ABSTRACT
Advancements in artificial intelligence (AI) for point-of-care ultrasound (POCUS) have ushered in new possibilities for medical diagnostics in low-resource settings. This review explores the current landscape of AI applications in POCUS across these environments, analyzing studies sourced from three databases-SCOPUS, PUBMED, and Google Scholars. Initially, 1196 records were identified, of which 1167 articles were excluded after a two-stage screening, leaving 29 unique studies for review. The majority of studies focused on deep learning algorithms to facilitate POCUS operations and interpretation in resource-constrained settings. Various types of low-resource settings were targeted, with a significant emphasis on low- and middle-income countries (LMICs), rural/remote areas, and emergency contexts. Notable limitations identified include challenges in generalizability, dataset availability, regional disparities in research, patient compliance, and ethical considerations. Additionally, the lack of standardization in POCUS devices, protocols, and algorithms emerged as a significant barrier to AI implementation. The diversity of POCUS AI applications in different domains (e.g., lung, hip, heart, etc.) illustrates the challenges of having to tailor to the specific needs of each application. By separating out the analysis by application area, researchers will better understand the distinct impacts and limitations of AI, aligning research and development efforts with the unique characteristics of each clinical condition. Despite these challenges, POCUS AI systems show promise in bridging gaps in healthcare delivery by aiding clinicians in low-resource settings. Future research endeavors should prioritize addressing the gaps identified in this review to enhance the feasibility and effectiveness of POCUS AI applications to improve healthcare outcomes in resource-constrained environments.
ABSTRACT
We present open-source tools for three-dimensional (3D) analysis of photographs of dissected slices of human brains, which are routinely acquired in brain banks but seldom used for quantitative analysis. Our tools can: (1) 3D reconstruct a volume from the photographs and, optionally, a surface scan; and (2) produce a high-resolution 3D segmentation into 11 brain regions per hemisphere (22 in total), independently of the slice thickness. Our tools can be used as a substitute for ex vivo magnetic resonance imaging (MRI), which requires access to an MRI scanner, ex vivo scanning expertise, and considerable ï¬nancial resources. We tested our tools on synthetic and real data from two NIH Alzheimer's Disease Research Centers. The results show that our methodology yields accurate 3D reconstructions, segmentations, and volumetric measurements that are highly correlated to those from MRI. Our method also detects expected diï¬erences between post mortem conï¬rmed Alzheimer's disease cases and controls. The tools are available in our widespread neuroimaging suite 'FreeSurfer' (https://surfer.nmr.mgh.harvard.edu/fswiki/PhotoTools).
Every year, thousands of human brains are donated to science. These brains are used to study normal aging, as well as neurological diseases like Alzheimer's or Parkinson's. Donated brains usually go to 'brain banks', institutions where the brains are dissected to extract tissues relevant to different diseases. During this process, it is routine to take photographs of brain slices for archiving purposes. Often, studies of dead brains rely on qualitative observations, such as 'the hippocampus displays some atrophy', rather than concrete 'numerical' measurements. This is because the gold standard to take three-dimensional measurements of the brain is magnetic resonance imaging (MRI), which is an expensive technique that requires high expertise especially with dead brains. The lack of quantitative data means it is not always straightforward to study certain conditions. To bridge this gap, Gazula et al. have developed an openly available software that can build three-dimensional reconstructions of dead brains based on photographs of brain slices. The software can also use machine learning methods to automatically extract different brain regions from the three-dimensional reconstructions and measure their size. These data can be used to take precise quantitative measurements that can be used to better describe how different conditions lead to changes in the brain, such as atrophy (reduced volume of one or more brain regions). The researchers assessed the accuracy of the method in two ways. First, they digitally sliced MRI-scanned brains and used the software to compute the sizes of different structures based on these synthetic data, comparing the results to the known sizes. Second, they used brains for which both MRI data and dissection photographs existed and compared the measurements taken by the software to the measurements obtained with MRI images. Gazula et al. show that, as long as the photographs satisfy some basic conditions, they can provide good estimates of the sizes of many brain structures. The tools developed by Gazula et al. are publicly available as part of FreeSurfer, a widespread neuroimaging software that can be used by any researcher working at a brain bank. This will allow brain banks to obtain accurate measurements of dead brains, allowing them to cheaply perform quantitative studies of brain structures, which could lead to new findings relating to neurodegenerative diseases.
