Feasibility and Efficacy of Online Neuropsychological Assessment.

Neuropsychological testing has intrinsic challenges, including the recruitment of patients and their participation in research projects. To create a method capable of collecting multiple datapoints (across domains and participants) while imposing low demands on the patients, we have developed PONT (Protocol for Online Neuropsychological Testing). Using this platform, we recruited neurotypical controls, individuals with Parkinson's disease, and individuals with cerebellar ataxia and tested their cognitive status, motor symptoms, emotional well-being, social support, and personality traits. For each domain, we compared each group to previously published values from studies using more traditional methods. The results show that online testing using PONT is feasible, efficient, and produces results that are in line with results obtained from in-person testing. As such, we envision PONT as a promising bridge to more comprehensive, generalizable, and valid neuropsychological testing.

Stack Ensemble Oriented Parkinson Disease Prediction Using Machine Learning Approaches Utilizing GridSearchCV-Based Hyper Parameter Tuning.

Since the coronavirus came into existence and brought the entire world to a standstill, there have been drastic changes in people's lives that continue to affect them even as the pandemic recedes. The isolation reduced physical activity and hindered access to non-COVID related healthcare during lockdown and the ensuing months brought increased attention to mental health and the neurological disorders that might have been exacerbated. One nervous system disorder that affects the elderly and needs better awareness is Parkinson's disease. We have machine learning and a growing number of deep learning models to predict, and detect its onset; their scope is not completely exhaustive and can still be optimized. In this research, the authors highlight techniques that have been implemented in recent years for prediction of the disease. Models based on the less redundantly used classifiers-naive Bayes, logistic regression, linear-support vector machine, kernelizing support vector machine, and multilayer perceptron-are initially implemented and compared. Based on limitations of the results, an ensemble stack model of hyper-tuned versions using GridSearchCV out of the top performing supervised classifiers along-with extreme gradient boosting classifier is implemented to further improve overall results. In addition, a convolutional neural network-based model is also implemented, and the results are analyzed using two epoch values to compare the performance of deep learning models. The benchmark datasets-UCI Parkinson's data and the spiral and wave datasets-have been used for machine and deep learning respectively. Performance metrics like accuracy, precision, recall, support, and F1 score are utilized, and confusion matrices and graphs are plotted for visualization. 94.87% accuracy was achieved using the stacking approach.

Links between COVID-19 and Parkinson's disease/Alzheimer's disease: reciprocal impacts, medical care strategies and underlying mechanisms.

The impact of coronavirus disease 2019 (COVID-19) pandemic on patients with neurodegenerative diseases and the specific neurological manifestations of COVID-19 have aroused great interest. However, there are still many issues of concern to be clarified. Therefore, we review the current literature on the complex relationship between COVID-19 and neurodegenerative diseases with an emphasis on Parkinson's disease (PD) and Alzheimer's disease (AD). We summarize the impact of COVID-19 infection on symptom severity, disease progression, and mortality rate of PD and AD, and discuss whether COVID-19 infection could trigger PD and AD. In addition, the susceptibility to and the prognosis of COVID-19 in PD patients and AD patients are also included. In order to achieve better management of PD and AD patients, modifications of care strategies, specific drug therapies, and vaccines during the pandemic are also listed. At last, mechanisms underlying the link of COVID-19 with PD and AD are reviewed.

When brain devices go wrong: a patient with a malfunctioning deep brain stimulator (DBS) presents to the emergency department.

A man in his 50s attended the emergency department with an acute deterioration in his Parkinson's symptoms, presenting with limb rigidity, widespread tremor, choreiform dyskinesia, dysarthria, intense sadness and a severe occipital headache. After excluding common differentials for sudden-onset parkinsonism (eg, infection, medication change), an error on the patient's deep brain stimulator was noted. The patient's symptoms only resolved once he was transferred to the specialist centre so that the programmer could reset the device settings. Due to COVID-19-related bed pressures on the ward, there was a delay in the patient receiving specialist attention-highlighting the need for non-specialist training in the emergency management of device errors.

