Video-Based Activity Recognition for Automated Motor Assessment of Parkinson's Disease.

Over the last decade, video-enabled mobile devices have become ubiquitous, while advances in markerless pose estimation allow an individual's body position to be tracked accurately and efficiently across the frames of a video. Previous work by this and other groups has shown that pose-extracted kinematic features can be used to reliably measure motor impairment in Parkinson's disease (PD). This presents the prospect of developing an asynchronous and scalable, video-based assessment of motor dysfunction. Crucial to this endeavour is the ability to automatically recognise the class of an action being performed, without which manual labelling is required. Representing the evolution of body joint locations as a spatio-temporal graph, we implement a deep-learning model for video and frame-level classification of activities performed according to part 3 of the Movement Disorder Society Unified PD Rating Scale (MDS-UPDRS). We train and validate this system using a dataset of n = 7310 video clips, recorded at 5 independent sites. This approach reaches human-level performance in detecting and classifying periods of activity within monocular video clips. Our framework could support clinical workflows and patient care at scale through applications such as quality monitoring of clinical data collection, automated labelling of video streams, or a module within a remote self-assessment system.

Moving towards vertically integrated artificial intelligence development.

Substantial interest and investment in clinical artificial intelligence (AI) research has not resulted in widespread translation to deployed AI solutions. Current attention has focused on bias and explainability in AI algorithm development, external validity and model generalisability, and lack of equity and representation in existing data. While of great importance, these considerations also reflect a model-centric approach seen in published clinical AI research, which focuses on optimising architecture and performance of an AI model on best available datasets. However, even robustly built models using state-of-the-art algorithms may fail once tested in realistic environments due to unpredictability of real-world conditions, out-of-dataset scenarios, characteristics of deployment infrastructure, and lack of added value to clinical workflows relative to cost and potential clinical risks. In this perspective, we define a vertically integrated approach to AI development that incorporates early, cross-disciplinary, consideration of impact evaluation, data lifecycles, and AI production, and explore its implementation in two contrasting AI development pipelines: a scalable "AI factory" (Mayo Clinic, Rochester, United States), and an end-to-end cervical cancer screening platform for resource poor settings (Paps AI, Mbarara, Uganda). We provide practical recommendations for implementers, and discuss future challenges and novel approaches (including a decentralised federated architecture being developed in the NHS (AI4VBH, London, UK)). Growth in global clinical AI research continues unabated, and introduction of vertically integrated teams and development practices can increase the translational potential of future clinical AI projects.

COVID-19 severity is associated with population-level gut microbiome variations.

The human gut microbiome interacts with many diseases, with recent small studies suggesting a link with COVID-19 severity. Exploring this association at the population-level may provide novel insights and help to explain differences in COVID-19 severity between countries. We explore whether there is an association between the gut microbiome of people within different countries and the severity of COVID-19, measured as hospitalisation rate. We use data from the large (n = 3,055) open-access gut microbiome repository curatedMetagenomicData, as well as demographic and country-level metadata. Twelve countries were placed into two groups (high/low) according to COVID-19 hospitalisation rate before December 2020 (ourworldindata.com). We use an unsupervised machine learning method, Topological Data Analysis (TDA). This method analyses both the local geometry and global topology of a high-dimensional dataset, making it particularly suitable for population-level microbiome data. We report an association of distinct baseline population-level gut microbiome signatures with COVID-19 severity. This was found both with a PERMANOVA, as well as with TDA. Specifically, it suggests an association of anti-inflammatory bacteria, including Bifidobacteria species and Eubacterium rectale, with lower severity, and pro-inflammatory bacteria such as Prevotella copri with higher severity. This study also reports a significant impact of country-level confounders, specifically of the proportion of over 70-year-olds in the population, GDP, and human development index. Further interventional studies should examine whether these relationships are causal, as well as considering the contribution of other variables such as genetics, lifestyle, policy, and healthcare system. The results of this study support the value of a population-level association design in microbiome research in general and for the microbiome-COVID-19 relationship, in particular. Finally, this research underscores the potential of TDA for microbiome studies, and in identifying novel associations.

