapy, only 66% had a documented diagnosis, and care pathways looped around ED. Three better practice pathway steps were each associated with lower risk of subsequent ED reattendance: documented FND diagnosis (OR = 0.32, p = 0.004), referral to clinical psychology (OR = 0.35, p = 0.04) and outpatient neurology follow-up (OR = 0.25, p < 0.001). CONCLUSION: People that present acutely to a UK city hospital with FND tend to follow looping pathways through hospital healthcare events, centred around ED, with low rates of documented diagnosis and referral for psychological therapy. When better practice occurs, it is associated with lower risk of ED reattendance.

Accuracy of Smartphone Video for Contactless Measurement of Hand Tremor Frequency.

BACKGROUND: Computer vision can measure movement from video without the time and access limitations of hospital accelerometry/electromyography or the requirement to hold or strap a smartphone accelerometer. OBJECTIVE: To compare computer vision measurement of hand tremor frequency from smartphone video with a gold standard measure accelerometer. METHODS: A total of 37 smartphone videos of hands, at rest and in posture, were recorded from 15 participants with tremor diagnoses (9 Parkinson's disease, 5 essential tremor, 1 functional tremor). Video pixel movement was measured using the computing technique of optical flow, with contemporaneous accelerometer recording. Fast Fourier transform and Bland-Altman analysis were applied. Tremor amplitude was scored by 2 clinicians. RESULTS: Bland-Altman analysis of dominant tremor frequency from smartphone video compared with accelerometer showed excellent agreement: 95% limits of agreement -0.38 Hz to +0.35 Hz. In 36 of 37 videos (97%), there was <0.5 Hz difference between computer vision and accelerometer measurement. There was no significant correlation between the level of agreement and tremor amplitude. CONCLUSION: The study suggests a potential new, contactless point-and-press measure of tremor frequency within standard clinical settings, research studies, or telemedicine.

Management of Secondary Poor Response to Botulinum Toxin in Cervical Dystonia: A Multicenter Audit.

BACKGROUND: Botulinum toxin A (BoNT-A) is an effective treatment for cervical dystonia. Nevertheless, up to 30% to 40% patients discontinue treatment, often because of poor response. The British Neurotoxin Network (BNN) recently published guidelines on the management of poor response to BoNT-A in cervical dystonia, but adherence to these guidelines has not yet been assessed. OBJECTIVES: To assess adherence to and usefulness of BNN guidelines in clinical practice. METHODS: We undertook a retrospective medical notes audit of adherence to the BNN guidelines in 3 United Kingdom tertiary neurosciences centers. RESULTS: Of 76 patients identified with poor response, 42 (55%) had a suboptimal response and, following BNN recommendations, 25 of them (60%) responded to adjustments in BoNT dose, muscle selection or injection technique. Of the remaining 34 (45%) patients with no BoNT response, 20 (59%) were tested for immune resistance, 8 (40%) of whom showed resistance. Fourteen (18%) of all patients were switched to BoNT-B, and 27 (36%) were referred for deep brain stimulation surgery. In those not immune to BoNT-A, clinical improvement was seen in 5 (41%) after adjusting their dose and injection technique. CONCLUSION: Our audit shows that optimizing BoNT dose or injection strategy largely led to improvements in those with suboptimal response and in those reporting no response without resistance. It would be helpful to standardize investigations of potential resistance in those with no therapeutic response.

Significant cognitive decline in Parkinson's disease exacerbates the reliance on visual feedback during upper limb reaches.

While upper limb reaches are often made in a feed-forward manner, visual feedback during the movement can be used to guide the reaching hand towards a target. In Parkinson's disease (PD), there is evidence that the utilisation of this visual feedback is increased. However, it is unclear if this is due solely to the characteristic slowness of movements in PD providing more opportunity for incorporating visual feedback to modify reach trajectories, or whether it is due to cognitive decline impacting (feed-forward) movement planning ability. To investigate this, we compared reaction times and movement times of reaches to a target in groups of PD patients with normal cognition (PD-NC), mild cognitive impairment (PD-MCI) or dementia (PD-D), to that of controls with normal cognition (CON-NC) or mild cognitive impairment (CON-MCI). Reaches were undertaken with full visual feedback (at a 'natural' and 'fast-as-possible' pace); with reduced visual feedback of the reaching limb to an illuminated target; and without any visual feedback to a remembered target with eyes closed. The PD-D group exhibited slower reaction times than all other groups across conditions, indicative of less efficient movement planning. When reaching to a remembered target with eyes closed, all PD groups exhibited slower movement times relative to their natural pace with full visual feedback. Crucially, this relative slowing was most pronounced for the PD-D group, compared to the PD-MCI and PD-NC groups, suggesting that substantial cognitive decline in PD exacerbates dependence on visual feedback during upper limb reaches.

