Predictor Variables Research Articles

A - 128 Informant Characteristics Impact Clinical Dementia Rating Scale Sum of Boxes in Mild Cognitive Impairment

Abstract Objective The Clinical Dementia Rating (CDR) Scale is an informant-based instrument widely used in clinical and research settings to stage dementia severity. Informant-based reports of functioning have been shown to be influenced by informant characteristics, indicating a potential source of bias. The current study adds to this growing area of research by exploring the differential impact of informant characteristics on CDR Sum of Boxes (CDR-SB) among non-Hispanic White (NHW), non-Hispanic Black (NHB) and Hispanic older adults with mild cognitive impairment (MCI). Method Participants included 2775 older adults diagnosed with MCI from the National Alzheimer’s Coordinating Center Uniform Data Set. Multiple linear regression models with forward selection evaluated the extent to which various informant characteristics predicted CDR-SB scores in the whole sample and NHW (n = 2170), NHB (n = 495), and Hispanic (n = 110) groups, covarying for participant demographics and cognition (MoCA). Results Informant sex, education, age, relationship type, and cohabitation status significantly predicted CDR-SB scores in this sample (R2 = 0.096, p < 0.001). Models stratified by race and ethnicity accounted for 20.2%, 10.3%, and 6.9% of the variance in CDR-SB scores in Hispanic, NHB, and NHW groups, respectively (ps < 0.001). Variability in model predictors was observed across groups, with informant characteristics accounting for more model variance than participant demographics in Hispanic and NHB groups. Results remained significant after adjusting for multiple comparisons. Conclusions Informant characteristics and relational factors may influence perceptions of participant functioning on the CDR-SB and may particularly affect scores among Hispanic older adults with MCI, though further validation in community-based cohorts with adequate racial and ethnic representation is warranted.

Dengue hemorrhagic fever prediction in coastal area using geographically weighted regression

Dengue hemorrhagic fever (DHF) is still a health problem globally, including in Indonesia. Geographical and climatic conditions in coastal areas are different from other areas, which may impact differences in environmental risk factors for dengue. This study aims to create a prediction model for the incidence of DHF in coastal areas. The research was conducted in Bantul Regency, Indonesia, involving data from 2015-2019. Dengue incidence data were collected from the health office. Climatic data were from climatology station. Data on altitude and shoreline distance were obtained by geographic information system (GIS) processing. Population density and wide settlement area are obtained from the Bureau of Statistics. The geographically weighted regression (GWR) analysis was carried out using GWR4. The results showed that GWR with a weighting of Fixed Bi-Square Kernel obtained an R2 value of 0.7768, better than the global model (R2 0.5254). It indicates that DHF (Y) in Bantul Regency is 77.68% determined by population density (X1), altitude (X2), settlement area (X3), shoreline distance (X4) and rainfall (X5) and the remaining 22.32% are influenced by other variables which are not investigated. Geographically, the predictor variables explain the DHF incidence with a strong category in the central region, and weak in coastal area.

Sex differences in conditioned pain modulation effects and its associations with autonomic nervous system activities in healthy, younger individuals: a pilot study.

Sex differences in conditioned pain modulation (CPM) have not been sufficiently explored. This pilot study aimed to examine sex differences in CPM effects and associations between autonomic activities and CPM effects in healthy, younger individuals. University students were recruited from February to March 2021 and divided by sex. They remained seated for 10 minutes as a rest period, then immersed their right hands in cold water for 2 minutes as a cold period. The pressure pain threshold (PPT) was measured after each period, presenting the CPM index (%) using the formula: (PPTcold/PPTrest) × 100. Autonomic nervous system variables were calculated using the formula-(autonomic variablecold/autonomic variablerest) × 100-and suffixed by "index" such as low-frequency/high-frequency (LF/HF) index. Some psychological questionnaires were self-recorded. Sex differences in the CPM index were statistically compared, and a simple linear regression analysis between the CPM and autonomic indices was conducted. Thirty-two participants were analyzed (14 women and 18 men; aged 21.1 ± 0.6 and 20.9 ± 0.3 years, respectively). Conditioned pain modulation effects were not different at 127.0 ± 19.1% in women and 124.0 ± 18.7% in men. The LF/HF index, LF normalized unit (nu) index (LFnu), and HFnu index had significant predictor variables for the CPM index across overall samples. The LF/HF index and LFnu index were significant predictor variables for the CPM index for women but not for men. Conditioned pain modulation effects between groups seem to be similar. The LF/HF and LFnu indices in women were significant, indicating that descending pain modulations in women might be more associated with autonomic activities than those in men.

