Bayesian Linear Model Research Articles

Sensitivity and feature importance of climate factors and evaluation of different machine learning models for predicting fire hotspots in Kalimantan, Indonesia

<p>Hotspots as indicators of forest fires capable of quickly monitoring large areas are often predicted using various machine learning methods. However, there is still little research that analyzes the sensitivity and feature importance of each predictor that forms a machine learning prediction model. This study evaluates and compares several machine learning methods to predict hotspots in Kalimantan. Using the most accurate machine learning model, each climate factor used as a predictor is analyzed for its sensitivity and feature importance. Some of the machine learning methods used include random forest, gradient boosting, Bayesian regression, and artificial neural networks. Meanwhile, several measures of sensitivity and feature importance used are variance-based, density-based, and distribution-based sensitivity indices, as well as permutation and Shapley feature importance. Evaluation of the ML model concluded that the Bayesian linear regression model outperformed other ML models, based on RMSE and explained variance score. Meanwhile, tree-based models, such as random forest and gradient boosting, are indicative of overfit. Based on the results of sensitivity analysis and feature importance, the number of dry days is the most important feature for the Bayesian linear regression model in predicting the number of hotspots in Kalimantan.</p>

A Comparison of the Modified Two-Part Bayesian Linear Regression Model with Existing Approaches for Estimating Error in Small Samples

A Comparison of the Modified Two-Part Bayesian Linear Regression Model with Existing Approaches for Estimating Error in Small Samples

A Prospective Cohort Study of Persistent Endocrine Disrupting Chemicals and Perceived Stress.

Persistent endocrine disrupting chemicals (EDCs) can dysregulate the stress response. We evaluated associations between persistent EDCs and perceived stress among participants from the Study of Environment, Lifestyle and Fibroids (n=1,394), a prospective cohort study of Black women. Participants completed the Perceived Stress Scale (PSS-4) at baseline, and every 20 months through 60 months (range of scores: 0-16); higher scores indicated higher stress. EDCs, including per- and polyfluoroalkyl substances (PFAS), polychlorinated biphenyls (PCBs), polybrominated diphenyl ethers (PBDEs), and organochlorine pesticides, were quantified in plasma samples at baseline. We fit Bayesian Kernel Machine Regression (BKMR) and linear mixed effects models to estimate associations of EDCs (as a mixture and individually) with PSS-4 scores at baseline and at each follow-up visit, respectively. Increasing percentiles of the mixture were not strongly associated with PSS-4 scores at baseline, and no interactions were observed among EDCs. Several individual EDCs (e.g., PFDA, PCB 118, PBDE 99) were associated with higher PSS-4 scores at baseline or follow-up, while other EDCs (e.g., PCB 138/158) were associated with lower PSS-4 scores at baseline or follow-up. The directionality of associations for individual EDCs was inconsistent across follow-up visits. In conclusion, specific EDCs may be associated with perceived stress in Black women.

Deep learning framework with Bayesian data imputation for modelling and forecasting groundwater levels

Although traditional physical models have been used to analyse groundwater systems, the emergence of novel machine learning models can improve the accuracy of the predictions. Deep learning has been prominent in environmental and climate change problems. In this paper, we present a framework for utilising deep learning models to predict groundwater levels based on nearby streamflow and rainfall data. We address the missing data problem using a Bayesian linear regression model within the deep learning framework. Our deep learning framework utilises models such as long-short term memory (LSTM) networks and convolutional neural networks (CNN) for multi-step ahead time series prediction. We examine the fluctuations in groundwater levels at various boreholes located near Middle Creek in New South Wales, Australia. We use the National Collaborative Research Infrastructure Strategy (NCRIS) groundwater database and utilise Bayesian linear regression to impute missing data. We investigate the accuracy of the selected models for individual and regional basins and univariate and multivariate strategies. Our results show that the LSTM-based regional model with multivariate strategy using rainfall data provided the best accuracy.