Seeing the unseen: Could Eulerian video magnification aid clinician detection of subclinical Parkinson's tremor?

INTRODUCTION: Eulerian magnification amplifies very small movements in video, revealing otherwise invisible motion. This raises the possibility that it could enable clinician visualisation of subclinical tremor using a standard camera. We tested whether Eulerian magnification of apparently atremulous hands reveals a Parkinsonian tremor more frequently in Parkinson's than in controls. METHOD: We applied Eulerian magnification to smartphone video of 48 hands that appeared atremulous during recording (22 hands from 11 control participants, 26 hands from 17 idiopathic Parkinson's participants). Videos were rated for Parkinsonian tremor appearance (yes/no) before and after Eulerian magnification by three movement disorder specialist neurologists. RESULTS: The proportion of hands correctly classified as Parkinsonian or not by clinicians was significantly higher after Eulerian magnification (OR = 2.67; CI = [1.39, 5.17]; p < 0.003). Parkinsonian-appearance tremors were seen after magnification in a number of control hands, but the proportion was greater in the Parkinson's hands. CONCLUSION: Eulerian magnification slightly improves clinician ability to identify apparently atremulous hands as Parkinsonian. This suggests that some of the apparent tremor revealed may be subclinical Parkinson's (pathological) tremor, and Eulerian magnification may represent a first step towards contactless visualisation of such tremor. However, the technique also reveals apparent tremor in control hands. Therefore, our method needs additional elaboration and would not be of direct clinical use in its current iteration.

The discerning eye of computer vision: Can it measure Parkinson's finger tap bradykinesia?

OBJECTIVE: The worldwide prevalence of Parkinson's disease is increasing. There is urgent need for new tools to objectively measure the condition. Existing methods to record the cardinal motor feature of the condition, bradykinesia, using wearable sensors or smartphone apps have not reached large-scale, routine use. We evaluate new computer vision (artificial intelligence) technology, DeepLabCut, as a contactless method to quantify measures related to Parkinson's bradykinesia from smartphone videos of finger tapping. METHODS: Standard smartphone video recordings of 133 hands performing finger tapping (39 idiopathic Parkinson's patients and 30 controls) were tracked on a frame-by-frame basis with DeepLabCut. Objective computer measures of tapping speed, amplitude and rhythm were correlated with clinical ratings made by 22 movement disorder neurologists using the Modified Bradykinesia Rating Scale (MBRS) and Movement Disorder Society revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS). RESULTS: DeepLabCut reliably tracked and measured finger tapping in standard smartphone video. Computer measures correlated well with clinical ratings of bradykinesia (Spearman coefficients): -0.74 speed, 0.66 amplitude, -0.65 rhythm for MBRS; -0.56 speed, 0.61 amplitude, -0.50 rhythm for MDS-UPDRS; -0.69 combined for MDS-UPDRS. All p < .001. CONCLUSION: New computer vision software, DeepLabCut, can quantify three measures related to Parkinson's bradykinesia from smartphone videos of finger tapping. Objective 'contactless' measures of standard clinical examinations were not previously possible with wearable sensors (accelerometers, gyroscopes, infrared markers). DeepLabCut requires only conventional video recording of clinical examination and is entirely 'contactless'. This next generation technology holds potential for Parkinson's and other neurological disorders with altered movements.

Health at the writing desk of John Ruskin: a study of handwriting and illness.

