|
Activity Number:
|
360
- Contributed Poster Presentations: Section on Bayesian Statistical Science
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2020 : 10:00 AM to 2:00 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
|
Abstract #313612
|
|
|
Title:
|
Evaluating a Novel Hierarchical Bayesian Method for Noninvasively Estimating the Effects of Exposures on Proximal and Distal Airway Inflammation
|
|
Author(s):
|
Jingying Weng* and Noa Molshatski and Paul Marjoram and William James Gauderman and Frank D Gilliland and Sandrah Proctor Eckel
|
|
Companies:
|
University of Southern California, Department of Preventive Medicine,Biostatistic Division and University of Southern California and University of Southern California and University of Southern California and University of Southern California and University of Southern California
|
|
Keywords:
|
Bayesian;
Hierarchical;
FeNO;
air pollution;
pharmacokinetics
|
|
Abstract:
|
Exhaled nitric oxide (FeNO) is a biomarker of airway inflammation in exhaled breath. FeNO measurements are being used to detect effects of air pollution exposures in environmental epidemiology. New insights are possible since the inverse relationship between FeNO concentration and exhalation flow rate has been described using a deterministic two compartment model with parameters that quantify proximal and distal airway sources of FeNO. A standard approach is to estimate these “NO parameters” separately for each participant using FeNO measurements at different flow rates (Stage 1) and to then relate estimated NO parameters to potential determinants (Stage 2). We have developed an alternative novel one-step Unified Hierarchical Bayesian estimation method. In a comprehensive simulation study, we show that our method generally outperforms two-stage methods. Our method has excellent convergence (99.8% within 48 hours vs. 65% using a frequentist analog), low bias in estimated associations (< 1%), and is robust to correlation between NO parameters. We used our method to relate traffic exposures to proximal and distal inflammation in the southern California Children’s Health study.
|
Authors who are presenting talks have a * after their name.