Application of non parametric Bayesian methods in high dimensional data

With the development of technology and the widespread collection of data, high-dimensional data analysis has become a research hotspot in many fields. Traditional parameter methods often face problems such as dimensional disasters in high-dimensional data analysis. Non parametric methods have broad application prospects in high-dimensional data because they do not rely on specific parameter distribution assumptions. The Bayesian rule is more suitable for dealing with noise and outliers in high-dimensional data because it takes uncertainty into account. Therefore, it is of great significance to combine non parametric methods with Bayesian methods for application research in high-dimensional data analysis. In this paper, the nonparametric Bayesian method was applied to the analysis of high-dimensional data, and the Dirichlet process Mixture model was used to cluster high-dimensional data. The regression analysis of high-dimensional data was carried out through the prediction model of nonparametric Bayesian regression. In this paper, the nonparametric Bayesian method based on Bayesian sparse linear model was used for feature selection of high-dimensional data. In order to determine the superiority of nonparametric Bayesian methods in high-dimensional data analysis, this paper conducted experiments on nonparametric Bayesian methods and traditional parametric methods in high-dimensional data analysis from five aspects of cluster analysis, classification analysis, regression analysis, feature selection and anomaly detection, and evaluated them through multiple indicators. This article explored the application of non parametric Bayesian methods in high-dimensional data analysis from these aspects through simulation experiments. The experimental results show that the clustering accuracy of the non parametric Bayesian clustering algorithm was 0.93, and the accuracy of the non parametric Bayesian classification algorithm was between 0.93 and 0.99; the coefficient of determination of nonparametric Bayesian regression algorithm was 0.98; the F1 values of non parametric Bayesian methods in anomaly detection ranged from 0.86 to 0.91, which was superior to traditional methods. Non parametric Bayesian methods have broad application prospects in high-dimensional data analysis, and can be applied in multiple fields such as clustering, classification, regression, etc.

The role of environmental sensitivity in the mental health of Syrian refugee children: a multi-level analysis

Individuals with high environmental sensitivity have nervous systems that are disproportionately receptive to both the protective and imperilling aspects of the environment, suggesting their mental health is strongly context-dependent. However, there have been few consolidated attempts to examine putative markers of sensitivity, across different levels of analysis, within a single cohort of individuals with high-priority mental health needs. Here, we examine psychological (self-report), physiological (hair hormones) and genetic (polygenic scores) markers of sensitivity in a large cohort of 1591 Syrian refugee children across two waves of data. Child-caregiver dyads were recruited from informal tented settlements in Lebanon, and completed a battery of psychological instruments at baseline and follow-up (12 months apart). Univariate and multivariate Bayesian linear mixed models were used to examine a) the interrelationships between markers of sensitivity and b) the ability of sensitivity markers to predict anxiety, depression, post-traumatic stress disorder, and externalising behaviour. Self-reported sensitivity (using the Highly Sensitive Child Scale) significantly predicted a higher burden of all forms of mental illness across both waves, however, there were no significant cross-lagged pathways. Physiological and genetic markers were not stably predictive of self-reported sensitivity, and failed to similarly predict mental health outcomes. The measurement of environmental sensitivity may have significant implications for identifying and treating mental illness, especially amongst vulnerable populations, but clinical utility is currently limited to self-report assessment.

Tropical Atmospheric Intraseasonal Oscillations Leading to Sea Level Extremes in Coastal Indonesia during Recent Decades

Abstract Coastal flooding induced by sea surface high extreme (HEX) events is an increasing risk to human society and infrastructure as both urban growth in coastal areas and anthropogenic sea level rise continue, especially for island nations like Indonesia. This paper investigates the role of atmospheric intraseasonal oscillations (ISOs), which are dominated by the Madden–Julian oscillation (MJO), in forcing HEXs on the coasts of Indonesia bordering the Indian Ocean. We use satellite altimetry data from 1993 to 2021 and tide gauge observations to detect HEXs, and modeling experiments using both the Regional Ocean Modeling System and a Bayesian dynamic linear model to understand the forcing and processes. We find that HEXs exhibit strong seasonality, with most events occurring during boreal winter (December–February) and spring (March–May) that are dominated by seasonal-to-decadal and intraseasonal variability respectively. In 32% of the 56 HEX events detected, the amplitude of ISO-induced sea level anomalies (SLAs) exceeds that of seasonal-to-decadal SLAs. Surface wind stress associated with atmospheric ISOs is the major forcing for intraseasonal SLAs, and both the remote westerly wind stress from the Indian Ocean equator and northwesterly longshore wind stress at the Indonesian coasts play important roles in driving the HEXs. The MJO is the dominant cause of ISO-dominated HEXs and its impact shows strong seasonal differences. Spring MJOs are associated with stronger convective anomalies over the eastern Indian Ocean equator that drive stronger zonal winds across the equatorial basin that lead to more HEX events compared to winter MJOs when the convection is shifted southward.

