An Automatic Gait Analysis Pipeline for Wearable Sensors: A Pilot Study in Parkinson's Disease.

The use of wearable sensors allows continuous recordings of physical activity from participants in free-living or at-home clinical studies. The large amount of data collected demands automatic analysis pipelines to extract gait parameters that can be used as clinical endpoints. We introduce a deep learning-based automatic pipeline for wearables that processes tri-axial accelerometry data and extracts gait events-bout segmentation, initial contact (IC), and final contact (FC)-from a single sensor located at either the lower back (near L5), shin or wrist. The gait events detected are posteriorly used for gait parameter estimation, such as step time, length, and symmetry. We report results from a leave-one-subject-out (LOSO) validation on a pilot study dataset of five participants clinically diagnosed with Parkinson's disease (PD) and six healthy controls (HC). Participants wore sensors at three body locations and walked on a pressure-sensing walkway to obtain reference gait data. Mean absolute errors (MAE) for the IC events ranged from 22.82 to 33.09 milliseconds (msecs) for the lower back sensor while for the shin and wrist sensors, MAE ranges were 28.56-64.66 and 40.19-72.50 msecs, respectively. For the FC-event detection, MAE ranges were 29.06-48.42, 40.19-72.70 and 36.06-60.18 msecs for the lumbar, wrist and shin sensors, respectively. Intraclass correlation coefficients, ICC(2,k), between the estimated parameters and the reference data resulted in good-to-excellent agreement (ICC ≥ 0.84) for the lumbar and shin sensors, excluding the double support time (ICC = 0.37 lumbar and 0.38 shin) and swing time (ICC = 0.55 lumbar and 0.59 shin). The wrist sensor also showed good agreements, but the ICCs were lower overall than for the other two sensors. Our proposed analysis pipeline has the potential to extract up to 100 gait-related parameters, and we expect our contribution will further support developments in the fields of wearable sensors, digital health, and remote monitoring in clinical trials.

Multimodal Classification of Parkinson's Disease in Home Environments with Resiliency to Missing Modalities.

Parkinson's disease (PD) is a chronic neurodegenerative condition that affects a patient's everyday life. Authors have proposed that a machine learning and sensor-based approach that continuously monitors patients in naturalistic settings can provide constant evaluation of PD and objectively analyse its progression. In this paper, we make progress toward such PD evaluation by presenting a multimodal deep learning approach for discriminating between people with PD and without PD. Specifically, our proposed architecture, named MCPD-Net, uses two data modalities, acquired from vision and accelerometer sensors in a home environment to train variational autoencoder (VAE) models. These are modality-specific VAEs that predict effective representations of human movements to be fused and given to a classification module. During our end-to-end training, we minimise the difference between the latent spaces corresponding to the two data modalities. This makes our method capable of dealing with missing modalities during inference. We show that our proposed multimodal method outperforms unimodal and other multimodal approaches by an average increase in F1-score of 0.25 and 0.09, respectively, on a data set with real patients. We also show that our method still outperforms other approaches by an average increase in F1-score of 0.17 when a modality is missing during inference, demonstrating the benefit of training on multiple modalities.

Distinct roles of dopamine and subthalamic nucleus in learning and probabilistic decision making.

