Hierarchical group testing for multiple infections

Peijie Hou, Joshua M. Tebbs, Christopher R Bilder, Christopher S. McMahan

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Group testing, where individuals are tested initially in pools, is widely used to screen a large number of individuals for rare diseases. Triggered by the recent development of assays that detect multiple infections at once, screening programs now involve testing individuals in pools for multiple infections simultaneously. Tebbs, McMahan, and Bilder (2013, Biometrics) recently evaluated the performance of a two-stage hierarchical algorithm used to screen for chlamydia and gonorrhea as part of the Infertility Prevention Project in the United States. In this article, we generalize this work to accommodate a larger number of stages. To derive the operating characteristics of higher-stage hierarchical algorithms with more than one infection, we view the pool decoding process as a time-inhomogeneous, finite-state Markov chain. Taking this conceptualization enables us to derive closed-form expressions for the expected number of tests and classification accuracy rates in terms of transition probability matrices. When applied to chlamydia and gonorrhea testing data from four states (Region X of the United States Department of Health and Human Services), higher-stage hierarchical algorithms provide, on average, an estimated 11% reduction in the number of tests when compared to two-stage algorithms. For applications with rarer infections, we show theoretically that this percentage reduction can be much larger.

Original languageEnglish (US)
Pages (from-to)656-665
Number of pages10
JournalBiometrics
Volume73
Issue number2
DOIs
StatePublished - Jun 1 2017

Fingerprint

Group Testing
Infection
Chlamydia
Gonorrhea
Testing
infection
testing
United States Dept. of Health and Human Services
Infertility
Transition Probability Matrix
Department of Health and Human Services
Markov Chains
Operating Characteristics
Biometrics
Rare Diseases
Markov processes
Screening
Decoding
Percentage
Assays

Keywords

  • Case identification
  • Markov chain
  • Pooled testing
  • Screening
  • Sensitivity
  • Specificity

ASJC Scopus subject areas

  • Statistics and Probability
  • Medicine(all)
  • Immunology and Microbiology(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • Applied Mathematics

Cite this

Hierarchical group testing for multiple infections. / Hou, Peijie; Tebbs, Joshua M.; Bilder, Christopher R; McMahan, Christopher S.

In: Biometrics, Vol. 73, No. 2, 01.06.2017, p. 656-665.

Research output: Contribution to journalArticle

Hou, P, Tebbs, JM, Bilder, CR & McMahan, CS 2017, 'Hierarchical group testing for multiple infections', Biometrics, vol. 73, no. 2, pp. 656-665. https://doi.org/10.1111/biom.12589
Hou, Peijie ; Tebbs, Joshua M. ; Bilder, Christopher R ; McMahan, Christopher S. / Hierarchical group testing for multiple infections. In: Biometrics. 2017 ; Vol. 73, No. 2. pp. 656-665.
@article{aa5b0f1a0087494ea7014d0c78eaeb8e,
title = "Hierarchical group testing for multiple infections",
abstract = "Group testing, where individuals are tested initially in pools, is widely used to screen a large number of individuals for rare diseases. Triggered by the recent development of assays that detect multiple infections at once, screening programs now involve testing individuals in pools for multiple infections simultaneously. Tebbs, McMahan, and Bilder (2013, Biometrics) recently evaluated the performance of a two-stage hierarchical algorithm used to screen for chlamydia and gonorrhea as part of the Infertility Prevention Project in the United States. In this article, we generalize this work to accommodate a larger number of stages. To derive the operating characteristics of higher-stage hierarchical algorithms with more than one infection, we view the pool decoding process as a time-inhomogeneous, finite-state Markov chain. Taking this conceptualization enables us to derive closed-form expressions for the expected number of tests and classification accuracy rates in terms of transition probability matrices. When applied to chlamydia and gonorrhea testing data from four states (Region X of the United States Department of Health and Human Services), higher-stage hierarchical algorithms provide, on average, an estimated 11{\%} reduction in the number of tests when compared to two-stage algorithms. For applications with rarer infections, we show theoretically that this percentage reduction can be much larger.",
keywords = "Case identification, Markov chain, Pooled testing, Screening, Sensitivity, Specificity",
author = "Peijie Hou and Tebbs, {Joshua M.} and Bilder, {Christopher R} and McMahan, {Christopher S.}",
year = "2017",
month = "6",
day = "1",
doi = "10.1111/biom.12589",
language = "English (US)",
volume = "73",
pages = "656--665",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "2",

}

TY - JOUR

T1 - Hierarchical group testing for multiple infections

AU - Hou, Peijie

AU - Tebbs, Joshua M.

AU - Bilder, Christopher R

AU - McMahan, Christopher S.

PY - 2017/6/1

Y1 - 2017/6/1

N2 - Group testing, where individuals are tested initially in pools, is widely used to screen a large number of individuals for rare diseases. Triggered by the recent development of assays that detect multiple infections at once, screening programs now involve testing individuals in pools for multiple infections simultaneously. Tebbs, McMahan, and Bilder (2013, Biometrics) recently evaluated the performance of a two-stage hierarchical algorithm used to screen for chlamydia and gonorrhea as part of the Infertility Prevention Project in the United States. In this article, we generalize this work to accommodate a larger number of stages. To derive the operating characteristics of higher-stage hierarchical algorithms with more than one infection, we view the pool decoding process as a time-inhomogeneous, finite-state Markov chain. Taking this conceptualization enables us to derive closed-form expressions for the expected number of tests and classification accuracy rates in terms of transition probability matrices. When applied to chlamydia and gonorrhea testing data from four states (Region X of the United States Department of Health and Human Services), higher-stage hierarchical algorithms provide, on average, an estimated 11% reduction in the number of tests when compared to two-stage algorithms. For applications with rarer infections, we show theoretically that this percentage reduction can be much larger.

AB - Group testing, where individuals are tested initially in pools, is widely used to screen a large number of individuals for rare diseases. Triggered by the recent development of assays that detect multiple infections at once, screening programs now involve testing individuals in pools for multiple infections simultaneously. Tebbs, McMahan, and Bilder (2013, Biometrics) recently evaluated the performance of a two-stage hierarchical algorithm used to screen for chlamydia and gonorrhea as part of the Infertility Prevention Project in the United States. In this article, we generalize this work to accommodate a larger number of stages. To derive the operating characteristics of higher-stage hierarchical algorithms with more than one infection, we view the pool decoding process as a time-inhomogeneous, finite-state Markov chain. Taking this conceptualization enables us to derive closed-form expressions for the expected number of tests and classification accuracy rates in terms of transition probability matrices. When applied to chlamydia and gonorrhea testing data from four states (Region X of the United States Department of Health and Human Services), higher-stage hierarchical algorithms provide, on average, an estimated 11% reduction in the number of tests when compared to two-stage algorithms. For applications with rarer infections, we show theoretically that this percentage reduction can be much larger.

KW - Case identification

KW - Markov chain

KW - Pooled testing

KW - Screening

KW - Sensitivity

KW - Specificity

UR - http://www.scopus.com/inward/record.url?scp=85020799053&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020799053&partnerID=8YFLogxK

U2 - 10.1111/biom.12589

DO - 10.1111/biom.12589

M3 - Article

VL - 73

SP - 656

EP - 665

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 2

ER -