Excess deaths from Alzheimer's disease and Parkinson's disease during the COVID-19 pandemic in the USA.

BACKGROUND: COVID-19 pandemic has indirect impacts on patients with chronic medical conditions, which may increase mortality risks for various non-COVID-19 causes. This study updates excess death statistics for Alzheimer's disease (AD) and Parkinson's disease (PD) up to 2022 and evaluates their demographic and spatial disparities in the USA. METHODS: This is an ecological time-series analysis of AD and PD mortality in the USA from January 2018 to March 2022. Poisson log-linear regressions were utilised to fit the weekly death data. Excess deaths were calculated with the difference between the observed and expected deaths under a counterfactual scenario of pandemic absence. RESULTS: From March 2020 to March 2022, we observed 41,115 and 10,328 excess deaths for AD and PD, respectively. The largest percentage increases in excess AD and PD deaths were found in the initial pandemic wave. For people aged ≥85 years, excess mortalities of AD and PD (per million persons) were 3946.0 (95% confidence interval [CI]: 2954.3, 4892.3) and 624.3 (95% CI: 369.4, 862.5), which were about 23 and 9 times higher than those aged 55-84 years, respectively. Females had a three-time higher excess mortality of AD than males (182.6 vs. 67.7 per million persons). The non-Hispanic Black people experienced larger increases in AD or PD deaths (excess percentage: 31.8% for AD and 34.6% for PD) than the non-Hispanic White population (17.1% for AD and 14.7% for PD). CONCLUSION: Under the continuing threats of COVID-19, efforts should be made to optimise health care capacity for patients with AD and PD.

A pilot study of a 12-week community-based boxing program for Parkinson's disease.

INTRODUCTION: Community-based exercise programs for Parkinson's disease (PD) have gained popularity. Our understanding of such programs on non-motor features is limited. We characterized the effect of a 12-week community-based boxing exercise program on motor and non-motor symptoms in people with Parkinson's disease (PwPD). METHODS: In this prospective observational study, PwPD underwent a 12-week community-based boxing program (2 sessions per week, for a total of 24 sessions). The following assessments were performed by a movement disorders neurologist at baseline and after completion of the program: MDS-Unified Parkinson's Disease Rating Scale part III (MDS-UPDRS III) in a modified version since assessments were performed virtually due to COVID-19 pandemic, MDS Non-Motor Rating Scale (MDS-NMS), Hamilton Depression Rating Scale (HDRS), Lilli Apathy Rating Scale (LARS), Parkinson's Disease Questionaire-39 (PDQ-39), and Schwab and England Activities of Daily Living scale (SE-ADL). Pre- and post-assessments were compared using Wilcoxon signed rank test; only participants who completed the program and both assessments were analyzed. RESULTS: A total of 14 PwPD agreed to be a part of the study and completed assessments. All participants were ambulatory and functionally independent at baseline. Total non-motor feature severity (MDS-NMS, p = 0.0031), depression (HDRS, p = 0.015), and motor features (MDS-UPDRS PART 3 modified, p = 0.023) all improved significantly after the intervention. Scales on apathy (LARS, p = 0.29), Parkinson's disease-specific health related quality (PDQ-39, p = 0.093), and activities of daily living (SE-ADL, p = 0.32) did not demonstrate significant change. CONCLUSION: PwPD who participated in a community-based, pilot boxing program showed improvements in motor exam and non-motor symptoms.

Acute Worsening of Atypical Parkinson's Syndrome After Receiving Second Dose of Moderna COVID-19 Vaccine.

INTRODUCTION: Atypical Parkinson's syndromes are a rare set of neurodegenerative conditions in which a patient experiences the typical symptoms of Parkinson's disease, in addition to various other unrelated issues. CASE PRESENTATION: We present the case of a 71-year-old White man with a 1-year history of weakness and upper extremity tremors that, per patient report, rapidly worsened after receiving the second dose of the Moderna COVID-19 vaccine. His symptoms were consistent with an asymmetric atypical Parkinson's disease, with electromyogram results indicating chronic motor neuron involvement. DISCUSSION: There have been multiple reports of deterioration in patients with Parkinson's disease and atypical Parkinson's syndromes in response to contracting COVID-19. However, there are few, if any, case reports that describe an acute change in Parkinson-related symptoms in association with the COVID-19 vaccines. CONCLUSIONS: As the pandemic continues, we must continue to remain vigilant as we learn more about the long-lasting effects of the virus and vaccines.