Even simple behaviour requires us to make decisions based on combining multiple pieces of learned and new information. Making such decisions requires both learning the optimal response to each given stimulus as well as combining probabilistic information from multiple stimuli before selecting a response. Computational theories of decision making predict that learning individual stimulus-response associations and rapid combination of information from multiple stimuli are dependent on different components of basal ganglia circuitry. In particular, learning and retention of memory, required for optimal response choice, are significantly reliant on dopamine, whereas integrating information probabilistically is critically dependent upon functioning of the glutamatergic subthalamic nucleus (computing the 'normalization term' in Bayes' theorem). Here, we test these theories by investigating 22 patients with Parkinson's disease either treated with deep brain stimulation to the subthalamic nucleus and dopaminergic therapy or managed with dopaminergic therapy alone. We use computerized tasks that probe three cognitive functions-information acquisition (learning), memory over a delay and information integration when multiple pieces of sequentially presented information have to be combined. Patients performed the tasks ON or OFF deep brain stimulation and/or ON or OFF dopaminergic therapy. Consistent with the computational theories, we show that stopping dopaminergic therapy impairs memory for probabilistic information over a delay, whereas deep brain stimulation to the region of the subthalamic nucleus disrupts decision making when multiple pieces of acquired information must be combined. Furthermore, we found that when participants needed to update their decision on the basis of the last piece of information presented in the decision-making task, patients with deep brain stimulation of the subthalamic nucleus region did not slow down appropriately to revise their plan, a pattern of behaviour that mirrors the impulsivity described clinically in some patients with subthalamic nucleus deep brain stimulation. Thus, we demonstrate distinct mechanisms for two important facets of human decision making: first, a role for dopamine in memory consolidation, and second, the critical importance of the subthalamic nucleus in successful decision making when multiple pieces of information must be combined.

Slower rates of prism adaptation but intact aftereffects in patients with early to mid-stage Parkinson's disease.

There is currently mixed evidence on the effect of Parkinson's disease on motor adaptation. Some studies report that patients display adaptation comparable to age-matched controls, while others report a complete inability to adapt to novel sensory perturbations. Here, early to mid-stage Parkinson's patients were recruited to perform a prism adaptation task. When compared to controls, patients showed slower rates of initial adaptation but intact aftereffects. These results support the suggestion that patients with early to mid-stage Parkinson's disease display intact adaptation driven by sensory prediction errors, as shown by the intact aftereffect. But impaired facilitation of performance through cognitive strategies informed by task error, as shown by the impaired initial adaptation. These results support recent studies that suggest that patients with Parkinson's disease retain the ability to perform visuomotor adaptation, but display altered use of cognitive strategies to aid performance and generalises these previous findings to the classical prism adaptation task.

Acceptability of an In-home Multimodal Sensor Platform for Parkinson Disease: Nonrandomized Qualitative Study.

BACKGROUND: Parkinson disease (PD) symptoms are complex, gradually progressive, and fluctuate hour by hour. Home-based technological sensors are being investigated to measure symptoms and track disease progression. A smart home sensor platform, with cameras and wearable devices, could be a useful tool to use to get a fuller picture of what someone's symptoms are like. High-resolution video can capture the ground truth of symptoms and activities. There is a paucity of information about the acceptability of such sensors in PD. OBJECTIVE: The primary objective of our study was to explore the acceptability of living with a multimodal sensor platform in a naturalistic setting in PD. Two subobjectives are to identify any suggested limitations and to explore the sensors' impact on participant behaviors. METHODS: A qualitative study was conducted with an inductive approach using semistructured interviews with a cohort of PD and control participants who lived freely for several days in a home-like environment while continuously being sensed. RESULTS: This study of 24 participants (12 with PD) found that it is broadly acceptable to use multimodal sensors including wrist-worn wearables, cameras, and other ambient sensors passively in free-living in PD. The sensor that was found to be the least acceptable was the wearable device. Suggested limitations on the platform for home deployment included camera-free time and space. Behavior changes were noted by the study participants, which may have related to being passively sensed. Recording high-resolution video in the home setting for limited periods of time was felt to be acceptable to all participants. CONCLUSIONS: The results broaden the knowledge of what types of sensors are acceptable for use in research in PD and what potential limitations on these sensors should be considered in future work. The participants' reported behavior change in this study should inform future similar research design to take this factor into account. Collaborative research study design, involving people living with PD at every stage, is important to ensure that the technology is acceptable and that the data outcomes produced are ecologically valid and accurate. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1136/bmjopen-2020-041303.

Progression of monoaminergic dysfunction in Parkinson's disease: a longitudinal 18F-dopa PET study.