A rare cause of monogenic cerebral small vessel disease and stroke: Cathepsin A-related arteriopathy with strokes and leukoencephalopathy (CARASAL).

BACKGROUND: Cathepsin A-related arteriopathy with strokes and leukoencephalopathy (CARASAL) is a rare monogenic cause of cerebral small vessel disease. To date, fewer than 15 patients with CARASAL have been described, all of common European ancestry. METHODS: Clinical and imaging phenotypes of two patients are presented. Genetic variants were identified using targeted Sanger and focused exome sequencing, respectively. RESULTS: Both patients carried the same pathogenic p.Arg325Cys mutation in CTSA. One patient of Chinese ethnicity presented with migraine, tinnitus and slowly progressive cognitive impairment with significant cerebral small vessel disease in the absence of typical cardiovascular risk factors. She later suffered an ischaemic stroke. A second patient from Brazil, of Italian ethnicity developed progressive dysphagia and dysarthria in his 50s, he later developed hearing loss and chronic disequilibrium. Magnetic resonance imaging in both cases demonstrated extensive signal change in the deep cerebral white matter, anterior temporal lobes, thalami, internal and external capsules and brainstem. CONCLUSIONS: CARASAL should be considered in patients with early onset or severe cerebral small vessel disease, particularly where there are prominent symptoms or signs related to brainstem involvement, such as hearing dysfunction, tinnitus or dysphagia or where there is significant thalamic and brainstem involvement on imaging.

Best practices in the real-world data life cycle.

With increasing digitization of healthcare, real-world data (RWD) are available in greater quantity and scope than ever before. Since the 2016 United States 21st Century Cures Act, innovations in the RWD life cycle have taken tremendous strides forward, largely driven by demand for regulatory-grade real-world evidence from the biopharmaceutical sector. However, use cases for RWD continue to grow in number, moving beyond drug development, to population health and direct clinical applications pertinent to payors, providers, and health systems. Effective RWD utilization requires disparate data sources to be turned into high-quality datasets. To harness the potential of RWD for emerging use cases, providers and organizations must accelerate life cycle improvements that support this process. We build on examples obtained from the academic literature and author experience of data curation practices across a diverse range of sectors to describe a standardized RWD life cycle containing key steps in production of useful data for analysis and insights. We delineate best practices that will add value to current data pipelines. Seven themes are highlighted that ensure sustainability and scalability for RWD life cycles: data standards adherence, tailored quality assurance, data entry incentivization, deploying natural language processing, data platform solutions, RWD governance, and ensuring equity and representation in data.

Precision reimbursement for precision medicine: the need for patient-level decisions between payers, providers and pharmaceutical companies.

Healthcare costs have been dramatically rising in developed economies worldwide. A key driver of cost increases has been high-cost drugs. The current model of reimbursement is not configured for drugs with uncertain outcomes. Future reimbursement will require better allocation of available healthcare system funds. Technological advancements have opened the door to a new type of outcomes-based reimbursement, enabling value exchange between payers and pharmaceutical companies, which we term precision reimbursement. Precision reimbursement extends beyond value-based contracts, with decisions at individual rather than aggregate level. For precision reimbursement to be adopted, there are data, computation and infrastructure requirements. All stakeholders benefit in moving to precision reimbursement for optimal resource allocation, risk sharing and, ultimately, improved outcomes. There are implementation challenges including cost, change management, information governance and development of surrogate markers. The overarching trend in medicine is toward personalised interventions, with precision reimbursement as the logical consequence.

The Unique Impact of COVID-19 on Human Gut Microbiome Research.

The coronavirus (COVID-19) pandemic has disrupted clinical trials globally, with unique implications for research into the human gut microbiome. In this mini-review, we explore the direct and indirect influences of the pandemic on the gut microbiome and how these can affect research and clinical trials. We explore the direct bidirectional relationships between the COVID-19 virus and the gut and lung microbiomes. We then consider the significant indirect effects of the pandemic, such as repeated lockdowns, increased hand hygiene, and changes to mood and diet, that could all lead to longstanding changes to the gut microbiome at an individual and a population level. Together, these changes may affect long term microbiome research, both in observational as well as in population studies, requiring urgent attention. Finally, we explore the unique implications for clinical trials using faecal microbiota transplants (FMT), which are increasingly investigated as potential treatments for a range of diseases. The pandemic introduces new barriers to participation in trials, while the direct and indirect effects laid out above can present a confounding factor. This affects recruitment and sample size, as well as study design and statistical analyses. Therefore, the potential impact of the pandemic on gut microbiome research is significant and needs to be specifically addressed by the research community and funders.