Development and Assessment of a Movement Disorder Simulator Based on Inertial Data.

The detection analysis of neurodegenerative diseases by means of low-cost sensors and suitable classification algorithms is a key part of the widely spreading telemedicine techniques. The choice of suitable sensors and the tuning of analysis algorithms require a large amount of data, which could be derived from a large experimental measurement campaign involving voluntary patients. This process requires a prior approval phase for the processing and the use of sensitive data in order to respect patient privacy and ethical aspects. To obtain clearance from an ethics committee, it is necessary to submit a protocol describing tests and wait for approval, which can take place after a typical period of six months. An alternative consists of structuring, implementing, validating, and adopting a software simulator at most for the initial stage of the research. To this end, the paper proposes the development, validation, and usage of a software simulator able to generate movement disorders-related data, for both healthy and pathological conditions, based on raw inertial measurement data, and give tri-axial acceleration and angular velocity as output. To present a possible operating scenario of the developed software, this work focuses on a specific case study, i.e., the Parkinson's disease-related tremor, one of the main disorders of the homonym pathology. The full framework is reported, from raw data availability to pathological data generation, along with a common machine learning method implementation to evaluate data suitability to be distinguished and classified. Due to the development of a flexible and easy-to-use simulator, the paper also analyses and discusses the data quality, described with typical measurement features, as a metric to allow accurate classification under a low-performance sensing device. The simulator's validation results show a correlation coefficient greater than 0.94 for angular velocity and 0.93 regarding acceleration data. Classification performance on Parkinson's disease tremor was greater than 98% in the best test conditions.

[Telecare in Parkinson's disease: A nationwide survey among Hungarian neurologists]. / Távellátás Parkinson-kórban: országos felmérés a magyar neurológusok körében.

Background and purpose: COVID-19 has made providing in-person care difficult. In most countries, including Hungary, telemedicine has partly served as a resolution for this issue. Our purpose was to explore the effects of COVID-19 on neurological care, the knowledge of neurology specialists on telemedicine, and the present state of telecare in Hungary, with a special focus on Parkinson's disease (PD). Methods: Between July and October 2021, a nationwide online survey was conducted among actively practicing Hungarian neurology specialists who were managing patients with PD. Results: A total of 104 neurologists were surveyed. All levels of care were evaluated in both publicly funded and private healthcare. Both time weekly spent on outpatient specialty consultation and the number of patients with PD seen weekly significantly decreased in public healthcare, while remained almost unchanged in private care (p<0.001); higher portion of patients were able to receive in-person care in private care (78.8% vs. 90.8%, p<0.001). In telecare, prescribing medicines has already been performed by the most (n=103, 99%). Electronic messages were the most widely known telemedicine tools (n=98, 94.2%), while phone call has already been used by most neurologists (n=95, 91.3%). Video-based consultation has been more widely used in private than public care (30.1% vs. 15.5%, p=0.001). Teleprocedures were considered most suitable for monitoring progression and symptoms of Parkinson's disease and evaluating the need for adjustments to antiparkinsonian pharmacotherapy. Conclusion: COVID-19 has had a major impact on the care of patients with PD in Hungary. Telemedicine has mitigated these detrimental effects; however, further developments could make it an even more reliable component of care.

Assessment of Risk Factors and Early Presentations of Parkinson Disease in Primary Care in a Diverse UK Population.