Post-mortem and neuroimaging studies in Parkinson's disease (PD) have shown involvement of the brain serotoninergic, noradrenergic and cholinergic pathways alongside the characteristic degeneration of nigrostriatal dopamine neurons. The rate of progression of the degenerative process in these extrastriatal areas is still unclear. We used (18)F-dopa PET, a marker of aromatic aminoacid decarboxylase activity in monoaminergic neurons, to assess longitudinal changes in tracer uptake in brain noradrenergic, serotoninergic and extrastriatal dopaminergic structures over a 3-year period in a group of early PD patients. Ten PD patients had (18)F-dopa PET twice: at baseline and again after 37.1±21.5 months follow up. A standard object map was used to extract tracer influx constants (Ki) in 11 striatal and extrastriatal regions. Progressive decreases in (18)F-dopa Ki occurred over the follow-up period in the majority of the investigated areas, the fastest annual declines occurring in putamen (8.1%), locus coeruleus (7.8%), and globus pallidus interna (7.7%). Caudate and hypothalamus showed 6.3% and 6.1% annual Ki declines, respectively. At baseline, some structures showed increased levels of (18)F-dopa uptake in PD compared to controls (internal pallidum, locus coeruleus), indicating possible compensatory upregulation of monoamine turnover. These increased levels had normalised (globus pallidus interna) or become subnormal (locus coeruleus) at follow-up suggesting exhaustion of these mechanisms within the first years of disease. Loss of monoaminergic function in extrastriatal regions, as reflected by(18)F-dopa PET, is delayed and occurs independently from nigrostriatal degeneration. When assessing the efficacy of novel neuroprotective agents on nigrostriatal dysfunction in PD, (18)F-dopa PET could provide supplementary information concerning function of extrastriatal monoaminergic structures.

Outcomes from stimulation of the caudal zona incerta and pedunculopontine nucleus in patients with Parkinson's disease.

INTRODUCTION: Axial symptoms including postural instability, falls and failure of gait initiation are some of the most disabling motor symptoms of Parkinson's disease (PD). We performed bilateral deep brain stimulation (DBS) of the pedunculopontine nucleus (PPN) in combination with the caudal zona incerta (cZi) in order to determine their efficacy in alleviating these symptoms. METHODS: Seven patients with predominant axial symptoms in both the 'on' and 'off' medication states underwent bilateral cZi and PPN DBS. Motor outcomes were assessed using the motor component of the Unified Parkinson's Disease Rating Scale (UPDRS 3) and a composite axial subscore was derived from items 27, 28, 29 and 30 (arising from chair, posture, gait and postural stability). Quality of life was measured using the PDQ39. Comparisons were made between scores obtained at baseline and those at a mean follow-up of 12 months. RESULTS: In both the off and on medication states, a statistically significant improvement in the UPDRS part 3 score was achieved by stimulation of the PPN, cZi and both in combination. In the off medication state, our composite axial subscore of the UPDRS part 3 improved with stimulation of the PPN, cZi and both in combination. The composite axial subscore, in the 'on' medication state, however, only showed a statistically significant improvement when a combination of cZi and PPN stimulation was used. CONCLUSIONS: This study provides evidence that a combination of PPN and cZi stimulation can achieve a significant improvement in the hitherto untreatable 'on' medication axial symptoms of PD.

A Neurologist's Guide to REM Sleep Behavior Disorder.