Dementia Disorders: A Narrative Review

This narrative review of research includes summaries of 40 papers on dementia disorders that were published during 2023. The publications of this period are primarily randomized controlled trials and systematic reviews/ meta-analyses of randomized controlled trials. A few of these are focused on the prevalence of dementia which approximated one per cent of the world’s population. Only a few studies focused on effects of dementia disorders including memory loss, discrimination, pain, depression and suicidality. Most of the studies addressed predictors of dementia disorders including neurotic personality, frequent tv/computer use and excessive exposure to metals. Loss of short-term memory and other negative experiences including negative life events, loneliness, stress and depression were also significant predictor variables in this recent literature. Physical conditions that were predictive of dementia included pain, hypertension, atrial fibrillation, multi-morbidities, inflammation, encephalitis and neuropathology. Potential underlying mechanisms included dysfunctional neurotransmitter systems (serotonergic, noradrenergic and dopaminergic) and gray matter loss in prefrontal, temporal and other regions associated with memory. Several research groups reported on effective interventions including a Mediterranean diet, plant-based diets, medicinal plants, psychedelics, second generation antidepressants, blood pressure medication, music therapy, aromatherapy and other alternative therapies. Methodological problems relate to the variability in the assessments of dementia disorders, the self-report measures and the cross-sectional data that are not definitive about directionality of predictors and effects of dementia disorders.

Identifying factors predicting outcomes after major trauma in older patients: Prognostic systematic review and meta-analysis.

Trauma is the most common cause of morbidity and mortality in older people, and it is important to determine the predictors of outcomes after major trauma in older people. MEDLINE, Embase, and Web of Science were searched, and manual search of relevant papers since 1987 to February 2023 was performed. Random-effects meta-analyses were performed. The primary outcome of interest was mortality, and secondary outcomes were medical complications, length of stay, discharge destination, readmission, and intensive care requirement. Among 6,064 studies in the search strategy, 136 studies qualified the inclusion criteria. Forty-three factors, ranging from demographics to patient factors, admission measurements, and injury factors, were identified as potential predictors. Mortality was the commonest outcome investigated, and increasing age was associated with increased risk of in-hospital mortality (odds ratio [OR], 1.05; 95% confidence interval [CI], 1.03-1.07) along with male sex (OR, 1.40; 95% CI, 1.24-1.59). Comorbidities of heart disease (OR, 2.59; 95% CI, 1.41-4.77), renal disease (OR, 2.52; 95% CI, 1.79-3.56), respiratory disease (OR, 1.40; 95% CI, 1.09-1.81), diabetes (OR, 1.35; 95% CI, 1.03-1.77), and neurological disease (OR, 1.42; 95% CI, 0.93-2.18) were also associated with increased in-hospital mortality risk. Each point increase in the Glasgow Coma Scale lowered the risk of in-hospital mortality (OR, 0.85; 95% CI, 0.76-0.95), while each point increase in Injury Severity Score increased the risk of in-hospital mortality (OR, 1.07; 95% CI, 1.04-1.09). There were limited studies and substantial variability in secondary outcome predictors; however, medical comorbidities, frailty, and premorbid living condition appeared predictive for those outcomes. This review was able to identify potential predictors for older trauma patients. The identification of these factors allows for future development of risk stratification tools for clinicians. Systematic Review and Meta-Analysis; Level III.