IMPORTANCE: Early features of Parkinson disease (PD) have been described through population-based studies that overrepresent White, affluent groups and may not be generalizable. OBJECTIVE: To investigate the association between risk factors and prediagnostic presentations of PD in an ethnically diverse UK population with high socioeconomic deprivation but universal access to health care. DESIGN, SETTING, AND PARTICIPANTS: A nested case-control study was conducted using electronic health care records on 1 016 277 individuals from primary care practices in East London to extract clinical information recorded between 1990 and February 6, 2018. The data were analyzed between September 3, 2020, and September 3, 2021. Individuals with a diagnosis of PD were compared with controls without PD or other major neurological conditions. MAIN OUTCOMES AND MEASURES: A matched analysis (10 controls matched for each patient with PD according to age and sex) and an unmatched analysis (adjusted for age and sex) were undertaken using multivariable logistic regression to determine associations between risk factors and prediagnostic presentations to primary care with subsequent diagnosis of PD. Three time periods (<2, 2-<5, and 5-10 years before diagnosis) were analyzed separately and together. RESULTS: Of 1 016 277 individuals included in the data set, 5699 were excluded and 1055 patients with PD and 1 009 523 controls were included in the analysis. Patients with PD were older than controls (mean [SD], 72.9 [11.3] vs 40.3 [15.2] years), and more were male (632 [59.9%] vs 516 862 [51.2%]). In the matched analysis (1055 individuals with PD and 10 550 controls), associations were found for tremor (odds ratio [OR], 145.96; 95% CI, 90.55-235.28) and memory symptoms (OR, 8.60; 95% CI, 5.91-12.49) less than 2 years before the PD diagnosis. The associations were also found up to 10 years before PD diagnosis for tremor and 5 years for memory symptoms. Among midlife risk factors, hypertension (OR, 1.36; 95% CI, 1.19-1.55) and type 2 diabetes (OR, 1.39; 95% CI, 1.19-1.62) were associated with subsequent diagnosis of PD. Associations with early nonmotor features, including hypotension (OR, 6.84; 95% CI, 3.38-13.85), constipation (OR, 3.29; 95% CI, 2.32-4.66), and depression (OR, 4.69; 95% CI, 2.88-7.63), were also noted. Associations were found for epilepsy (OR, 2.5; 95% CI, 1.63-3.83) and hearing loss (OR, 1.66; 95% CI, 1.06-2.58), which have not previously been well reported. These findings were replicated using data from the UK Biobank. No association with future PD diagnosis was found for ethnicity or deprivation index level. CONCLUSIONS AND RELEVANCE: This study provides data suggesting that a range of comorbidities and symptoms are encountered in primary care settings before PD diagnosis in an ethnically diverse and deprived population. Novel temporal associations were observed for epilepsy and hearing loss with subsequent development of PD. The prominence of memory symptoms suggests an excess of cognitive dysfunction in early PD in this population or difficulty in correctly ascertaining symptoms in traditionally underrepresented groups.

Resolving Missing Data from the Movement Disorder Society Unified Parkinson's Disease Rating Scale: Implications for Telemedicine.

BACKGROUND: Telemedicine has become standard in clinical care and research during the coronavirus disease 2019 pandemic. Remote administration of Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part III (Motor Examination) precludes ratings of all items, because Rigidity and Postural Stability (six scores) require in-person rating. OBJECTIVE: The objective of this study was to determine imputation accuracy for total-sum and item-specific MDS-UPDRS Motor Examination scores in remote administration. METHODS: We applied multivariate imputation by chained equations techniques in a cross-sectional dataset where patients had one MDS-UPDRS rating (International Translational Program, n = 8,588) and in a longitudinal dataset where patients had multiple ratings (Rush Program, n = 396). Successful imputation was stringently defined as (1) generalized Lin's concordance correlation coefficient >0.95, reflecting near-perfect agreement between total-sum score with complete data and surrogate score, calculated without patients' actual Rigidity and Postural Stability scores; and (2) perfect agreement for item-level scores for Rigidity and Postural Stability items. RESULTS: For total-sum score when Rigidity and Postural Stability scores were withdrawn, using one or multiple visits, multivariate imputation by chained equations imputation reached near-perfect agreement with the original total-sum score. However, at the item level, the degree of perfect agreement between the surrogate and actual Rigidity items and Postural Stability scores always fell below threshold. CONCLUSIONS: The MDS-UPDRS Part III total-sum score, a key clinical outcome in research and in clinical practice, can be accurately imputed without the Rigidity and Postural Stability items that cannot be rated by telemedicine. No formula, however, allows for specific item-level imputation. When Rigidity and Postural Stability item scores are of key clinical or research interest, patients with PD must be scored in person. © 2022 International Parkinson and Movement Disorder Society.