Effect of loading conditions on short fatigue crack propagation behaviours in cast Al[sbnd]Si alloys

The effect of loading conditions on short crack propagation behaviours in cast AlSi alloys was investigated by a combination of photo-microscopy monitoring and post mortem analysis. The findings suggest that the path of short cracks is minimally influenced by loading conditions, whereas loading conditions significantly affect the fatigue crack growth rate (FCGR) and its statistical characteristics. Crack closure effect is observed under zero and negative stress ratio conditions. Roughness-induced crack closure occurs due to the coarse grain microstructure of cast AlSi alloys and the Stage-I mode growth of cracks within grains in the microstructural short crack regime. The high level of plasticity around the crack tip under negative stress ratio conditions has a significant impact on FCGR, resulting in a negative crack opening stress. When the stress ratio exceeds approximately 0.3, short cracks exhibit no crack closure. The load-level effect is observed only at high load conditions with negative stress ratios. Finally, a probabilistic short crack growth model was established using a Bayesian linear regression model to analyse the effect of stress ratio on the uncertainty of FCGR. After considering the crack closure effect, the difference in distributions of FCGR model parameters decreases significantly among different stress ratio conditions.

Non-Gaussian normative modelling with hierarchical Bayesian regression

Abstract Normative modelling is an emerging technique for parsing heterogeneity in clinical cohorts. This can be implemented in practice using hierarchical Bayesian regression, which provides an elegant probabilistic solution to handle site variation in a federated learning framework. However, applications of this method to date have employed a Gaussian assumption, which may be restrictive in some applications. We have extended the hierarchical Bayesian regression framework to flexibly model non-Gaussian data with heteroskdastic skewness and kurtosis. To this end, we employ a flexible distribution from the sinh-arcsinh (SHASH) family, and introduce a novel reparameterisation and a Markov chain Monte Carlo sampling approach to perform inference in this model. Using a large neuroimaging dataset collected at 82 different sites, we show that the results achieved with this extension are equivalent or better than a warped Bayesian linear regression baseline model on most datasets, while providing better control over the parameters governing the shape of distributions that the approach is able to model. We also demonstrate that the attained flexibility is useful for accurately modelling highly nonlinear relationships between aging and imaging derived phenotypes, which shows that the extension is important for pushing the field of normative modelling forward. All methods described here are available in the open-source pcntoolkit.

Estimating positional plus-minus in the NBA

Abstract Plus-minus is a widely used performance metric in sports. Players with high plus-minus ratings are often considered more efficient than others. While numerous plus-minus models have emerged since the introduction of adjusted plus-minus in 2004, most of these metrics focus on evaluating player performance at the individual level. In the present study, we follow the plus-minus framework and adopt a hierarchical Bayesian linear model to estimate plus-minus at the position level in the NBA from 2015–16 to 2021–22. Results show that players with versatile offensive skills and big players who defend the paint area are the most valuable offensive and defensive contributors respectively. We also find that the gaps in offensive plus-minus between offensive position groups have decreased over time. Overall, our analysis offers valuable information regarding average positional values in the NBA, allowing more objective player comparisons within position groups. We also show improved prediction accuracy in player plus-minus when factoring in player positions.