Though John Ruskin (1819-1900) is remembered principally for his work as a theorist, art critic and historian of visual culture, he wrote exhaustively about his health in his correspondence and diaries. Ruskin was prone to recurring depressive and hypochondriacal feelings in his youth and adulthood. In 1871, at the age of 52 years, he developed an illness with relapsing psychiatric and neurological features. He had a series of attacks of brain disturbance, and a deterioration of his mental faculties affected his writing for years before curtailing his career a decade before he died. Previous writers have suggested he had a psychiatric malady, perhaps schizophrenia or schizoaffective disorder. But the more obvious conclusion from a close medical reading of Ruskin's descriptions of his illness is he had some sort of 'organic' brain illness. This paper aims to give insight into the relationship between Ruskin's state of well-being and the features of his writing through a palaeographical study of his letters and diary entries. We examine the handwriting for physical traces of Ruskin's major brain illness, guided by the historical narrative of the illness. We also examine Ruskin's recording of his experiences for what they reveal about the failure of his health and its impact on his work. Ruskin's handwriting does not have clear-cut pathological features before around 1885, though suggestions of subtle writing deficits were present as early as 1876. After 1887, Ruskin's handwriting shows fixed pathological signs-tremor, disturbed letter formation and features that reflect a slow and laborious process of writing. These observations are more than could be explained by normal ageing, and suggest the presence of a neurological deficit affecting writing control. Our findings are consistent with conclusions that we drew from the historical record-that John Ruskin had an organic neurological disorder with cognitive, behavioural, psychiatric and motor effects.

Inferring the long duration response to levodopa in Parkinson's disease.

INTRODUCTION: The long duration response to levodopa in Parkinson's disease outlasts drug elimination by days to weeks. Though a substantive part of anti-parkinsonian motor benefit, it cannot easily be observed. OBJECTIVES: To infer the magnitude of the long duration response during the first decade of Parkinson's disease and identify factors that influence it. METHODS: Serial practically defined off scores of 24 patients from a longitudinal study of levodopa short duration response were used to establish their rate of motor progression. A line of notional untreated disability (as if drug treatment had never been given) with the same progression gradient was the basis for calculation of the long duration response. Predictors of mean long duration response amplitude were identified using a multiple linear regression model. RESULTS: Over a mean treatment period of 16.6 ±â€¯4.4 years, annual increase in motor disability was 2.3% of the maximum score. The long duration response composed 49% of total levodopa response during the first decade of treatment, and this proportion was significantly higher soon after commencing levodopa (p = 0.001). Higher pre-treatment motor score (r = 0.60) and lower MMSE (r = 0.60) were the main predictors of a larger long duration response. There was little correlation between long and short duration responses. CONCLUSIONS: Long duration responses contribute almost half of the total levodopa benefit during the first decade of treatment. An appreciation of both long and short duration components of drug symptomatic effects is important in clinical trial design to investigate possible neuroprotective treatments.

A History of Dystonia: Ancient to Modern.

Before 1911, when Hermann Oppenheim introduced the term dystonia, this movement disorder lacked a unifying descriptor. While words like epilepsy, apoplexy, and palsy have had their meanings since antiquity, references to dystonia are much harder to identify in historical documents. Torticollis is an exception, although there is difficulty distinguishing dystonic torticollis from congenital muscular torticollis. There are, nevertheless, possible representations of dystonia in literature and visual art from the pre-modern world. Eighteenth century systematic nosologists such as Linnaeus, de Sauvages, and Cullen had attempted to classify some spasmodic conditions, including torticollis. But only after Charcot's contributions to clinical neuroscience were the various forms of generalized and focal dystonia clearly delineated. They were categorized as névroses: Charcot's term for conditions without an identifiable neuroanatomical cause. For a time thereafter, psychoanalytic models of dystonia based on Freud's ideas about unconscious conflicts transduced into physical symptoms were ascendant, although there was always a dissenting "organic" school. With the rise of subspecialization in movement disorders during the 1970s, the pendulum swung strongly back toward organic causation. David Marsden's clinical and electrophysiological research on the adult-onset focal dystonias was particularly important in establishing a physical basis for these disorders. We are still in a period of "living history" of dystonia, with much yet to be understood about pathophysiology. Rigidly dualistic models have crumbled in the face of evidence of electrophysiological and psychopathological overlap between organic and functional dystonia. More flexible biopsychosocial frameworks may address the demand for new diagnostic and therapeutic rationales.

A New Evolutionary Algorithm-Based Home Monitoring Device for Parkinson's Dyskinesia.