Drivers of adaptive capacity of rural women farmers: The role of climate action and information mediums in rural Ghana

AbstractGender‐differentiated roles, responsibilities, access, rights, and knowledge gaps shape women's vulnerability to climate change. This is especially critical for women farmers whose livelihoods are climate‐dependent. A key component in building women farmers’ resilience to climate change is deepening their adaptive capacity. Therefore, this research sought to measure the adaptive capacity of women farmers from two unique districts of Ghana using the sustainable livelihood capitals and investigate how access to climate information and the uptake of climate action can influence women's adaptive capacity. Rural women farmers (n = 497) were interviewed through a survey and supported with key informant interviews from six agricultural staff at the selected districts. The adaptive capacity of respondents was rated moderate at 0.405. Differences between the adaptive capacity of women from different agroecological zones (Dormaa East—0.422; East Gonja—0.388) were statistically insignificant (p > 0.05). All climate information mediums except the TV medium had a significant prediction on women farmers’ adaptive capacity. The odds of a decreasing relationship of predictor variables, such as extension officer medium, radio, and adaptation action, require strategic structuring to accrue holistic benefit. The study thus recommends deepening women's benefit from extension services by attracting and retaining female extensionists, while training extensionists on tailored techniques for engaging female farmers. Again, extensionists who report high outreach to female farmers should be incentivized. Traditional and modern Information and Communication Technology mediums must be explored and integrated as alternatives. Co‐benefit practices for both adaptation and mitigation should be encouraged among women farmers to deepen climate action.

Explainable machine learning for predicting stomatal conductance across multiple plant functional types

Stomatal conductance (gs) is a key leaf-level function controlling water, carbon, and energy exchange between vegetation and the surrounding environment. Conventionally, semi-empirical models have been used to model gs, but these models require re-parameterization as ecosystems undergo phenological changes over the growing season. In contrast, machine learning (ML) models offer a potential path to overcome this problem but are less interpretable than process-based models. This study explores ML as an approach to develop flexible and robust models of gs for a range of plant functional types (PFTs), including C3 crops, C3 grasses, shrubs, and tree species across different continents. An explainable machine-learning approach (eXML) was used here to provide novel interpretations and insights into the ML model formulations and relative predictor importance. We contrast the performance of three ML architectures: extreme gradient boosting, random forests, and neural networks. Models were developed and examined using many combinations of environmental and physiological predictors. The results demonstrated that ML models significantly outperform conventional semi-empirical models in predicting gs responses to the environment, while not requiring re-parameterization as is required in the semi-empirical paradigm. Particular focus is placed on models formulated around predictor sets that are: (a) relevant to gs estimation in modern terrestrial biophysical simulation models, and (b) composed of variables describing environmental and physiological drivers that can be remotely sensed non-invasively. “Generalized” models developed using data from all four PFTs demonstrated strong predictive performance using only three predictor variables, capturing 63–80 % of the variability in stomatal conductance across all ML architectures. Four predictor variables resulted in models capturing 79–83 % of gs variability, and models developed using all five predictor variables examined here were able to capture as much as 87 % of gs variability across all PFTs. Uncertainty in gs predictions was quantified using quantile regression. Shapley additive explanations was applied to unravel instance-based positive and negative contributions of environmental and physiological predictors to gs modeling, while illustrating that the models are consistent with the underlying ecophysiology. This work demonstrates the power of ML to introduce a new paradigm in the simulation of highly dynamic ecophysiological processes critical to environmental prediction.

Impact of missing data and ICC on full information maximum-likelihood estimation in multilevel SEMs

A Monte Carlo simulation study was conducted to investigate the performance of full information maximum-likelihood (FIML) estimator in multilevel structural equation modeling (SEM) with missing data and different intra-class correlations (ICCs) coefficients. The study simulated the influence of two independent variables (missing data patterns, and ICC coefficients) in multilevel SEM on five outcome measures (model rejection rates, parameter estimate bias, standard error bias, coverage, and power). Results indicated that FIML parameter estimates were generally robust for data missing on outcomes and/or higher-level predictor variables under the data completely at random (MCAR) and for data missing at random (MAR). However, FIML estimation yielded substantially lower parameter and standard error bias when data was not missing on higher-level variables, and in high rather than in low ICC conditions (0.50 vs 0.20). Future research should extend to further examination of the impacts of data distribution, complexity of the between-level model, and missingness on the between-level variables on FIML estimation performance.

Cervicofacial Pediatric Tissue Expansion: Aesthetic Unit-Based Algorithm.

