Bayesian exposure-response analysis for immunoassays data with measurement errors
Bayesian exposure-response analysis for immunoassays data with measurement errors
批准号:
9978057
负责人:
Qixuan Chen
金额:
$20.08万
依托单位国家:
美国
项目类别:
财政年份:
2019
资助国家:
美国
项目状态:
已结题
起止时间:
2019-07-15 至 2023-06-30
关键词:
8 year oldAllergensAllergic DiseaseAllergic rhinitisAsthmaBackBayesian MethodBiological AssayBiological SciencesCalibrationCanis familiarisChildComputer softwareConcentration measurementDataData AnalysesDetectionDictyopteraDisease OutcomeDustEnvironmental ExposureExposure toExtrinsic asthmaFelis catusGoalsHealthHouse DustHypersensitivityImmunoassayIndividualInterventionLeadLiteratureMarkov chain Monte Carlo methodologyMeasurementMeasuresMethodsModelingMoldsMorbidity - disease rateMusNeighborhoodsNew York CityOutcomePathogenesisPrevalenceProteinsPublic HealthPyroglyphidaeReadingReproducibilityResearchRisk FactorsSamplingShapesStatistical MethodsSymptomsTimeUncertaintyWorkasthma preventionasthmaticcockroach allergendata explorationdata standardsdesignepidemiology studyindoor allergeninner cityinsightmouse allergenpyroglyphidregression treesresponsetooluser-friendly
中文摘要
点击翻译按钮获取中文摘要
英文摘要
PROJECT SUMMARY
The prevalence of allergic diseases and asthma among children is increasing worldwide. For sensitized individuals
with allergic asthma and rhinitis, continued exposure to indoor allergens will produce symptoms and exacerbation. Despite numerous epidemiological studies, the exposure-response relationships between indoor allergens and
asthma morbidity remain poorly understood. The goal of the proposed research is to develop new Bayesian methods and software to study exposure-response relationships between indoor allergen concentrations and asthma
morbidity among inner-city children with asthma. The new methods will correct measurement errors in the indoor allergen measurements using the standards data analyzed in immunoassays and provide estimates of allergen
concentrations at the extreme ends of calibration curves that would previously have been identified as below limits
of detection. In addition, the proposed methods will allow for assessing nonlinear exposure-response relationships
between a single allergen and a binary health outcome as well as the combined health effect of co-exposure to
multiple allergens and allow for inclusion of other covariates. Using Markov chain Monte Carlo simulations, we can
predict the health effects of exposures to indoor allergens and obtain imputations of the allergen concentrations
for those below limits of detection. We will apply the proposed methods to the data from the New York City
Neighborhood Asthma and Allergy Study (NAAS) among 7-8 years old asthmatic children living in New York
City. We will provide a user-friendly R package that implements the proposed methods and a Shiny app that
allows interactive data exploration. This will make our work more accessible, reproducible and directly useful.
Once completed, the proposed research will move forward not only statistical tools for analyzing immunoassay data
measured with errors and exposure-response analysis of such data but also research in indoor allergen exposure
and asthma morbidity among asthmatic children.
期刊论文(3)
专著(0)
科研奖励(0)
会议论文
Inference from Nonrandom Samples Using Bayesian Machine Learning.
使用贝叶斯机器学习从非随机样本进行推断。
DOI:
10.1093/jssam/smab049
发表时间:
2023
期刊:
Journal of survey statistics and methodology
影响因子:
2.1
作者:
[Liu,Yutao, Gelman,Andrew, Chen,Qixuan]
通讯作者:
Chen,Qixuan
DOI:
10.1016/j.annepidem.2022.04.008
发表时间:
2022-06
期刊:
Annals of epidemiology
影响因子:
5.6
作者:
[]
通讯作者:
海外基金