Treatment paradigms in Parkinson's Disease and Covid-19.

People with Parkinson's Disease (PwP) may be at higher risk for complications from the Coronavirus Disease 2019 (Covid-19) due to older age and to the multi-faceted nature of Parkinson's Disease (PD) per se, presenting with a variety of motor and non-motor symptoms. Those on advanced therapies may be particularly vulnerable. Taking the above into consideration, along with the potential multi-systemic impact of Covid-19 on affected patients and the complications of hospitalization, we are providing an evidence-based guidance to ensure a high standard of care for PwP affected by Covid-19 with varying severity of the condition. Adherence to the dopaminergic medication of PwP, without abrupt modifications in dosage and frequency, is of utmost importance, while potential interactions with newly introduced drugs should always be considered. Treating physicians should be cautious to acknowledge and timely address any potential complications, while consultation by a neurologist, preferably with special knowledge on movement disorders, is advised for patients admitted in non-neurological wards. Non-pharmacological approaches, including the patient's mobilization, falls prevention, good sleep hygiene, emotional support, and adequate nutritional and fluid intake, are essential and the role of telemedicine services should be strengthened and encouraged.

A longitudinal study on the effects of COVID-19 pandemic on non-motor symptoms in Parkinson's disease.

INTRODUCTION: The COVID-19 pandemic led to psychological consequences on people's mental health, representing a condition of increased vulnerability for the weakest sections of population, including elderly patients with Parkinson's disease (PD). This longitudinal study aimed at exploring the impact of the most frequent non-motor symptoms and their contribute on health-related quality of life of PD patients after the COVID-19 outbreak, in comparison with the pre-pandemic status. METHODS: Forty-two non-demented PD patients underwent a first assessment between December 2018 and January 2020 (T0). Then, between March and May 2021 (T1), they were contacted again and asked to complete the second assessment. Levels of global functioning, several non-motor symptoms (i.e. depression, apathy, anxiety, anhedonia) and health-related quality of life were investigated. RESULTS: Results of the the paired Wilcoxon signed-rank test showed that at T1, PD patients scored lower on the emotional subscale of the DAS, Z = - 2.49; p = 0.013; Cohen dz = 0.691. Higher scores of the TEPS total score, Z = - 2.38; p = 0.025; Cohen dz = 0.621, and LEDD, Z = - 2.63; p = 0.008; Cohen dz = 0.731, were also reported at T1. CONCLUSION: The present study suggested that self-isolation at home might lead to a reduction of apathy and anhedonia in PD patients due to the increase in social support provided by families during COVID-19 restrictions. This evidence brings out the need of a consistent and persistent social support which might be represented by caregivers or/and social assistive robotics.

The state of telemedicine for persons with Parkinson's disease.

PURPOSE OF REVIEW: The COVID-pandemic has facilitated the implementation of telemedicine in both clinical practice and research. We highlight recent developments in three promising areas of telemedicine: teleconsultation, telemonitoring, and teletreatment. We illustrate this using Parkinson's disease as a model for other chronic neurological disorders. RECENT FINDINGS: Teleconsultations can reliably administer parts of the neurological examination remotely, but are typically not useful for establishing a reliable diagnosis. For follow-ups, teleconsultations can provide enhanced comfort and convenience to patients, and provide opportunities for blended and proactive care models. Barriers include technological challenges, limited clinician confidence, and a suboptimal clinician-patient relationship. Telemonitoring using wearable sensors and smartphone-based apps can support clinical decision-making, but we lack large-scale randomized controlled trials to prove effectiveness on clinical outcomes. Increasingly many trials are now incorporating telemonitoring as an exploratory outcome, but more work remains needed to demonstrate its clinical meaningfulness. Finding a balance between benefits and burdens for individual patients remains vital. Recent work emphasised the promise of various teletreatment solutions, such as remotely adjustable deep brain stimulation parameters, virtual reality enhanced exercise programs, and telephone-based cognitive behavioural therapy. Personal contact remains essential to ascertain adherence to teletreatment. SUMMARY: The availability of different telemedicine tools for remote consultation, monitoring, and treatment is increasing. Future research should establish whether telemedicine improves outcomes in routine clinical care, and further underpin its merits both as intervention and outcome in research settings.