Brain-Machine Interfaces: The Role of the Neurosurgeon.

Neurotechnology is set to expand rapidly in the coming years as technological innovations in hardware and software are translated to the clinical setting. Given our unique access to patients with neurologic disorders, expertise with which to guide appropriate treatments, and technical skills to implant brain-machine interfaces (BMIs), neurosurgeons have a key role to play in the progress of this field. We outline the current state and key challenges in this rapidly advancing field, including implant technology, implant recipients, implantation methodology, implant function, and ethical, regulatory, and economic considerations. Our key message is to encourage the neurosurgical community to proactively engage in collaborating with other health care professionals, engineers, scientists, ethicists, and regulators in tackling these issues. By doing so, we will equip ourselves with the skills and expertise to drive the field forward and avoid being mere technicians in an industry driven by those around us.

Immune Aberrations in Obsessive-Compulsive Disorder: a Systematic Review and Meta-analysis.

Some lines of evidence have indicated that immune dysregulation could play a role in the pathophysiology of obsessive-compulsive disorder (OCD). However, results have been inconsistent across studies. Thus, a systematic review and meta-analysis of studies measuring immune mediators in participants with OCD compared to healthy controls (HC) was conducted. The PubMed/MEDLINE, PsycINFO, and EMBASE electronic databases were systematically searched from inception through June 21, 2018. Sixteen studies met inclusion criteria comprising data from 1001 participants (538 with OCD and 463 were HCs). Levels of TNF-α, IL-6, IL-1ß, IL-4, IL-10, and interferon-γ did not significantly differ between participants with OCD and healthy controls. In addition, the ex vivo production of TNF-α and IL-6 by isolated macrophages did not significantly differ between participants with OCD and HCs. Nevertheless, included studies have varied in methodological quality with the enrollment of samples that differed regarding medication status, the proper matching of OCD participants and HCs, age groups, and the presence of psychiatric comorbidities. In conclusion, an association between immune dysregulation and OCD remains unproven. Future studies should consider enrolling larger and more homogeneous samples with OCD.

A Retrospective Cohort Study to Assess Patient and Physician Reported Outcome Measures After Decompressive Hemicraniectomy for Malignant Middle Cerebral Artery Stroke.

INTRODUCTION: Decompressive hemicraniectomy for malignant middle cerebral artery (MCA) infarction is known to reduce mortality. However, there are on-going concerns in terms of the quality of life in survivors. We aimed to examine the correlation between patient and physician reported outcome measures in decompressive hemicraniectomy. PATIENTS AND METHODS: We analyzed outcomes in 21 patients who underwent decompressive hemicraniectomy for malignant MCA infarction between September 2003 and August 2013 within a regional health system. Patient and physician reported outcome measures were collected at follow-up. These were Stroke Impact Scale (SIS) Version 3, modified Rankin Scale (mRS), National Hospital Seizure Severity Scale, Headache Impact Test and Patient Health Questionnaire for depression. RESULTS: There was a good correlation between physician and patient reported outcome measures. The Spearman's rank correlation coefficient between mRS and structured SIS Version 3 was -0.887 (p < 0.001); with unstructured SIS results, the correlation coefficient was -0.663 (p = 0.001). There was no statistically significant correlation between life worth and modified Rankin Scale: r = -0.3383 (p = 0.087). DISCUSSION: Our findings of a statistically significant correlation between mRS and SIS have not previously been reported in patients with this condition. These findings provide further information to inform patient and next of kin discussions regarding outcomes from decompressive hemicraniectomy in malignant MCA infarction.

Changes in government spending on healthcare and population mortality in the European union, 1995-2010: a cross-sectional ecological study.