Tissue expansion is a powerful tool for reconstruction of pediatric soft-tissue pathologies, but complication rates for children have been reported as high as 40%. Infection and implant extrusion lead to premature removal and delays in reconstruction. Expanding the head and neck is uniquely challenging because the confluence of facial aesthetic units must be respected. These challenges have prompted the senior author's creation of an aesthetic-unit based algorithm. A retrospective study of pediatric patients who underwent cervicofacial tissue expander placement by the senior author (R.J.R) was performed over a 17-year period. Predictor variables included age, sex, race, indication, number of expanders placed at each operation, serial expansion, expander type, expander size, home versus clinic inflation, and prophylactic antibiotics. Univariate and multivariate analyses were performed to identify risk factors for complications. An aesthetic-unit based reconstructive algorithm is proposed. Forty-eight pediatric patients had 111 cervicofacial tissue expanders placed. Twenty expanders were associated with complications (18%) for surgical site-infection (12.6%), extrusion (4.5%), and expander deflation (6.3%). Expanders placed for congenital nevi (p=0.042) and use of textured expander (p=0.027) were significantly associated with decreased complications. When controlling for covariates, serial expansion of the same site was associated with increased rates of readmission (p=0.027) after having just one prior expander. Iatrogenic ectropion occurred in 13.5% of the study population; expanders with at least one complication during tissue expansion were significantly associated with incidence of iatrogenic ectropion (p=0.026). By using an aesthetic-unit based algorithm, reconstructive outcomes can be optimized for pediatric cervicofacial tissue expansion.

Optimizing Screening for Intrastriatal Interventions in Huntington's Disease Using Predictive Models.

Intrastriatal delivery of potential therapeutics in Huntington's disease (HD) requires sufficient caudate and putamen volumes. Currently, volumetric magnetic resonance imaging is rarely done in clinical practice, and these data are not available in large research cohorts such as Enroll-HD. The objective of this study was to investigate whether predictive models can accurately classify HD patients who exceed caudate and putamen volume thresholds required for intrastriatal therapeutic interventions. We obtained and merged data for 1374 individuals across three HD cohorts: IMAGE-HD, PREDICT-HD, and TRACK-HD/TRACK-ON. We imputed missing data for clinical variables with >72% non-missing values and used the model-building algorithm BORUTA to identify the 10 most important variables. A random forest algorithm was applied to build a predictive model for putamen volume >2500 mm3 and caudate volume >2000 mm3 bilaterally. Using the same 10 predictors, we constructed a logistic regression model with predictors significant at P < 0.05. The random forest model with 1000 trees and minimal terminal node size of 5 resulted in 83% area under the curve (AUC). The logistic regression model retaining age, CAG repeat size, and symbol digit modalities test-correct had 85.1% AUC. A probability cutoff of 0.8 resulted in 5.4% false positive and 66.7% false negative rates. Using easily obtainable clinical data and machine learning-identified initial predictor variables, random forest, and logistic regression models can successfully identify people with sufficient striatal volumes for inclusion cutoffs. Adopting these models in prescreening could accelerate clinical trial enrollment in HD and other neurodegenerative disorders when volume cutoffs are necessary enrollment criteria. © 2024 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Niche position accounts for the positive occupancy–abundance relationship of lake fishes

AbstractAimIf the positive occupancy–abundance relationship prevails, locally abundant species are widely distributed. Although broadly supported, studies on lake fishes have thus far contributed little to this topic, especially at intermediate and small spatial scales. Here, the main objective was to investigate the relationship between occupancy and abundance of lake fish species within a large lake, as well as examine the relative importance of ecological niches, functional traits and phylogenetic relatedness in forming the relationship.LocationPoyang Lake, China.TaxonFishes.MethodsWe calculated occupancy and mean abundance for 78 fish species and estimated niche position and niche breadth for each species based on a set of environmental variables. Additionally, we generated four functional trait vectors and one phylogenetic vector, describing trait similarity and phylogenetic relatedness, respectively. Linear models, hierarchical partitioning analyses and boosted regression trees were used in combination to explore the relative role of niche position, niche breadth, trait vectors and phylogenetic relatedness in determining fish occupancy, abundance and their relationship.ResultsOccupancy and mean abundance of fish species in Poyang Lake showed a significantly positive and rather strong interspecific relationship. Interspecific variations in fish occupancy and abundance were well accounted for by niche position, followed by niche breadth. Nonetheless, trait vectors and phylogenetic relatedness were of minor importance in affecting fish occupancy and abundance. Additionally, occupancy was better explained than abundance by the predictor variables used, which was shown by both linear models and boosted regression trees.Main ConclusionsThis study suggests that the positive correlation between occupancy and abundance also occurs in lake fish species. Furthermore, ecological niche features, especially niche position, were more important than functional traits and phylogenetic relatedness in accounting for occupancy and abundance of fish species in Poyang Lake.