Subject(s)
Alzheimer Disease , Brain , Imaging, Three-Dimensional , Machine Learning , Humans , Imaging, Three-Dimensional/methods , Alzheimer Disease/diagnostic imaging , Alzheimer Disease/pathology , Brain/diagnostic imaging , Brain/pathology , Photography/methods , Dissection , Magnetic Resonance Imaging/methods , Neuropathology/methods , Neuroimaging/methodsABSTRACT
The role for routine whole genome and transcriptome analysis (WGTA) for poor prognosis pediatric cancers remains undetermined. Here, we characterize somatic mutations, structural rearrangements, copy number variants, gene expression, immuno-profiles and germline cancer predisposition variants in children and adolescents with relapsed, refractory or poor prognosis malignancies who underwent somatic WGTA and matched germline sequencing. Seventy-nine participants with a median age at enrollment of 8.8 y (range 6 months to 21.2 y) are included. Germline pathogenic/likely pathogenic variants are identified in 12% of participants, of which 60% were not known prior. Therapeutically actionable variants are identified by targeted gene report and whole genome in 32% and 62% of participants, respectively, and increase to 96% after integrating transcriptome analyses. Thirty-two molecularly informed therapies are pursued in 28 participants with 54% achieving a clinical benefit rate; objective response or stable disease ≥6 months. Integrated WGTA identifies therapeutically actionable variants in almost all tumors and are directly translatable to clinical care of children with poor prognosis cancers.
Subject(s)
DNA Copy Number Variations , Gene Expression Profiling , Neoplasms , Humans , Child , Neoplasms/genetics , Neoplasms/therapy , Female , Adolescent , Male , Child, Preschool , Prognosis , Gene Expression Profiling/methods , Infant , Transcriptome , Young Adult , Whole Genome Sequencing , Germ-Line Mutation , Mutation , Genome, Human/genetics , Genetic Predisposition to DiseaseABSTRACT
Digital health tracking is a source of valuable insights for public health research and consumer health technology. The brain is the most complex organ, containing information about psychophysical and physiological biomarkers that correlate with health. Specifically, recent developments in electroencephalogram (EEG), functional near-infra-red spectroscopy (fNIRS), and photoplethysmography (PPG) technologies have allowed the development of devices that can remotely monitor changes in brain activity. The inclusion criteria for the papers in this review encompassed studies on self-applied, remote, non-invasive neuroimaging techniques (EEG, fNIRS, or PPG) within healthcare applications. A total of 23 papers were reviewed, comprising 17 on using EEGs for remote monitoring and 6 on neurofeedback interventions, while no papers were found related to fNIRS and PPG. This review reveals that previous studies have leveraged mobile EEG devices for remote monitoring across the mental health, neurological, and sleep domains, as well as for delivering neurofeedback interventions. With headsets and ear-EEG devices being the most common, studies found mobile devices feasible for implementation in study protocols while providing reliable signal quality. Moderate to substantial agreement overall between remote and clinical-grade EEGs was found using statistical tests. The results highlight the promise of portable brain-imaging devices with regard to continuously evaluating patients in natural settings, though further validation and usability enhancements are needed as this technology develops.
ABSTRACT
This cohort study evaluates the role that community-level socioeconomic status plays in hypertension-related hospital readmission within 12 weeks after delivery.
Subject(s)
Patient Readmission , Female , Humans , Postpartum PeriodABSTRACT
HIV-related stigma is a primary barrier to seeking HIV care. Online social media interventions utilizing peer-led approaches provide an opportunity to revolutionize HIV health behavior change. Secondary analysis of the UCLA HOPE Study (6 waves) was done to examine the effectiveness of an online peer-led intervention in reducing HIV-related internalized stigma (IS), association between IS and sexual risk behaviors (SRB), and associated costs for changing the likelihood of HIV testing. Among 897 participants, an inverse relationship between IS (Discomfort with people with HIV, Stereotypes, Moral Judgment) and SRB (Number of Sexual Partners, Sexual Encounters) factors was identified over time (p < .05). Engagement in stigma conversations increased participant likelihood to request HIV tests (B = 0.02, Wald = 8.10, p = .004) when made in group versus one-on-one contact. Innovative technology has potential to improve HIV-care efforts through expanded reach to at-risk populations, improved communication maintenance, ease of accessibility, and user anonymity.