Parkinson's disease and Covid-19: Is there an impact of ethnicity and the need for palliative care.

Under the traditional models of care for People with Parkinson's Disease (PD, PwP), many of their needs remain unmet and a substantial burden of motor and non-motor symptoms they experience may not be tackled sufficiently. An introduction of palliative care (PC) interventions early in the course of PD offers profound benefits: it may improve quality of life of patients, their families and caregivers through the prevention and relief of medical symptoms, while, at the same time, emphasizing their emotional needs and spiritual wellbeing, establishing goals of care, and engaging in the advance care planning (ACP). The ongoing Coronavirus Disease 2019 (Covid-19) pandemic poses an unprecedented set of challenges for PwP and has in many ways (both directly and indirectly) magnified their suffering, thus rapidly raising the demand for PC interventions. Covid-19, as well as the repercussions of prolonged mobility restrictions and limited health-care access might exacerbate the severity of PD motor symptoms and interact negatively with a range of non-motor symptoms, with a detrimental effect on quality of life. Greater motor disability, higher amount of levodopa-induced motor fluctuations with an increased daily off-time, fatigue, anxiety, depression, sleep disturbances, pain and worsening of cognitive complaints might dominate the clinical presentation in PwP during the Covid-19 pandemic, alongside raising psychological and spiritual concerns and anticipatory grief. Here, we aim to provide a foundation for pragmatic and clinically orientated PC approach to improve quality of life and relieve suffering of PwP in the context of the current, ongoing Covid-19 pandemic.

Comprehensive telemedicine solution for remote monitoring of Parkinson's disease patients with orthostatic hypotension during COVID-19 pandemic.

OBJECTIVE: Orthostatic hypotension (OH) represents a frequent but under-recognized phenomenon in Parkinson's disease (PD). During COVID-19 pandemic, Information and Communication Technologies (ICT) have become pivotal in the management of chronic diseases like PD, not only to assess motor impairment, but also for vital signs monitoring. This pilot study aimed to propose a real-time remote home-monitoring system and protocol for PD patients with OH. METHODS: Vital parameters were acquired by wireless devices and transmitted to an ICT platform, providing data and smart notifications to the healthcare provider through an interactive web portal. Eight patients with idiopathic PD and OH underwent 5-day monitoring. Data about OH episodes, therapeutic interventions, impact on daily activities, and patient satisfaction were collected and analyzed. RESULTS: The proposed solution allowed the identification of 65 OH episodes and subsequent medical interventions. Thirty-five episodes were asymptomatic, especially in the postprandial and in the afternoon recordings. Systolic-blood-pressure (SBP) and diastolic-blood-pressure (DBP) were significantly lower in symptomatic episodes, while the pressure drops resulted significantly higher in presence of symptoms. High usability and patient satisfaction scores were observed. CONCLUSION: The proposed home-monitoring system and protocol have proved to provide useful information and to allow prompt interventions in the management of PD patients with OH during COVID-19 pandemic.

Internet of Things Technologies and Machine Learning Methods for Parkinson's Disease Diagnosis, Monitoring and Management: A Systematic Review.