Parkinson's disease (PD) is a neurodegenerative movement disorder. Although there is no cure, symptomatic treatments are available and can significantly improve quality of life. The motor, or movement, features of PD are caused by reduced production of the neurotransmitter dopamine. Dopamine deficiency is most often treated using dopamine replacement therapy. However, this therapy can itself lead to further motor abnormalities referred to as dyskinesia. Dyskinesia consists of involuntary jerking movements and muscle spasms, which can often be violent. To minimise dyskinesia, it is necessary to accurately titrate the amount of medication given and monitor a patient's movements. In this paper, we describe a new home monitoring device that allows dyskinesia to be measured as a patient goes about their daily activities, providing information that can assist clinicians when making changes to medication regimens. The device uses a predictive model of dyskinesia that was trained by an evolutionary algorithm, and achieves AUC>0.9 when discriminating clinically significant dyskinesia.

Using epigenetic networks for the analysis of movement associated with levodopa therapy for Parkinson's disease.

Levodopa is a drug that is commonly used to treat movement disorders associated with Parkinson's disease. Its dosage requires careful monitoring, since the required amount changes over time, and excess dosage can lead to muscle spasms known as levodopa-induced dyskinesia. In this work, we investigate the potential for using epiNet, a novel artificial gene regulatory network, as a classifier for monitoring accelerometry time series data collected from patients undergoing levodopa therapy. We also consider how dynamical analysis of epiNet classifiers and their transitions between different states can highlight clinically useful information which is not available through more conventional data mining techniques. The results show that epiNet is capable of discriminating between different movement patterns which are indicative of either insufficient or excessive levodopa.

Study of levodopa response in Parkinson's disease: Observations on rates of motor progression.

INTRODUCTION: It is important to understand how the rate of motor progression in PD relates to dopaminergic treatment. METHODS: The methods for this study comprised prospective defined off state measurements of the levodopa response at 3-year intervals over a mean 13.3-year period in 34 patients enrolled before treatment initiation. RESULTS: Despite worsening of on and off scores, the magnitude of the l-dopa short-duration response is maintained as the disease progresses. A linear mixed-effects regression analysis of off phase motor scores showed a yearly deterioration of 2.3% of the maximum disability score. Greater motor disability at the commencement of treatment was an independent predictor of faster progression. Demented patients had worse motor function than those without dementia (P = 0.02), and motor deficit appeared to accelerate toward the end of the disease course in patients who had died. CONCLUSIONS: These observations should inform clinical trial design for drugs with possible neuroprotective properties.

Which figure copy test is more sensitive for cognitive impairment in Parkinson's disease: Wire cube or interlocking pentagons?

BACKGROUND: Performance on figure copy tests has been shown to predict progressive cognitive decline in Parkinson's disease (PD). Historically, the interlocking pentagons from the Mini Mental State Exam (MMSE) have been the figure copy test most commonly used during cognitive screening evaluations. However, the wire cube from the Montreal Cognitive Assessment (MoCA) is increasingly being used. OBJECTIVE: To evaluate which of these figure copy tests is more sensitive for cognitive impairment in PD. METHODS: Sixty-three PD patients from UK and USA completed the MMSE and MoCA. Logistic regression and sensitivity/specificity analyses were used to evaluate the utility of each figure copy test for detecting global cognitive impairment. RESULTS: The wire cube was a significant indicator of cognitive impairment (OR=4.79, 95% CI=1.63-14.07, p=0.004), with a sensitivity/specificity of 0.74/0.63 in our sample. In contrast, interlocking pentagons were not a significant indicator of cognitive impairment (OR=1.88, 95% CI=0.54-6.50, p=0.32), with a sensitivity/specificity of 0.26/0.84. CONCLUSION: The wire cube is more sensitive to cognitive impairment in PD, most likely related to its greater complexity. The results have implications for clinicians who may have time for just one figure copying task as part of a brief screen for cognitive impairment in busy clinics and for researchers applying the PD mild cognitive impairment diagnostic criteria necessitating two tests of visuospatial function to be administered.

Computational approaches for understanding the diagnosis and treatment of Parkinson's disease.

This study describes how the application of evolutionary algorithms (EAs) can be used to study motor function in humans with Parkinson's disease (PD) and in animal models of PD. Human data is obtained using commercially available sensors via a range of non-invasive procedures that follow conventional clinical practice. EAs can then be used to classify human data for a range of uses, including diagnosis and disease monitoring. New results are presented that demonstrate how EAs can also be used to classify fruit flies with and without genetic mutations that cause Parkinson's by using measurements of the proboscis extension reflex. The case is made for a computational approach that can be applied across human and animal studies of PD and lays the way for evaluation of existing and new drug therapies in a truly objective way.