Temporal changes in SARS-CoV-2 clearance kinetics and the optimal design of antiviral pharmacodynamic studies: an individual patient data meta-analysis of a randomised, controlled, adaptive platform study (PLATCOV)

Effective antiviral drugs prevent hospitalisation and death from COVID-19. Antiviral efficacy can be efficiently assessed in vivo by measuring rates of SARS-CoV-2 clearance estimated from serial viral genome densities quantitated in nasopharyngeal or oropharyngeal swab eluates. We conducted an individual patient data meta-analysis of unblinded arms in the PLATCOV platform trial to characterise changes in viral clearance kinetics and infer optimal design and interpretation of antiviral pharmacometric evaluations. Serial viral density data were analysed from symptomatic, previously healthy, adult patients (within 4 days of symptom onset) enrolled in a large multicentre, randomised, adaptive, pharmacodynamic, platform trial (PLATCOV) comparing antiviral interventions for SARS-CoV-2. Viral clearance rates over 1 week were estimated under a hierarchical Bayesian linear model with B-splines used to characterise temporal changes in enrolment viral densities and clearance rates. Bootstrap re-sampling was used to assess the optimal duration of follow-up for pharmacometric assessment, where optimal was defined as maximising the expected Z score when comparing effective antivirals with no treatment. PLATCOV is registered at ClinicalTrials.gov, NCT05041907. Between Sept 29, 2021, and Oct 20, 2023, 1262 patients were randomly assigned in the PLATCOV trial. Unblinded data were available from 800 patients (who provided 16 818 oropharyngeal viral quantitative PCR [qPCR] measurements), of whom 504 (63%) were female. 783 (98%) patients had received at least one vaccine dose and 703 (88%) were fully vaccinated. SARS-CoV-2 viral clearance was biphasic (bi-exponential). The first phase (α) was accelerated by effective interventions. For all the effective interventions studied, maximum discriminative power (maximum expected Z score) was obtained when evaluating serial data from the first 5 days after enrolment. Over the 2-year period studied, median viral clearance half-lives estimated over 7 days shortened from 16·6 h (IQR 15·3 to 18·2) in September, 2021, to 9·2 h (8·0 to 10·6) in October, 2023, in patients receiving no antiviral drugs, equivalent to a relative reduction of 44% (95% credible interval [CrI] 19 to 64). A parallel reduction in viral clearance half-lives over time was observed in patients receiving antiviral drugs. For example, in the 158 patients assigned to ritonavir-boosted nirmatrelvir (3380 qPCR measurements), the median viral clearance half-life reduced from 6·4 h (IQR 5·7 to 7·3) in June, 2022, to 4·8 h (4·2 to 5·5) in October, 2023, a relative reduction of 26% (95% CrI -4 to 42). SARS-CoV-2 viral clearance kinetics in symptomatic, vaccinated individuals accelerated substantially over 2 years of the pandemic, necessitating a change to how new SARS-CoV-2 antivirals are compared (ie, shortening the period of pharmacodynamic assessment). As of writing (October, 2023), antiviral efficacy in COVID-19 can be efficiently assessed in vivo using serial qPCRs from duplicate oropharyngeal swab eluates taken daily for 5 days after drug administration. Wellcome Trust.

Opioid Risk Tool, in-hospital opioid exposure, and opioid demand predict pain outcomes following traumatic injury.

Prescribed opioids are a mainstay pain treatment after traumatic injury, but a subgroup of patients may be at risk for continued opioid use. We evaluated the predictive utility of a traditional screening tool, the Opioid Risk Tool (ORT), and two other measures: average in-hospital milligram morphine equivalents (MME) per day and an assessment of opioid demand in predicting pain outcomes. Assessments of pain-related outcomes (pain intensity, interference, injury-related stress, and need for additional pain treatment) were administered at 2 weeks and 12 months post-discharge in a sample of 34 patients hospitalized for traumatic injury. Bayesian linear models were used to evaluate changes in responses over time as a function of predictors. High-risk ORT, higher MME per day, and greater opioid demand predicted less change in outcomes over time. This report provides first evidence that malleable factors of opioid and opioid demand have utility in predicting pain outcomes following traumatic injury.

Estimating the Distribution of True Rates of Visual Field Progression in Glaucoma.