Parkinson's disease is a chronic neurodegenerative disease that affects a large portion of the population, especially the elderly. It manifests with motor, cognitive and other types of symptoms, decreasing significantly the patients' quality of life. The recent advances in the Internet of Things and Artificial Intelligence fields, including the subdomains of machine learning and deep learning, can support Parkinson's disease patients, their caregivers and clinicians at every stage of the disease, maximizing the treatment effectiveness and minimizing the respective healthcare costs at the same time. In this review, the considered studies propose machine learning models, trained on data acquired via smart devices, wearable or non-wearable sensors and other Internet of Things technologies, to provide predictions or estimations regarding Parkinson's disease aspects. Seven hundred and seventy studies have been retrieved from three dominant academic literature databases. Finally, one hundred and twelve of them have been selected in a systematic way and have been considered in the state-of-the-art systematic review presented in this paper. These studies propose various methods, applied on various sensory data to address different Parkinson's disease-related problems. The most widely deployed sensors, the most commonly addressed problems and the best performing algorithms are highlighted. Finally, some challenges are summarized along with some future considerations and opportunities that arise.

Feasibility of remote neurocognitive assessment: pandemic adaptations for a clinical trial, the Cognition and Obstructive Sleep Apnea in Parkinson's Disease, Effect of Positive Airway Pressure Therapy (COPE-PAP) study.

BACKGROUND: The COVID-19 pandemic poses challenges for timely outcome assessment in randomized clinical trials (RCT). Our aim was to describe our remote neurocognitive testing (NCT) protocol administered by telephone in patients with Parkinson's disease (PD) and obstructive sleep apnea (OSA). METHODS: We studied PD patients with OSA and Montreal Cognitive Assessment (MoCA) score ≤ 27 participating in a RCT assessing OSA treatment impact on cognition. Trial outcomes included change in MoCA and specific cognitive domains from baseline to 3 and 6 months. With COVID19 pandemic-related restrictions, 3-month visits were converted from in-person to telephone administration with materials mailed to participants for compatible tests and retrieved by courier the same day. In exploratory analyses, we compared baseline vs. 3-month results in the control arm, which were not expected to change significantly (test-re-test), using a paired t-test and assessed agreement with the intraclass correlation coefficient (ICC). RESULTS: Seven participants were approached and agreed to remote NCT at 3-month follow-up. Compared to the in-person NCT control arm group, they were younger (60.6 versus 70.6 years) and had a shorter disease course (3.9 versus 9.2 years). Remote NCT data were complete. The mean test-retest difference in MoCA was similar for in-person and remote NCT control-arm groups (between group difference - 0.69; 95%CI - 3.67, 2.29). Agreement was good for MOCA and varied for specific neurocognitive tests. CONCLUSION: Telephone administration of the MoCA and a modified neurocognitive battery is feasible in patients with PD and OSA. Further validation will require a larger sample size.

A Markerless 2D Video, Facial Feature Recognition-Based, Artificial Intelligence Model to Assist With Screening for Parkinson Disease: Development and Usability Study.

BACKGROUND: Masked face is a characteristic clinical manifestation of Parkinson disease (PD), but subjective evaluations from different clinicians often show low consistency owing to a lack of accurate detection technology. Hence, it is of great significance to develop methods to make monitoring easier and more accessible. OBJECTIVE: The study aimed to develop a markerless 2D video, facial feature recognition-based, artificial intelligence (AI) model to assess facial features of PD patients and investigate how AI could help neurologists improve the performance of early PD diagnosis. METHODS: We collected 140 videos of facial expressions from 70 PD patients and 70 matched controls from 3 hospitals using a single 2D video camera. We developed and tested an AI model that performs masked face recognition of PD patients based on the acquisition and evaluation of facial features including geometric and texture features. Random forest, support vector machines, and k-nearest neighbor were used to train the model. The diagnostic performance of the AI model was compared with that of 5 neurologists. RESULTS: The experimental results showed that our AI models can achieve feasible and effective facial feature recognition ability to assist with PD diagnosis. The accuracy of PD diagnosis can reach 83% using geometric features. And with the model trained by random forest, the accuracy of texture features is up to 86%. When these 2 features are combined, an F1 value of 88% can be reached, where the random forest algorithm is used. Further, the facial features of patients with PD were not associated with the motor and nonmotor symptoms of PD. CONCLUSIONS: PD patients commonly exhibit masked facial features. Videos of a facial feature recognition-based AI model can provide a valuable tool to assist with PD diagnosis and the potential of realizing remote monitoring of the patient's condition, especially during the COVID-19 pandemic.