Predicting dental anxiety in young adults: classical statistical modelling approach versus machine learning approach

ObjectivesTo predict and identify the key demographic and clinical exposure factors associated with dental anxiety among young adults, and to compare if the traditional statistical modelling approach provides similar results to the machine learning (ML) approach in predicting factors for dental anxiety.MethodsA cross-sectional study of Western Illinois University students. Three survey instruments (sociodemographic questionnaire, modified dental anxiety scale (MDAS), and dental concerns assessment tool (DCA)) were distributed via email to the students using survey monkey. The dependent variable was the mean MDAS scores, while the independent variables were the sociodemographic and dental concern assessment variables. Multivariable analysis was done by comparing the classical statistical model and the machine learning model. The classical statistical modelling technique was conducted using the multiple linear regression analysis and the final model was selected based on Akaike information Criteria (AIC) using the backward stepwise technique while the machine learining modelling was performed by comparing two ML models: LASSO regression and extreme gradient boosting machine (XGBOOST) under 5-fold cross-validation using the resampling technique. All statistical analyses were performed using R version 4.1.3.ResultsThe mean MDAS was 13.73 ± 5.51. After careful consideration of all possible fitted models and their interaction terms the classical statistical approach yielded a parsimonious model with 13 predictor variables with Akaike Information Criteria (AIC) of 2376.4. For the ML approach, the Lasso regression model was the best-performing model with a mean RMSE of 0.617, R2 of 0.615, and MAE of 0.483. Comparing the variable selection of ML versus the classical statistical model, both model types identified 12 similar variables (out of 13) as the most important predictors of dental anxiety in this study population.ConclusionThere is a high burden of dental anxiety within this study population. This study contributes to reducing the knowledge gap about the impact of clinical exposure variables on dental anxiety and the role of machine learningin the prediction of dental anxiety. The predictor variables identified can be used to inform public health interventions that are geared towards eliminating the individual clinical exposure triggers of dental anxiety are recommended.

DIGITAL ELEVATION MODEL CORRECTION IN URBAN AREAS USING EXTREME GRADIENT BOOSTING, LAND COVER AND TERRAIN PARAMETERS

Abstract. The accuracy of digital elevation models (DEMs) in urban areas is influenced by numerous factors including land cover and terrain irregularities. Moreover, building artefacts in global DEMs cause artificial blocking of surface flow pathways. This compromises their quality and adequacy for hydrological and environmental modelling in urban landscapes where precise and accurate terrain information is needed. In this study, the extreme gradient boosting (XGBoost) ensemble algorithm is adopted for enhancing the accuracy of two medium-resolution 30-metre DEMs over Cape Town, South Africa: Copernicus GLO-30 and ALOS World 3D (AW3D). XGBoost is a scalable, portable and versatile gradient boosting library that can solve many environmental modelling problems. The training datasets are comprised of eleven predictor variables including elevation, urban footprints, slope, aspect, surface roughness, topographic position index, terrain ruggedness index, terrain surface texture, vector roughness measure, forest cover and bare ground cover. The target variable (elevation error) was calculated with respect to highly accurate airborne LiDAR. After training and testing, the model was applied for correcting the DEMs at two implementation sites. The corrections achieved significant accuracy gains which are competitive with other proposed methods. There was a 46–53% reduction in the root mean square error (RMSE) of Copernicus DEM, and a 72–73% reduction in the RMSE of AW3D DEM. These results showcase the potential of gradient-boosted decision trees for enhancing the quality of global DEMs, especially in urban areas.

