Discovering structure in multiple outcomes models for tests of childhood neurodevelopment.
Ontology highlight
ABSTRACT:
SUBMITTER: LaLonde A
PROVIDER: S-EPMC7225082 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Clinical trials often collect multiple outcomes on each patient, as the treatment may be expected to affect the patient on many dimensions. For example, a treatment for a neurological disease such as ALS is intended to impact several dimensions of neurological function as well as survival. The assessment of treatment on the basis of multiple outcomes is challenging, both in terms of selecting a test and interpreting the results. Several global tests have been proposed, and we provide a general approach to selecting and executing a global test. The tests require minimal parametric assumptions, are flexible about weighting of the various outcomes, and are appropriate even when some or all of the outcomes are censored. The test we propose is based on a simple scoring mechanism applied to each pair of subjects for each endpoint. The pairwise scores are then reduced to a summary score, and a rank-sum test is applied to the summary scores. This can be seen as a generalization of previously proposed nonparametric global tests (e.g., O'Brien, 1984). We discuss the choice of optimal weighting schemes based on power and relative importance of the outcomes. As the optimal weights are generally unknown in practice, we also propose an adaptive weighting scheme and evaluate its performance in simulations. We apply the methods to analyze the impact of a treatment on neurological function and death in an ALS trial.
| S-EPMC4960007 | biostudies-literature
Project description:BackgroundA very large body of research documents relationships between self-reported Adverse Childhood Experiences (srACEs) and adult health outcomes. Despite multiple assessment tools that use the same or similar questions, there is a great deal of inconsistency in the operationalization of self-reported childhood adversity for use as a predictor variable. Alternative conceptual models are rarely used and very limited evidence directly contrasts conceptual models to each other. Also, while a cumulative numeric 'ACE Score' is normative, there are differences in the way it is calculated and used in statistical models. We investigated differences in model fit and performance between the cumulative ACE Score and a 'multiple individual risk' (MIR) model that enters individual ACE events together into prediction models. We also investigated differences that arise from the use of different strategies for coding and calculating the ACE Score.MethodsWe merged the 2011-2012 BRFSS data (N = 56,640) and analyzed 3 outcomes. We compared descriptive model fit metrics and used Vuong's test for model selection to arrive at best fit models using the cumulative ACE Score (as both a continuous or categorical variable) and the MIR model, and then statistically compared the best fit models to each other.ResultsThe multiple individual risk model was a better fit than the categorical ACE Score for the 'lifetime history of depression' outcome. For the outcomes of obesity and cardiac disease, the cumulative risk and multiple individual risks models were of comparable fit, but yield different and complementary inferences.ConclusionsAdditional information-rich inferences about ACE-health relationships can be obtained from including a multiple individual risk modeling strategy. Results suggest that investigators working with large srACEs data sources could empirically derive the number of items, as well as the exposure coding strategy, that are a best fit for the outcome under study. A multiple individual risk model could also be considered in addition to the cumulative risk model, potentially in place of estimation of unadjusted ACE-outcome relationships.
| S-EPMC7525970 | biostudies-literature
Project description:To understand the formation, evolution, and function of complex systems, it is crucial to understand the internal organization of their interaction networks. Partly due to the impossibility of visualizing large complex networks, resolving network structure remains a challenging problem. Here we overcome this difficulty by combining the visual pattern recognition ability of humans with the high processing speed of computers to develop an exploratory method for discovering groups of nodes characterized by common network properties, including but not limited to communities of densely connected nodes. Without any prior information about the nature of the groups, the method simultaneously identifies the number of groups, the group assignment, and the properties that define these groups. The results of applying our method to real networks suggest the possibility that most group structures lurk undiscovered in the fast-growing inventory of social, biological, and technological networks of scientific interest.