REM Sleep Behavior Disorder (RBD) is a chronic sleep condition characterized by dream enactment and loss of REM atonia. Individuals often present to clinic with complaints of injury to themselves or their bed-partner due to violent movements during sleep. RBD patients have a high risk of developing one of the neurodegenerative α-synucleinopathy diseases: over 70% will develop parkinsonism or dementia within 12 years of their diagnosis. RBD patients also exhibit accelerated disease progression and a more severe phenotype than α-synucleinopathy sufferers without RBD. The disease's low prevalence and the relatively limited awareness of the condition amongst medical professionals makes the diagnosis and treatment of RBD challenging. Uncertainty in patient management is further exacerbated by a lack of clinical guidelines for RBD patient care. There are no binary prognostic markers for RBD disease course and there are no clinical guidelines for neurodegeneration scaling or tracking in these patients. Both clinicians and patients are therefore forced to deal with uncertain outcomes. In this review, we summarize RBD pathology and differential diagnoses, diagnostic, and treatment guidelines as well as prognostic recommendations with a look to current research in the scientific field. We aim to raise awareness and develop a framework for best practice for RBD patient management.

Systematic Review Looking at the Use of Technology to Measure Free-Living Symptom and Activity Outcomes in Parkinson's Disease in the Home or a Home-like Environment.

BACKGROUND: The emergence of new technologies measuring outcomes in Parkinson's disease (PD) to complement the existing clinical rating scales has introduced the possibility of measurement occurring in patients' own homes whilst they freely live and carry out normal day-to-day activities. OBJECTIVE: This systematic review seeks to provide an overview of what technology is being used to test which outcomes in PD from free-living participant activity in the setting of the home environment. Additionally, this review seeks to form an impression of the nature of validation and clinimetric testing carried out on the technological device(s) being used. METHODS: Five databases (Medline, Embase, PsycInfo, Cochrane and Web of Science) were systematically searched for papers dating from 2000. Study eligibility criteria included: adults with a PD diagnosis; the use of technology; the setting of a home or home-like environment; outcomes measuring any motor and non-motor aspect relevant to PD, as well as activities of daily living; unrestricted/unscripted activities undertaken by participants. RESULTS: 65 studies were selected for data extraction. There were wide varieties of participant sample sizes (<10 up to hundreds) and study durations (<2 weeks up to a year). The metrics evaluated by technology, largely using inertial measurement units in wearable devices, included gait, tremor, physical activity, bradykinesia, dyskinesia and motor fluctuations, posture, falls, typing, sleep and activities of daily living. CONCLUSIONS: Home-based free-living testing in PD is being conducted by multiple groups with diverse approaches, focussing mainly on motor symptoms and sleep.

Freezing of Gait in People with Parkinson's Disease: Nature, Occurrence, and Risk Factors.

BACKGROUND: Freezing of gait (FOG) is a common symptom of Parkinson's disease (PD) which can result in falls and fall related injuries, poor quality of life and reduced functional independence. It is a heterogeneous phenomenon that is difficult to quantify and eludes a unified pathophysiological framework. OBJECTIVE: Our aim was to document the occurrence and nature of freezing, cognitive stops and stumbles in people with PD during walks with varying cognitive loads and conditions designed to elicit FOG. METHODS: 130 people with PD walked under four conditions (normal walking, walking plus easy and hard dual-tasks, and a FOG elicitation condition. Video and accelerometry recordings were examined to document freezes and other gait disruptions. RESULTS: Participants experienced 391 freezes, 97 cognitive stops and 73 stumbles in the trial walks; with total gait disruptions increasing with task complexity. Most freezes in the FOG elicitation condition occurred during turning and approach destination. People who experienced freezing during the walks were more likely to have Postural Instability and Gait Difficulty (PIGD) subtype, longer disease duration and more severe UPDRS part II and part III sub-scores than people who did not freeze. They also took higher doses of levodopa, reported freezing in the past month, more prior falls, had poorer executive function, poorer proprioception, slower reaction time, poorer standing and leaning balance, more depressive symptoms, lower quality of life and greater fear of falling. PD disease duration, reduced controlled leaning balance and poor proprioception were identified as independent and significant determinants of freezing in logistic regression analysis. CONCLUSION: The multiple motor and cognitive factors identified as being associated with freezing, including poor proprioception and impaired controlled leaning balance provide new insights into this debilitating PD symptom and may contribute to potential new targets for rehabilitation.