Moral Values as Mediators in the Relationship between Prosocial Behaviour and Social Responsibility among University Students

Universities must confront social challenges and prepare their students to be future socially responsible professionals. This research considers social responsibility in depth and examines how it can be promoted among university students. Specifically, it analyses whether prosocial behaviour and moral values are predictor variables, and to study whether moral values are a mediator variable between prosocial behaviour and university student social responsibility. Non-probabilistic convenience sampling was used in a Spanish university (N = 193; 115 females; Mage = 19). Three scales were applied: the University Student Social Responsibility scale, the Prosocial Tendencies Measures scale and the Importance of Personal and Professional Values scale. The results of the regression models showed that prosocial behaviour and moral values both contributed significantly to the model (F (2,196) = 41.979; p &lt; .001), predicting 30.2% of university student social responsibility. In the mediation model, total effects between the variables were observed, as was an indirect effect of prosocial behaviour on social responsibility mediated by moral values (β = .07; t = 3.80; p &lt; .001). This suggests that university programmes that seek to help the community and enable people to discover values will more effectively be able to develop social responsibility.

Real-time prognostic biomarkers for predicting in-hospital mortality and cardiac complications in COVID-19 patients.

Hospitalized patients with Coronavirus disease 2019 (COVID-19) are highly susceptible to in-hospital mortality and cardiac complications such as atrial arrhythmias (AA). However, the utilization of biomarkers such as potassium, B-type natriuretic peptide, albumin, and others for diagnosis or the prediction of in-hospital mortality and cardiac complications has not been well established. The study aims to investigate whether biomarkers can be utilized to predict mortality and cardiac complications among hospitalized COVID-19 patients. Data were collected from 6,927 hospitalized COVID-19 patients from March 1, 2020, to March 31, 2021 at one quaternary (Henry Ford Health) and five community hospital registries (Trinity Health Systems). A multivariable logistic regression prediction model was derived using a random sample of 70% for derivation and 30% for validation. Serum values, demographic variables, and comorbidities were used as input predictors. The primary outcome was in-hospital mortality, and the secondary outcome was onset of AA. The associations between predictor variables and outcomes are presented as odds ratio (OR) with 95% confidence intervals (CIs). Discrimination was assessed using area under ROC curve (AUC). Calibration was assessed using Brier score. The model predicted in-hospital mortality with an AUC of 90% [95% CI: 88%, 92%]. In addition, potassium showed promise as an independent prognostic biomarker that predicted both in-hospital mortality, with an AUC of 71.51% [95% Cl: 69.51%, 73.50%], and AA with AUC of 63.6% [95% Cl: 58.86%, 68.34%]. Within the test cohort, an increase of 1 mEq/L potassium was associated with an in-hospital mortality risk of 1.40 [95% CI: 1.14, 1.73] and a risk of new onset of AA of 1.55 [95% CI: 1.25, 1.93]. This cross-sectional study suggests that biomarkers can be used as prognostic variables for in-hospital mortality and onset of AA among hospitalized COVID-19 patients.

Using decision tree to predict non-suicidal self-injury among young adults: the role of depression, childhood maltreatment and recent bullying victimization.

Importance: Non-suicidal self-injury (NSSI) is a significant mental health issue requiring a deeper understanding of its underlying causes, such as childhood maltreatment, adult bullying victimization, and depression. Previous studies have not adequately addressed the cumulative risks of these factors on NSSI among college students. This population-based study investigates these cumulative risk factors.Design, setting, and participants: The cross-sectional study included 63 university's college students with a mean age of 19.6 years (N = 95,833).Main outcomes and measures: Two Chi-Square Automatic Interaction Detection (CHAID) decision tree models were used to classify subgroups based on childhood maltreatment and adult bullying victimization experiences and to investigate their cumulative risks of NSSI. Recursive partitioning algorithms determined each predictor variable's relative importance.Results: The CHAID model accurately predicted NSSI behaviours with an overall accuracy rate of 77.8% for individuals with clinically relevant depressive symptoms and 97.2% for those without. Among depressed individuals, childhood emotional abuse was the strongest NSSI predictor (Chi-Square, 650.747; adjusted P < .001), followed by sexual and physical abuse. For non-depressed individuals, emotional abuse in childhood was the strongest NSSI predictor (Chi-Square, 2084.171; adjusted P < .001), with sexual and verbal bullying in the past year representing the most significant proximal risks.Conclusions and relevance: Emotional abuse during childhood profoundly impacts individuals, increasing the risk of NSSI in both depressed and non-depressed individuals. Clinically relevant depressive symptoms have a moderating effect on the relationship between childhood maltreatment, adult bullying victimization, and NSSI. Identifying these factors can inform targeted interventions to prevent NSSI development among young adults.