| S-EPMC3240966 | biostudies-literature
Project description:The novel coronavirus disease 2019 (COVID-19) has spread worldwide and threatened human life. Diagnosis is crucial to contain the spread of SARS-CoV-2 infections and save lives. Diagnostic tests for COVID-19 have varying sensitivity and specificity, and the false-negative results would have substantial consequences to patient treatment and pandemic control. To detect all suspected infections, multiple testing is widely used. However, it may be challenging to build an assertion when the testing results are inconsistent. Considering the situation where there is more than one diagnostic outcome for each subject, we proposed a Bayesian probabilistic framework based on the sensitivity and specificity of each diagnostic method to synthesize a posterior probability of being infected by SARS-CoV-2. We demonstrated that the synthesized posterior outcome outperformed each individual testing outcome. A user-friendly web application was developed to implement our analytic framework with free access via http://www2.ccrb.cuhk.edu.hk/statgene/COVID_19/. The web application enables the real-time display of the integrated outcome incorporating two or more tests and calculated based on Bayesian posterior probability. A simulation-based assessment demonstrated higher accuracy and precision of the Bayesian probabilistic model compared with a single-test outcome. The online tool developed in this study can assist physicians in making clinical evaluations by effectively integrating multiple COVID-19 tests.
| S-EPMC8441124 | biostudies-literature
Project description:We consider the problem of estimating the effect of exposure on multiple continuous outcomes, when the outcomes are measured on different scales and are nested within multiple outcome classes, or "domains." Our Bayesian model extends the linear mixed models approach to allow the exposure effect to differ across domains and across outcomes within domains. Our model can be parameterized to allow shrinkage of the effects within the different levels of nesting, or to allow fixed domain-specific effects with no shrinkage. Our model also allows covariate effects to differ across outcomes and domains. Our methodology is applied to data on prenatal methylmercury exposure and multiple outcomes in four domains measured at 9 years of age on children enrolled in the Seychelles Child Development Study. We use three different priors and found that our main conclusions were not sensitive to the choice of prior. Simulation studies examine the model performance under alternative scenarios. Our results demonstrate that a sizeable increase in power is possible.
| S-EPMC3031784 | biostudies-literature
Project description:Most toxicologic studies focus on a single agent, although this does not reflect real-world scenarios in which humans are exposed to multiple chemicals.We prospectively studied manganese-lead interactions in early childhood to examine whether manganese-lead coexposure is associated with neurodevelopmental deficiencies that are more severe than expected based on effects of exposure to each metal alone.Four hundred fifty-five children were enrolled at birth in an longitudinal cohort study in Mexico City, provided blood samples, and were followed until 36 months of age. We measured lead and manganese at 12 and 24 months and assessed neurodevelopment at 6-month intervals from 12 to 36 months of age using Bayley Scales of Infant Development-II.Mean (± SD) blood concentrations at 12 and 24 months were, respectively, 24.7 ± 5.9 μg/L and 21.5 ± 7.4 μg/L for manganese and 5.1 ± 2.6 μg/dL and 5.0 ± 2.9 μg/dL for lead. Mixed-effects models, including Bayley scores at five time points, showed a significant interaction over time: highest manganese quintile × continuous lead; mental development score, β = -1.27 [95% confidence interval (CI): -2.18, -0.37]; psychomotor development score, β = -0.92 (95% CI: -1.76, -0.09). Slopes for the estimated 12-month lead effect on 18-month mental development and 24- through 36-month psychomotor development scores were steeper for children with high manganese than for children with midrange manganese levels.We observed evidence of synergism between lead and manganese, whereby lead toxicity was increased among children with high manganese coexposure. Findings highlight the importance of understanding health effects of mixed exposures, particularly during potentially sensitive developmental stages such as early childhood.
| S-EPMC3261931 | biostudies-literature
Project description:Methods for multiple informants help to estimate the marginal effect of each multiple source predictor and formally compare the strength of their association with an outcome. We extend multiple informant methods to the case of hierarchical data structures to account for within cluster correlation. We apply the proposed method to examine the relationship between features of the food environment near schools and children's body mass index z-scores (BMIz). Specifically, we compare the associations between two different features of the food environment (fast food restaurants and convenience stores) with BMIz and investigate how the association between the number of fast food restaurants or convenience stores and child's BMIz varies across distance from a school. The newly developed methodology enhances the types of research questions that can be asked by investigators studying effects of environment on childhood obesity and can be applied to other fields.