The purpose of this study was to estimate the distribution of the true rates of progression (RoP) of visual field (VF) loss. We analyzed the progression of mean deviation over time in series of ≥ 10 tests from 3352 eyes (one per patient) from 5 glaucoma clinics, using a novel Bayesian hierarchical Linear Mixed Model (LMM); this modeled the random-effect distribution of RoPs as the sum of 2 independent processes following, respectively, a negative exponential distribution (the "true" distribution of RoPs) and a Gaussian distribution (the "noise"), resulting in a skewed exGaussian distribution. The exGaussian-LMM was compared to a standard Gaussian-LMM using the Watanabe-Akaike Information Criterion (WAIC). The random-effect distributions were compared to the empirical cumulative distribution function (eCDF) of linear regression RoPs using a Kolmogorov-Smirnov test. The WAIC indicated a better fit with the exGaussian-LMM (estimate [standard error]: 192174.4 [721.2]) than with the Gaussian-LMM (192595 [697.4], with a difference of 157.2 [22.6]). There was a significant difference between the eCDF and the Gaussian-LMM distribution (P < 0.0001), but not with the exGaussian-LMM distribution (P = 0.108). The estimated mean (95% credible intervals, CIs) "true" RoP (-0.377, 95% CI = -0.396 to -0.359 dB/year) was more negative than the observed mean RoP (-0.283, 95% CI = -0.299 to -0.268 dB/year), indicating a bias likely due to learning in standard LMMs. The distribution of "true" RoPs can be estimated with an exGaussian-LMM, improving model accuracy. We used these results to develop a fast and accurate analytical approximation for sample-size calculations in clinical trials using standard LMMs, which was integrated in a freely available web application.

Estimating the burden of vitiligo: a systematic review and modelling study

Vitiligo is a chronic autoimmune disease characterised by depigmented skin patches, which can pose substantial psychosocial challenges particularly in individuals with dark skin tones. Despite its impact on quality of life, there is an absence of standardised global epidemiological data. We sought to address this gap with the present study. In this study we did a systematic review and modelling analysis to estimate the global, regional, and national prevalence and incidence of vitiligo. We did a comprehensive search of nine digital libraries (PubMed, Embase, Web of Science, Scientific Electronic Library Online, KCI Korean Journal Database, Russian Science Citation Index, Western Pacific Region Index Medicus, Informit, and Health Research and Development Information Network) from inception up to May 25, 2023. We included cross-sectional or cohort studies reporting the incidence rate or prevalence of vitiligo, or data from which incidence rate or prevalence could be calculated, in the general population of a country or area of a country. Summary estimate data were extracted. A main outcome was to estimate the worldwide, regional, and country-specific lifetime prevalence of vitiligo diagnosed by physicians or dermatologists among the general population and in adults and children (as per age groups defined in included studies). We used a Bayesian hierarchical linear mixed model to estimate prevalence, and calculated number of affected individuals using the UN population structure in 2022. In estimating lifetime prevalence, studies reporting point or period prevalence were excluded. Our other main outcome was to estimate incidence rates of vitiligo, but due to a small number of studies, the data on incidence were presented in a descriptive summary. This study was registered on PROSPERO, CRD42023390433. Our search identified 22 192 records, of which 90 studies met our inclusion criteria. Of these studies, six focused on the incidence of vitiligo, 79 reported on the prevalence of vitiligo, and five provided data on both incidence and prevalence. 71 studies reported on lifetime prevalence. In the most recent years studied, incidence rates in the general population ranged from 24·7 cases (95% CI 24·3-25·2) per 100 000 person-years in South Korea in 2019, to 61·0 cases (60·6-61·4) in the USA in 2017. In individual studies, incidence rates showed an increasing trend over the periods studied. The global lifetime prevalence of vitiligo diagnosed by a physician or dermatologist was estimated at 0·36% (95% credible interval [CrI] 0·24-0·54) in the general population (28·5 million people [95% CrI 18·9-42·6]), 0·67% (0·43-1·07) in the adult population (37·1 million adults [23·9-58·9]), and 0·24% (0·16-0·37) in the child population (5·8 million children [3·8-8·9]). Vitiligo prevalence was higher in adults than in children across all regions. Central Europe and south Asia reported the highest prevalence (0·52% [0·28-1·07] and 0·52% [0·33-0·82], respectively, in the general population). This study highlights the need for standardised epidemiological data collection globally to inform public health policies and improve vitiligo diagnosis and management. Emphasis on the impact on individuals with darker skin tones is crucial to reducing stigma and improving quality of life. Furthermore, our study highlights the need to conduct more research in regions and populations that have been historically under-represented, to effectively address the worldwide burden of vitiligo. None.