A Novel Approach for Predicting Anthropogenic CO2 Emissions Using Machine Learning Based on Clustering of the CO2 Concentration

The monitoring of anthropogenic CO2 emissions, which increase the atmospheric CO2 concentration, plays the most important role in the management of emission reduction and control. With the massive increase in satellite-based observation data related to carbon emissions, a data-driven machine learning method has great prospects for predicting anthropogenic CO2 emissions. Training samples, which are used to model predictions of anthropogenic CO2 emissions through machine learning algorithms, play a key role in obtaining accurate predictions for the spatial heterogeneity of anthropogenic CO2 emissions. We propose an approach for predicting anthropogenic CO2 emissions using the training datasets derived from the clustering of the atmospheric CO2 concentration and the segmentation of emissions to resolve the issue of the spatial heterogeneity of anthropogenic CO2 emissions in machine learning modeling. We assessed machine learning algorithms based on decision trees and gradient boosting (GBDT), including LightGBM, XGBoost, and CatBoost. We used multiple parameters related to anthropogenic CO2-emitting activities as predictor variables and emission inventory data from 2019 to 2021, and we compared and verified the accuracy and effectiveness of different prediction models based on the different sampling methods of training datasets combined with machine learning algorithms. As a result, the anthropogenic CO2 emissions predicted by CatBoost modeling from the training dataset derived from the clustering analysis and segmentation method demonstrated optimal prediction accuracy and performance for revealing anthropogenic CO2 emissions. Based on a machine learning algorithm using observation data, this approach for predicting anthropogenic CO2 emissions could help us quickly obtain up-to-date information on anthropogenic CO2 emissions as one of the emission monitoring tools.

Relationships Between Religious Commitment, Workplace Experiences, and Professional and Psychological Outcomes Among U.S. Muslim Physicians.

To examine relationships between religiosity, workplace discrimination, religious accommodation, and related professional and psychological outcomes among US Muslim physicians. In 2021, the authors surveyed 264 physicians from 3 U.S.-based Muslim clinician organizations. Religious commitment, as measured by multiple items, was evaluated as a possible predictor of workplace discrimination and accommodation; job turnover; career satisfaction; workplace motivation; and belonging, burnout, and depression. Bivariate regression models were used to identify possible significant relationships between predictor and outcome variables. Predictors with meaningful bivariate analyses were included in separate multivariate regression models for each outcome. Participants' mean age was 39.5 years (standard deviation, 10.03). Most were male (160/246; 65%), U.S.-born (146/244; 60%), completed medical school in the United States (190/243; 78%), and wore a beard/hijab (135/235; 57%). Participants identified as African American (40/247; 16%), Arab (55/247; 22%), South Asian (82/247; 33%), and White (70/247; 28%). Multivariate models demonstrated that religious importance was positively associated with discrimination from patients (odds ratio [OR] = 3.78; P = .02) and depression (OR = 5.36; P = .002), and negatively associated with prayer accommodation at work (OR = .20; P = .001). Engaging in congregational religious activities was negatively associated with discrimination from patients (OR = .64; P = .006) and job turnover (OR = .63; P = .02) and positively associated with accommodations for prayer (OR = 1.42; P = .008) and general religious identity accommodation (OR = 1.47; P = .01). Additionally, participant race and ethnicity were variably associated with these outcomes. This study demonstrates how religious identity may negatively associate with workplace experiences and well-being among U.S. Muslim physicians and highlights the buffering role of religious practice. It spotlights an urgent need for academic medical centers to ameliorate religious discrimination and implement workplace accommodation policies for Muslim physicians.