Subject(s)
HIV Infections , Peer Group , Sexual Behavior , Social Media , Social Stigma , Humans , HIV Infections/psychology , Male , Female , Adult , Sexual Behavior/psychology , Risk-Taking , Middle Aged , Sexual Partners/psychology , Patient Acceptance of Health Care/psychology , HIV Testing/methods , Stereotyping , Young AdultABSTRACT
OBJECTIVES: Sling immobilization is commonly used following rotator cuff repair. The purpose of this study was to determine the detrimental impact of sling usage on mobility and balance in an older adult population through validated gait and balance testing. The authors hypothesize that sling use will negatively affect balance and stability. METHODS: This institutional review board-approved and registered randomized prospective clinical trial enrolled patients from 2019 to 2021. Following informed consent, patients were randomized into two groups: a sling worn (group 1) and no sling worn (group 2). Participants were assessed via the Edmonton Frail Scale as well as Tinetti gait and balance scoring. RESULTS: Fifty patients were included in the study, 23 (46%) men and 27 (54%) women, with a mean age of 72.2 years. The balance score median was 16.00 for participants not wearing a sling and 15.00 for participants wearing a sling. The gait score median was 12.00 for participants not wearing a sling and 11.50 for participants wearing a sling. The balance and gait scores were significantly greater when patients were not wearing a shoulder sling with P values of 0.006 and 0.011, respectively. The overall combined gait and balance score was significantly greater, with median values of 27.00 for participants not wearing a sling and 26.00 for participants wearing a sling (P = 0.001). Patients reported little to no anxiety about falling while wearing the sling, with a score of 0.16. CONCLUSIONS: Postoperative sling immobilization negatively affects balance and gait in the geriatric population, potentially increasing the risk of postoperative falls in an already at-risk population.
Subject(s)
Gait , Male , Humans , Female , Aged , Prospective StudiesABSTRACT
BACKGROUND: Rural populations experience a higher prevalence of both food insecurity and type 2 diabetes mellitus (T2DM) than metropolitan populations and face many challenges in accessing resources essential to optimal T2DM self-management. This study aims to address these challenges by delivering a T2DM-appropriate food box and recipes directly to rural participants' homes. METHODS: This is a comparative effectiveness randomized controlled trial including 400 English- or Spanish-speaking rural adult participants with T2DM (HbA1c ≥6.5%) experiencing food insecurity. Participants are randomly assigned to a 3-month Healthy Food Delivery Intervention (HFDI) plus one 60-min virtual consultation with a diabetes educator or consultation only. The HFDI includes a weekly food box delivery with recipes. Data are collected at pre-intervention, 3-months (post-intervention), 9-months, and 15-months. The primary outcome is change in HbA1c, with secondary measures including diet quality (Healthy Eating Index-2015, calculated from one 24-h dietary recall at each data collection time point), cardio-metabolic risk factors (i.e., blood pressure, lipids, body mass index, glucose), and patient-centered outcomes (e.g., T2DM self-efficacy, T2DM-related distress). Process evaluation data (e.g., successful food box deliveries, diabetes educator consultation attendance, intervention satisfaction) are collected during and post-intervention (3-months). A cost-effectiveness analysis based on traditional cost per quality-adjusted life year gain thresholds will be conducted to estimate the incremental cost-effectiveness between HFDI plus consultation and consultation alone. CONCLUSION: Findings from this study will provide evidence regarding the effectiveness of an intervention that promotes participant adherence and improves access to healthy food. CLINICAL TRIAL REGISTRATION: NCT04876053.