OBJECTIVE: Economic measures such as unemployment and gross domestic product are correlated with changes in health outcomes. We aimed to examine the effects of changes in government healthcare spending, an increasingly important measure given constrained government budgets in several European Union countries. DESIGN: Multivariate regression analysis was used to assess the effect of changes in healthcare spending as a proportion of total government expenditure, government healthcare spending as a proportion of gross domestic product and government healthcare spending measured in purchasing power parity per capita, on five mortality indicators. Additional variables were controlled for to ensure robustness of data. One to five year lag analyses were conducted. SETTING AND PARTICIPANTS: European Union countries 1995-2010. MAIN OUTCOME MEASURES: Neonatal mortality, postneonatal mortality, one to five years of age mortality, under five years of age mortality, adult male mortality, adult female mortality. RESULTS: A 1% decrease in government healthcare spending was associated with significant increase in all mortality metrics: neonatal mortality (coefficient -0.1217, p = 0.0001), postneonatal mortality (coefficient -0.0499, p = 0.0018), one to five years of age mortality (coefficient -0.0185, p = 0.0002), under five years of age mortality (coefficient -0.1897, p = 0.0003), adult male mortality (coefficient -2.5398, p = 0.0000) and adult female mortality (coefficient -1.4492, p = 0.0000). One per cent decrease in healthcare spending, measured as a proportion of gross domestic product and in purchasing power parity, was both associated with significant increases (p < 0.05) in all metrics. Five years after the 1% decrease in healthcare spending, significant increases (p < 0.05) continued to be observed in all mortality metrics. CONCLUSIONS: Decreased government healthcare spending is associated with increased population mortality in the short and long term. Policy interventions implemented in response to the financial crisis may be associated with worsening population health.

Cardiac device-associated lead infection: a diagnosis not to be missed.

A 66-year-old gentleman was admitted to hospital with a history of general malaise for 5 months. His symptoms worsened 2 weeks prior to presentation. He experienced swinging pyrexia, night sweats and shortness of breath on exertion. Initial evaluation did not reveal any source of infection. Subsequent investigation revealed infection with vegetation affecting the intra-cardiac leads of cardiac resynchronization therapy device (CRT-D). The patient was treated with prolonged intravenous antibiotics and removal of the device and indwelling leads. The patient made a full recovery and a new device was implanted.

Working memory recall precision is a more sensitive index than span.

Delayed adjustment tasks have recently been developed to examine working memory (WM) precision, that is, the resolution with which items maintained in memory are recalled. However, despite their emerging use in experimental studies of healthy people, evaluation of patient populations is sparse. We first investigated the validity of adjustment tasks, comparing precision with classical span measures of memory across the lifespan in 114 people. Second, we asked whether precision measures can potentially provide a more sensitive measure of WM than traditional span measures. Specifically, we tested this hypothesis examining WM in a group with early, untreated Parkinson's disease (PD) and its modulation by subsequent treatment on dopaminergic medication. Span measures correlated with precision across the lifespan: in children, young, and elderly participants. However, they failed to detect changes in WM in PD patients, either pre- or post-treatment initiation. By contrast, recall precision was sensitive enough to pick up such changes. PD patients pre-medication were significantly impaired compared to controls, but improved significantly after 3 months of being established on dopaminergic medication. These findings suggest that precision methods might provide a sensitive means to investigate WM and its modulation by interventions in clinical populations.

Normoammonemic encephalopathy: solely valproate induced or multiple mechanisms?

A 77-year-old woman presented with subacute onset progressive confusion, aggression, auditory hallucinations and delusions. In the preceding months, the patient had a number of admissions with transient unilateral hemiparesis with facial droop, and had been started on valproate for presumed hemiplegic migraine. Valproate was withdrawn soon after admission and her cognitive abilities have gradually improved over 3 months of follow-up. Valproate levels taken prior to withdrawal were subtherapeutic and the patient was normoammonaemic. EEG undertaken during inpatient stay showed changes consistent with encephalopathy, and low titre N-methyl-D-aspartate (NMDA) receptor antibodies were present in this patient. The possible aetiologies of valproate-induced encephalopathy and NMDA receptor-associated encephalitis present a diagnostic dilemma. We present a putative combinatorial hypothesis to explain this patient's symptoms.