Predictive factors for resilience quotient among village health volunteers in Northern Thailand post-COVID-19

Village Health Volunteers (VHVs) played an important role during the COVID-19 virus outbreak by coordinating with the public health team and closely engaging with community members. This study aimed to assess the resilience quotient levels of VHVs in Northern Thailand post-COVID-19. The research involved a random sample of 416 VHVs and utilized various tools such as questionnaires. Data analysis employed descriptive statistics and stepwise multiple regression. The study revealed that most of the sample group were women (81.3%), with an average age of 55.03 years (X̅ = 55.03, SD = 10.44). Most were in a relationship (79.3%), and 49.0% had completed primary education. Additionally, 47.8% were employed in agriculture, and 54.3% reported having sufficient income. A significant portion of them, 70.7%, had no history of chronic illnesses, whereas 53.1% had previously tested positive for COVID-19. The overall resilience quotient level of VHVs was high (X̅ = 61.88, SD = 9.14). The study identified the following four significant predictor variables: mental health, anxiety, depression, and mental health literacy, accounting for 40.30% of the variance. These findings were statistically significant at 0.05 (R = 0.639, Adjusted R2 = 0.403, F = 71.071, P-value &lt; 0.001). In conclusion, this study provides valuable insights for developing targeted interventions and support systems to enhance the resilience quotient of VHVs, particularly in the post-COVID-19 landscape and similar situations.

(050) Vulvodynia: Risk Associated with Vulvar/Vaginal, Psychological and Physical Side Effects of Oral Contraceptive Use

Abstract Introduction Research has shown that hormonal contraceptive (HC) use is associated with risk for vulvar pain [1] and vulvodynia [2,3]. Although some literature has focused on combined hormonal contraceptives (CHCs), Bouchard et al [2] found that risk was higher for those using high progestin potency HCs. In addition to increased risk associated with HC use, research also suggests that characteristics of the menstrual cycle (eg., premenstrual symptoms) are associated with risk for vulvodynia [4]. Objective Test for associations between having a diagnosis of vulvodynia (including vestibulodynia) and experiencing vulvar/vaginal, psychological, and physical side effects from OC use. Test for differences in these associations across estroprogestinic OCs, progesterone only OCs, and OCs of an unknown composition (based on self-reports). Methods A sample of 2199 females participated in a larger study on genito-pelvic pain and sexuality and provided data on both HC use and genito-pelvic pain. Efforts were made to recruit a heterogenous sample, with an oversampling of females with genito-pelvic pain. The dependent variable was a dichotomous variable of whether they had ever received a diagnosis of vulvodynia or vestibulodynia. Predictor variables were: ever used each type of OC (analyses conducted separately for estroprogestinic, progesterone only, and unknown type); and experiencing the following side effects associated with each OC type: vulvar pain (dichotomous), vaginal dryness (dichotomous), decreased sexual desire (dichotomous), affective symptoms (sum of dichotomous responses to: anxiety, nervousness, depression, anger, mood swings) and physical symptoms (sum of dichotomous responses to: cramps, back and joint pain, bloating, cellulite, breast discomfort). Three nominal logistic regression analyses were conducted (one for each OC), and a final nominal logistic regression was conducted combining the relevant predictors for each OC into one analysis. Results Of the 2199 participants, n=673 had never used OCs, n=827 had used them in the past, and n=699 were currently using them. Regarding vulvar/vaginal pain, n=1083 had no vulvar or vaginal pain, n=341 had only vulvar pain, n=194 had only vaginal pain, and n=581 both vulvar and vaginal pain. Finally, regarding diagnoses, n=582 (26%) had a diagnosis of vulvodynia/vestibulodynia (all types combined). Results from the nominal logistic regressions are presented in Tables 1 and 2. Findings of central importance are: having ever used any of the three categories of OCs was associated with increased risk for a diagnosis; vulvar pain and vaginal dryness were the only side effects of OCs that demonstrated a consistent association with increased risk of having a diagnosis; side effects of estroprogestinic OCs were the most strongly associated with increased risk of having a diagnosis; and the effects observed in the first three models remained significant even when all were included in the same final analysis (with the exception of vulvar pain with progesterone only OC). Conclusions Use of both estroprogestinic and progesterone only OCs are associated with diagnosis of vulvodynia, but side effects of estroprogestinic OCs demonstrated the strongest association. Genital-specific side effects of OCs may represent indicators of a tissue-specific sensitivity to hormonal changes that are associated with risk for vulvodynia. Disclosure No.