| S-EPMC4103695 | biostudies-literature
Project description:Perfluoroalkyl substances (PFAS) were among various persistent organic pollutants suspected to have been released during the collapse of the World Trade Center (WTC) on 9/11. Evidence on the association between prenatal PFAS exposure and child neurodevelopment is limited and inconsistent. This study evaluated the association between prenatal PFAS exposure and child cognitive outcomes measured at 5 different time points in a population prenatally exposed to the WTC disaster. The study population included 302 pregnant women in the Columbia University WTC birth cohort enrolled between December 13, 2001 and June 26, 2002 at three hospitals located near the WTC site: Beth Israel, St. Vincent's, and New York University Downtown. We evaluated the association between prenatal exposure to four PFAS (perfluorooctane sulfonate (PFOS), perfluorooctanoic acid (PFOA), perfluorohexanesulfonic acid (PFHxS), perfluorononanoic acid (PFNA)) and child neurodevelopment measured using the Bayley Scales of Infant Development (BSID-II) at approximately 1, 2 and 3 years of age and using The Wechsler Preschool and Primary Scale of Intelligence (WPPSI) at approximately 4 and 6 years of age. Geometric mean (range) concentrations of PFAS were 6.03 (1.05, 33.7), 2.31 (0.18, 8.14), 0.43 (<LOQ, 10.3) and 0.67 (<LOQ, 15.8) ng/mL for PFOS, PFOA, PFNA and PFHxS, respectively. Several PFAS were associated with increases in cognitive outcomes in females and overall (males and females combined). Child sex modified the association between PFOS and the mental development index measured using BSID-II, with the observed relationship being positive for females and negative for males. Through principal component analyses, we observed a negative relationship between PFNA and the psychomotor development index measured using BSID-II and the verbal IQ measured using WPPSI. Our results suggest a sex- and compound-specific relationship between prenatal PFAS exposures and childhood neurodevelopment.
| S-EPMC7362877 | biostudies-literature
Project description:ObjectiveMultilevel models have become a standard data analysis approach in intervention research. Although the vast majority of intervention studies involve multiple outcome measures, few studies use multivariate analysis methods. The authors discuss multivariate extensions to the multilevel model that can be used by psychotherapy researchers.Method and resultsUsing simulated longitudinal treatment data, the authors show how multivariate models extend common univariate growth models and how the multivariate model can be used to examine multivariate hypotheses involving fixed effects (e.g., does the size of the treatment effect differ across outcomes?) and random effects (e.g., is change in one outcome related to change in the other?). An online supplemental appendix provides annotated computer code and simulated example data for implementing a multivariate model.ConclusionsMultivariate multilevel models are flexible, powerful models that can enhance clinical research.
| S-EPMC4119868 | biostudies-literature
Project description:IntroductionEarly onset and high prevalence of allergic diseases result in high individual and socio-economic burdens. Several studies provide evidence for possible effects of environmental factors on allergic diseases, but these are mainly single-exposure studies. The exposome provides a novel holistic approach by simultaneously studying a large set of exposures. The aim of the study was to evaluate the association between a broad range of prenatal and childhood environmental exposures and allergy-related outcomes in children.Material and methodsAnalyses of associations between 90 prenatal and 107 childhood exposures and allergy-related outcomes (last 12 months: rhinitis and itchy rash; ever: doctor-diagnosed eczema and food allergy) in 6-11 years old children (n = 1270) from the European Human Early-Life Exposome cohort were performed. Initially, we used an exposome-wide association study (ExWAS) considering the exposures independently, followed by a deletion-substitution-addition selection (DSA) algorithm considering all exposures simultaneously. All the exposure variables selected in the DSA were included in a final multi-exposure model using binomial general linear model (GLM).ResultsIn ExWAS, no exposures were associated with the outcomes after correction for multiple comparison. In multi-exposure models for prenatal exposures, lower distance of residence to nearest road and higher di-iso-nonyl phthalate level were associated with increased risk of rhinitis, and particulate matter absorbance (PMabs) was associated with a decreased risk. Furthermore, traffic density on nearest road was associated with increased risk of itchy rash and diethyl phthalate with a reduced risk. DSA selected no associations of childhood exposures, or between prenatal exposures and eczema or food allergy.DiscussionThis first comprehensive and systematic analysis of many environmental exposures suggests that prenatal exposure to traffic-related variables, PMabs and phthalates are associated with rhinitis and itchy rash.
| S-EPMC8768577 | biostudies-literature