Subject(s)
Diabetes Mellitus, Type 2 , Diet, Healthy , Glycated Hemoglobin , Rural Population , Adult , Female , Humans , Male , Body Mass Index , Comparative Effectiveness Research , Cost-Benefit Analysis , Diabetes Mellitus, Type 2/therapy , Diet, Healthy/methods , Food Supply , Glycated Hemoglobin/analysis , Patient Education as Topic/methods , Patient Education as Topic/organization & administration , Self-Management/methods , Randomized Controlled Trials as TopicABSTRACT
Background: Perceived risk of harm associated with cannabis use has decreased in recent decades, particularly among emerging adults who show the highest prevalence of use. Cannabis-related protective behavioral strategies (PBS) are associated with lower cannabis use and fewer consequences; however, individuals who perceive using cannabis as low risk may use cannabis PBS less often. Therefore, using cross-sectional data, we examined the associations between perceived risk of harm associated with cannabis use, cannabis PBS, and cannabis use frequency. Method: Participants were 146 emerging adults between the ages of 18-25 (56.2% female) who reported consuming cannabis at least 3 times/week and completed measures of past-month cannabis use, past three-month use of cannabis PBS, and perceived risk of harm associated with cannabis use. Path analyses examined direct and indirect effects of perceived risk of cannabis-related harm on cannabis frequency through cannabis PBS. Results: Most (66.4%) participants reported no perceived risk of harm associated with occasional cannabis use, whereas 30.1% reported no perceived risk of harm associated with regular cannabis use. Findings indicated a significant indirect effect between perceived risk of harm and cannabis use frequency through cannabis PBS, b = -10.23, SE = 3.80, 95% CI [-17.67, -2.80], p = .007. Conclusions: Among emerging adults who consume cannabis regularly, findings suggest that a greater perceived risk of cannabis-related harm is associated with decreased cannabis use frequency via increased use of cannabis PBS. Although future analyses evaluating causal mechanisms are needed, these findings have clinical implications for harm reduction interventions focused on cannabis use.
ABSTRACT
We present open-source tools for 3D analysis of photographs of dissected slices of human brains, which are routinely acquired in brain banks but seldom used for quantitative analysis. Our tools can: (i) 3D reconstruct a volume from the photographs and, optionally, a surface scan; and (ii) produce a high-resolution 3D segmentation into 11 brain regions per hemisphere (22 in total), independently of the slice thickness. Our tools can be used as a substitute for ex vivo magnetic resonance imaging (MRI), which requires access to an MRI scanner, ex vivo scanning expertise, and considerable financial resources. We tested our tools on synthetic and real data from two NIH Alzheimer's Disease Research Centers. The results show that our methodology yields accurate 3D reconstructions, segmentations, and volumetric measurements that are highly correlated to those from MRI. Our method also detects expected differences between post mortem confirmed Alzheimer's disease cases and controls. The tools are available in our widespread neuroimaging suite "FreeSurfer" ( https://surfer.nmr.mgh.harvard.edu/fswiki/PhotoTools ).
ABSTRACT
Opioid use disorder is a growing public health concern in the United States, causing economic burden and hindered by stigma. New forms of data, including location data, may improve the effectiveness of interventions for preventing and treating opioid use disorder and/or misuse, increase access to treatment and address racial and ethnic disparities. This qualitative study aimed to identify factors that contribute to users' experience with a publicly available location-tracking mobile app - and investigate their privacy and ethical concerns. The study was conducted through two 15-minute interviews within a 48-h time frame. Participants were recruited from a pool of past research participants, Facebook ads, and referrals, and had to meet certain inclusion criteria related to opioid use disorder and/or misuse. The study had a final sample of 30 participants, 15 male and 15 female. The study suggests that a simple onboarding process and convenient experience can enhance participant adherence to the study app and other similar location-based research apps. However, the study also found that participants had concerns about privacy and transparency about locational privacy when sharing their location data. To improve the app, researchers suggest incorporating user behavior earlier in the app development stage. The study also highlights the importance of addressing ethical and privacy concerns such as limiting the types of collected data, incorporating data encryption and retention strategies, giving access to research staff only, and not sharing the data with third-party companies or law enforcement agencies to increase user satisfaction.