Exploring transportation equity issues for persons with disabilities: The impact of gender on mobility and accessibility indicators

IntroductionPersons with disabilities still face numerous barriers in their everyday lives, especially in transportation. The problem of access to transportation is identified through fewer daily trips and more barriers in public transport. These problems indicate transportation equity issues among persons with disabilities. Another issue recognized in previous studies was a gender imbalance in the samples that could indicate gender equality problems among persons with disabilities. This paper aims to investigate mobility and accessibility indicators among persons with disabilities, with a particular emphasis on the impact of gender, in order to explore two critical transportation equity issues: inclusivity and social justice. MethodsThe mobility and accessibility indicators analyzed in this research were the Number of daily trips, Mobility satisfaction, Infrastructure accessibility satisfaction, and Modal distributions of daily trips. The data about indicators was collected by an online version of a questionnaire. The research was performed on 100 persons with disabilities from Serbia, equally distributed by gender. The most common recorded diagnosis of the respondents was spinal cord injury. ResultsIn general, respondents made 3.26 trips per day. At two transportation modes, we identified significant differences between males and females. Males frequently tripped as passenger car drivers, and females often traveled as passengers in passenger cars. Additionally, nine Bayesian linear regression models with weak informative prior distributions brought much helpful information. ConclusionsThe obtained results bring stakeholders valuable information in creating policies, practices, and recommendations to achieve specific goals related to transportation equity. Improving flexibility and time efficiency of females’ trips and resolving the problem of females’ fear of abuse and harassment in taxi cars were recognized as the two most critical topics.

Genetic variation within a stick insect species associated with community-level traits.

Phenotypic variation within species can affect the ecological dynamics of populations and communities. Characterizing the genetic variation underlying such effects can help parse the roles of genetic evolution and plasticity in 'eco-evolutionary dynamics' and inform how genetic variation may shape patterns of evolution. Here we employ genome-wide association (GWA) methods in Timema cristinae stick insects and their co-occurring arthropod communities to identify genetic variation associated with community-level traits. Previous studies have shown that maladaptation (i.e., imperfect crypsis) of T. cristinae can reduce the abundance and species richness of other arthropods due to an increase in bird predation. Whether genetic variation that is independent from crypsis has similar effects is unknown and was tested here using genome-wide genotyping-by-sequencing data of stick insects, arthropod community information, and GWA mapping with Bayesian sparse linear mixed models. We find associations between genetic variation in stick insects and arthropod community traits. However, these associations disappeared when host-plant traits are accounted for. We thus use path analysis to disentangle interrelationships among stick-insect genetic variation, host-plant traits and community traits. This revealed that host-plant size has large effects on arthropod communities, while genetic variation in stick insects has a smaller, but still significant effect. Our findings demonstrate that: (1) genetic variation in a species can be associated with community-level traits, but that (2) interrelationships among multiple factors may need to be analyzed to disentangle whether such associations represent causal relationships. This work helps to build a framework for genomic studies of eco-evolutionary dynamics.

Quantifying vowel category distinctness using Bayesian modelling

Phonetic and sociolinguistic studies of vowel merger require a measure of acoustic distinctness between vowel categories. Three desiderata for such a metric are that it be multivariate, in the sense that it account for correlations between dimensions (e.g., F1 and F2), control for other factors affecting vowel formants (e.g. surrounding consonants), and work for unbalanced data (common in naturalistic data). Previous work (Nycz and Hall-Lew, 2013; Kelley &amp; Tucker, 2020) has considered a variety of measures, including variants of Euclidean distance, Pillai score, and Bhattacharyya affinity, but none meet all three criteria. We present a new method for quantifying vowel merger that meets all desiderata and can be applied to different metrics: we fit a Bayesian mixed-effects linear model to jointly predict F1 and F2, then compute any desired metric—here, Euclidean distance, Pillai score, and Bhattacharyya affinity—from the posterior. We evaluate each metric, and the overall method, to describe PIN-PEN across a range of English dialect corpora. We find that controlling for covariates and unbalanced data adds substantial signal, but that multivariate modelling does not perform substantially better than univariate modelling. Additionally, we argue that Bhattacharyya affinity has particularly desirable properties (e.g., allowing for heteroskedastic data: Johnson, 2015).

