A Discriminant Function Approach to Adjust for Processing and Measurement Error When a Biomarker is Assayed in Pooled Samples

Robert Lyles,Emily Mitchell,Dane Van Domelen,Enrique Schisterman

doi:10.3390/ijerph121114723

Abstract

Pooling biological specimens prior to performing expensive laboratory assays has been shown to be a cost effective approach for estimating parameters of interest. In addition to requiring specialized statistical techniques, however, the pooling of samples can introduce assay errors due to processing, possibly in addition to measurement error that may be present when the assay is applied to individual samples. Failure to account for these sources of error can result in biased parameter estimates and ultimately faulty inference. Prior research addressing biomarker mean and variance estimation advocates hybrid designs consisting of individual as well as pooled samples to account for measurement and processing (or pooling) error. We consider adapting this approach to the problem of estimating a covariate-adjusted odds ratio (OR) relating a binary outcome to a continuous exposure or biomarker level assessed in pools. In particular, we explore the applicability of a discriminant function-based analysis that assumes normal residual, processing, and measurement errors. A potential advantage of this method is that maximum likelihood estimation of the desired adjusted log OR is straightforward and computationally convenient. Moreover, in the absence of measurement and processing error, the method yields an efficient unbiased estimator for the parameter of interest assuming normal residual errors. We illustrate the approach using real data from an ancillary study of the Collaborative Perinatal Project, and we use simulations to demonstrate the ability of the proposed estimators to alleviate bias due to measurement and processing error.

Highlights

Epidemiological studies in general and environmental health-oriented research in particular often require conducting expensive laboratory assays of biospecimens to measure continuous biomarker concentrations that may be associated with adverse outcomes
The first thing to note is that when both measurement and processing error are accounted for in model (8), the parameter β* is identifiable, but the residual variance (σ2) and the log odds ratio (OR) of interest is not
The other three models (ME only, processing error (PE) only, and neither measurement error (ME) nor PE) all agree with regard to a positive but non-significant estimated log odds ratio (log OR) characterizing the adjusted association between spontaneous abortion (SA) status and monocyte chemotactic protein 1 (MCP1) levels

Summary

Introduction

Epidemiological studies in general and environmental health-oriented research in particular often require conducting expensive laboratory assays of biospecimens to measure continuous biomarker concentrations that may be associated with adverse outcomes. In such studies, the physical pooling of samples prior to performing assays can be an effective design strategy aimed at reducing lab assay costs, ensuring or preserving sufficient specimen volumes, or minimizing the potential for measurements below a limit of detection. In discussing practical aspects of the approach, they anticipated the potential need to consider assay measurement errors in studies that utilize pooling. Schisterman et al [7] proposed a framework for modeling measurement error as a feature of individual and pooled assay results, as well as pool processing error

Methods

Results

Conclusion