Subject(s)
Mobile Applications , Opioid-Related Disorders , Humans , Male , Female , United States , Privacy , Analgesics, Opioid , Data CollectionABSTRACT
BACKGROUND: Despite the growing increase in the utilization of hospice in the U.S, disparities exist in the utilization of hospice. Accumulating evidence has shown that neighborhood characteristics have an impact on availability of hospice agencies. OBJECTIVE: To assess the association between neighborhood social vulnerability and hospice agency availability. METHODS: Using the Medicare Post-Acute Care and Hospice Provider Utilization and Payment Public Use Files (PAC PUF) for 2019. Hospice agency addresses were geocoded to the census tract level. Multivariable Poisson regression models were used to assess the association between socioeconomic status SVI theme and hospice agency availability adjusting for number of home health agencies, primary care health profession shortage, per cent Black, and Percent Hispanic at the census tract level and rurality. RESULTS: The socioeconomic status SVI subtheme was associated with decreased likelihood of hospice agency availability (adjusted IRR (aIRR), .56; 95% CI, .50- .63; P < .001). Predominantly Black, and predominantly Hispanic neighborhoods had lower rates of hospice agency availability (aIRR, .48; 95% CI, .39-.59; P < .001 and aIRR, .29; 95% CI, .24-.36; P < .001), respectively. CONCLUSION: Neighborhood socioeconomic disadvantage was associated with lower availability of hospice agencies. Policies aimed at increasing access to hospice should be cognizant of neighborhood socioeconomic disadvantage.
Subject(s)
Hospice Care , Hospices , Aged , Humans , United States , Socioeconomic Disparities in Health , Medicare , Residence Characteristics , Neighborhood Characteristics , Socioeconomic FactorsABSTRACT
Components of artificial intelligence (AI) for analysing social big data, such as natural language processing (NLP) algorithms, have improved the timeliness and robustness of health data. NLP techniques have been implemented to analyse large volumes of text from social media platforms to gain insights on disease symptoms, understand barriers to care and predict disease outbreaks. However, AI-based decisions may contain biases that could misrepresent populations, skew results or lead to errors. Bias, within the scope of this paper, is described as the difference between the predictive values and true values within the modelling of an algorithm. Bias within algorithms may lead to inaccurate healthcare outcomes and exacerbate health disparities when results derived from these biased algorithms are applied to health interventions. Researchers who implement these algorithms must consider when and how bias may arise. This paper explores algorithmic biases as a result of data collection, labelling and modelling of NLP algorithms. Researchers have a role in ensuring that efforts towards combating bias are enforced, especially when drawing health conclusions derived from social media posts that are linguistically diverse. Through the implementation of open collaboration, auditing processes and the development of guidelines, researchers may be able to reduce bias and improve NLP algorithms that improve health surveillance.
Subject(s)
Artificial Intelligence , Public Health Surveillance , Humans , Bias , Data Collection , Disease OutbreaksABSTRACT
INTRODUCTION: Increasing engagement in HIV care among people living with HIV, especially those from Black/African American and Hispanic/Latinx communities, is an urgent need. Mobility data that measure individuals' movements over time in combination with sociostructural data (eg, crime, census) can potentially identify barriers and facilitators to HIV care engagement and can enhance public health surveillance and inform interventions. METHODS AND ANALYSIS: The proposed work is a longitudinal observational cohort study aiming to enrol 400 Black/African American and Hispanic/Latinx individuals living with HIV in areas of the USA with high prevalence rates of HIV. Each participant will be asked to share at least 14 consecutive days of mobility data per month through the study app for 1 year and complete surveys at five time points (baseline, 3, 6, 9 and 12 months). The study app will collect Global Positioning System (GPS) data. These GPS data will be merged with other data sets containing information related to HIV care facilities, other healthcare, business and service locations, and sociostructural data. Machine learning and deep learning models will be used for data analysis to identify contextual predictors of HIV care engagement. The study includes interviews with stakeholders to evaluate the implementation and ethical concerns of using mobility data to increase engagement in HIV care. We seek to study the relationship between mobility patterns and HIV care engagement. ETHICS AND DISSEMINATION: Ethical approval has been obtained from the Institutional Review Board of the University of California, Irvine (#20205923). Collected data will be deidentified and securely stored. Dissemination of findings will be done through presentations, posters and research papers while collaborating with other research teams.