Longitudinal antibody dynamics after COVID-19 vaccine boosters based on prior infection status and booster doses

Global concern over COVID-19 vaccine distribution disparities highlights the need for strategic booster shots. We explored longitudinal antibody responses post-booster during the Omicron wave in a Japanese cohort, emphasizing prior infection and booster doses. This prospective cohort study included 1763 participants aged 18 years and older with at least three vaccine doses (7376 datapoints). Antibody levels were measured every 2 months. We modeled temporal declines in antibody levels after COVID-19 vaccine boosters according to prior infection status and booster doses using a Bayesian linear mixed-effects interval-censored model, considering age, sex, underlying conditions, and lifestyle. Prior infection enhanced post-booster immunity (posterior median 0.346, 95% credible interval [CrI] 0.335–0.355), maintaining antibody levels (posterior median 0.021; 95% CrI 0.019–0.023) over 1 year, in contrast to uninfected individuals whose levels had waned by 8 months post-vaccination. Each additional booster was correlated with higher baseline antibody levels and slower declines, comparing after the third dose. Female sex, older age, immunosuppressive status, and smoking history were associated with lower baseline post-vaccination antibodies, but not associated with decline rates except for older age in the main model. Prior infection status and tailored, efficient, personalized booster strategies are crucial, considering sex, age, health conditions, and lifestyle.

Damage detection for structural health monitoring using reinforcement and imitation learning

Structural damages are responsible for expenses associated with maintaining the safety and serviceability of infrastructures. Detecting damages is difficult because they often develop over years affecting structural responses in orders of magnitudes smaller than external effects, such as temperature. When damage occurs, structural responses depart from a normal condition to an abnormal one, which is referred to as an anomaly. Existing anomaly detection methodologies lack a mechanism to quantify the probability of rightfully detecting anomalies as a function of the anomaly’s characteristics, e.g. duration and magnitude, and associate them with the severity of structural damages. This paper proposes a framework addressing these challenges by relying on Bayesian dynamic linear models as well as reinforcement and imitation learning approaches. The former allows separating the changes in the structural responses from the ones caused by external effects, while the latter two enable incorporating information obtained from the changes in the structural responses for detecting anomalies. The proposed methodologies are validated using measurements collected on three instrumented bridge spans in Canada. The results show a good performance of the methods proposed in detecting structural damages with different severity levels and lay the foundation for further applications for other civil infrastructures.

Global, regional and national epidemiology of alopecia areata: a systematic review and modelling study.

Alopecia areata (AA) is a chronic autoimmune disease that leads to a high psychiatric, economic and systemic disease burden. A comprehensive understanding of AA epidemiology is essential for evaluating healthcare source utilization; however, a systematic approach to summarizing epidemiological data on AA is lacking. To investigate systematically the global, regional and national incidence and prevalence of AA. A structured search was conducted using the databases MEDLINE, Embase, Cochrane Library, Web of Science, SciELO and Korean Journal Database from their date of inception to 4 October 2023. Studies that reported the prevalence or incidence of AA were included. We used a Bayesian hierarchical linear mixed model to analyse prevalence estimates. The primary outcomes of our study were the global, regional and national prevalence of physician-diagnosed AA for the overall population, for adults and for children. The incidence data were summarized descriptively. In total, 88 studies from 28 countries were included in the analysis. The reported incidence of AA tended to be higher in adults aged 19-50 years, and this trend was consistent with its estimated prevalence. The reported prevalence in overall populations tended to be higher in men vs. women. The estimated lifetime prevalence rate of AA was 0.10% [95% credible interval (CrI) 0.03-0.39] in the general population worldwide, 0.12% (95% CrI 0.02-0.52) in adults and 0.03% (95% CrI 0.01-0.12) in children. The estimated prevalence of AA was highest in the Asian region and lowest in the African region. In this study, 48% of the Global Burden of Disease regions had insufficient data on the prevalence or incidence of AA. Further studies are needed to provide epidemiological information on middle- and low-income countries. Our study may serve as a crucial reference in terms of healthcare policy decisions.