Subject(s)
Black or African American , HIV Infections , Humans , HIV Infections/epidemiology , Delivery of Health Care , Longitudinal Studies , Hispanic or Latino , Observational Studies as TopicABSTRACT
Background: The giant cell tumour of the tendon sheath (GCTTS) is the second most frequent soft tissue tumour affecting the hand. No consensus exists on the etiology, prognostic factors, or recurrence rate of GCTTS. This article presents a series of 18 cases supplemented by a literature review that examines the epidemiology, presentation, gross and microscopic characteristics, and recurrence rate of GCTTS. Methods: A total of 18 patients with a histo-pathological diagnosis of a GCTTS of the hand or finger were reviewed. The location for the tumour was limited to the wrist and hand. All cases were operated under Wide Awake Local anaesthesia (WALANT), and using a magnifying loupe. Results: A total of 18 patients presented at our institution with a diagnosis of GCTTS from 2016 to 2018. Of the 18 patients, 11 were female and 7 were male. The mean age of included patients was 43.6 years (31-59 years). The most common site for the lesion was the middle finger (4/18), followed by the index finger, wrist, and thumb (3/18 each). The little and ring finger were least commonly affected with one case each. The mean size of the tumour was 2.4 cm (0.5-5 cm). None of the patients reported recurrence of the lesion on an average follow-up of 18.8 months. Conclusion: GCTTS is a benign, slowly growing lesion of the hand that typically does not cause any symptoms and is treated with surgical resection. Meticulous excision of the GCTTS using magnification loupes to ensure appropriate wide excision of the tumour is the treatment of choice to prevent a recurrence. In addition, a radiographic and histopathological examination must be performed on the tumour to rule out other diagnoses. Finally, the function of the hand should be reconstructed to minimize the loss of any functional unit.
ABSTRACT
The increasing popularity of mHealth presents an opportunity for collecting rich datasets using mobile phone applications (apps). Our health-monitoring mobile application uses motion detection to track an individual's physical activity and location. The data collected are used to improve health outcomes, such as reducing the risk of chronic diseases and promoting healthier lifestyles through analyzing physical activity patterns. Using smartphone motion detection sensors and GPS receivers, we implemented an energy-efficient tracking algorithm that captures user locations whenever they are in motion. To ensure security and efficiency in data collection and storage, encryption algorithms are used with serverless and scalable cloud storage design. The database schema is designed around Mobile Advertising ID (MAID) as a unique identifier for each device, allowing for accurate tracking and high data quality. Our application uses Google's Activity Recognition Application Programming Interface (API) on Android OS or geofencing and motion sensors on iOS to track most smartphones available. In addition, our app leverages blockchain and traditional payments to streamline the compensations and has an intuitive user interface to encourage participation in research. The mobile tracking app was tested for 20 days on an iPhone 14 Pro Max, finding that it accurately captured location during movement and promptly resumed tracking after inactivity periods, while consuming a low percentage of battery life while running in the background.
Subject(s)
Blockchain , Mobile Applications , Smartphone , Advertising , AlgorithmsABSTRACT
Background: Fluoropyrimidine toxicity is often due to variations in the gene (DPYD) encoding dihydropyrimidine dehydrogenase (DPD). DPYD genotyping can be used to adjust doses to reduce the likelihood of fluoropyrimidine toxicity while maintaining therapeutically effective drug levels. Methods: A multiplex QPCR assay was locally developed to allow genotyping for six DPYD variants. The test was offered prospectively for all patients starting on fluoropyrimidines at the BC Cancer Centre in Vancouver and then across B.C., Canada as well as retrospectively for patients suspected to have had an adverse reaction to therapy. Dose adjustments were made for variant carriers. The incidence of toxicity in the first three cycles was compared between DPYD variant allele carriers and non-variant carriers. Subsequent to an initial implementation phase, this test was made available province-wide. Results: In 9 months, 186 patients were tested and 14 were found to be heterozygous variant carriers. Fluoropyrimidine-related toxicity was higher in DPYD variant carriers. Of 127 non-variant carriers who have completed chemotherapy, 18 (14%) experienced severe (grade ≥3, Common Terminology Criteria for Adverse Events version 5.0). Of note, 22% (3 patients) of the variant carriers experienced severe toxicity even after DPYD-guided dose reductions. For one of these carriers who experienced severe thrombocytopenia within the first week, DPYD testing likely prevented lethal toxicity. In DPYD variant carriers who tolerate reduced doses, a later 25% increase led to chemotherapy discontinuation. As a result, a recommendation was made to clinicians based on available literature and expert opinion specifying that variant carriers who tolerated two cycles without toxicity can have a dose escalation of only 10%. Conclusion: DPYD-guided dose reductions were a feasible and acceptable method of preventing severe toxicity in DPYD variant carriers. Even with dose reductions, there were variant carriers who still experienced severe fluoropyrimidine toxicity, highlighting the importance of adhering to guideline-recommended dose reductions. Following the completion of the pilot phase of this study, DPYD genotyping was made available province-wide in British Columbia.
ABSTRACT
This study examines the factors associated with COVID-19 testing, vaccination intent (both individually and jointly), and willingness to use contact tracing digital apps among a cohort of Black and Latinx men who have sex with men (BLMSM) living in Los Angeles during the initial peak (July 2020) of the COVID-19 pandemic. A questionnaire detailing participants COVID-19 experiences was sent to 300 primarily BLMSM after the first state-wide COVID-19 lockdown. Logistic regression models with random cluster effects were used for analyses. Forty-two percent (42%) tested for COVID-19, 27% were willing to get vaccinated, and about 45% reported willingness to use contact tracing digital apps. Controlling for intervention participation, age, education, marital status, employment, health, tobacco, binge drinking, and self-reported anxiety, those who were depressed had 33% (95% CI: 0.13 to 0.82) odds of using a prevention strategy (either test for COVID-19 or vaccination intent) as the group who were not depressed. Those who had high school diploma or less had 23% (95% CI: 0.11 to 0.48) odds to use digital contact tracing apps as the group with education level of at least Associate's or Bachelor's degree. Without considering the format of the test kits, vaccine side effects, and ease of use for digital contact tracing apps, participants appeared to still be hesitant in using COVID-19 prevention strategies at the initial height of the pandemic. Our findings suggest the need for further investigation into this hesitancy to better inform and prepare for future epidemics.
ABSTRACT
Learning-based image reconstruction models, such as those based on the U-Net, require a large set of labeled images if good generalization is to be guaranteed. In some imaging domains, however, labeled data with pixel- or voxel-level label accuracy are scarce due to the cost of acquiring them. This problem is exacerbated further in domains like medical imaging, where there is no single ground truth label, resulting in large amounts of repeat variability in the labels. Therefore, training reconstruction networks to generalize better by learning from both labeled and unlabeled examples (called semi-supervised learning) is problem of practical and theoretical interest. However, traditional semi-supervised learning methods for image reconstruction often necessitate handcrafting a differentiable regularizer specific to some given imaging problem, which can be extremely time-consuming. In this work, we propose "supervision by denoising" (SUD), a framework to supervise reconstruction models using their own denoised output as labels. SUD unifies stochastic averaging and spatial denoising techniques under a spatio-temporal denoising framework and alternates denoising and model weight update steps in an optimization framework for semi-supervision. As example applications, we apply SUD to two problems from biomedical imaging-anatomical brain reconstruction (3D) and cortical parcellation (2D)-to demonstrate a significant improvement in reconstruction over supervised-only and ensembling baselines. Our code available at https://github.com/seannz/sud.
ABSTRACT
Aflatoxins are carcinogenic toxins produced by fungi, and many countries legislate limits in food. Previous research suggests elevated liver cancer (LC) mortality in some areas may be due to aflatoxin exposure, but this has not been investigated spatially. We investigate links between aflatoxin legislation, climate, and LC mortality and other covariates globally. Comparison tests of LC mortality showed expected patterns with legislation and climate. They also showed associations between high LC mortality and high Hepatitis, low alcohol consumption, low health expenditure and high family agriculture rates. Spatial analysis showed latitudinal trend with significant clusters of low LC mortality in Europe and high rates in West Africa, Central America, East and South-East Asia. Only health expenditure and Hepatitis were significant in spatial regression, but climate and family agriculture were also significant in multiple linear regression (MLR). Results suggest that aflatoxin education and legislation should be expanded, particularly in hot/wet climates.