Accounting for misclassification bias of binary outcomes due to underscreening: A sensitivity analysis

Nanhua Zhang*, Si Cheng, Lilliam Ambroggio, Todd A. Florin, Maurizio Macaluso

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

Background: Diagnostic tests are performed in a subset of the population who are at higher risk, resulting in undiagnosed cases among those who do not receive the test. This poses a challenge for estimating the prevalence of the disease in the study population, and also for studying the risk factors for the disease. Methods: We formulate this problem as a missing data problem because the disease status is unknown for those who do not receive the test. We propose a Bayesian selection model which models the joint distribution of the disease outcome and whether testing was received. The sensitivity analysis allows us to assess how the association of the risk factors with the disease outcome as well as the disease prevalence change with the sensitivity parameter. Results: We illustrated our model using a retrospective cohort study of children with asthma exacerbation that were evaluated for pneumonia in the emergency department. Our model found that female gender, having fever during ED or at triage, and having severe hypoxia are significantly associated with having radiographic pneumonia. In addition, simulation studies demonstrate that the Bayesian selection model works well even under circumstances when both the disease prevalence and the screening proportion is low. Conclusion: The Bayesian selection model is a viable tool to consider for estimating the disease prevalence and in studying risk factors of the disease, when only a subset of the target population receive the test.

Original languageEnglish (US)
Article number168
JournalBMC Medical Research Methodology
Volume17
Issue number1
DOIs
StatePublished - Dec 12 2017

Fingerprint

Pneumonia
Joint Diseases
Triage
Health Services Needs and Demand
Routine Diagnostic Tests
Population
Hospital Emergency Service
Cohort Studies
Fever
Asthma
Retrospective Studies
Hypoxia

Keywords

  • Misclassification
  • Radiographic pneumonia
  • Selection model
  • Underscreening

ASJC Scopus subject areas

  • Epidemiology
  • Health Informatics

Cite this

@article{cbe452116d3c4fe3b9d2ce0d5627bfc3,
title = "Accounting for misclassification bias of binary outcomes due to underscreening: A sensitivity analysis",
abstract = "Background: Diagnostic tests are performed in a subset of the population who are at higher risk, resulting in undiagnosed cases among those who do not receive the test. This poses a challenge for estimating the prevalence of the disease in the study population, and also for studying the risk factors for the disease. Methods: We formulate this problem as a missing data problem because the disease status is unknown for those who do not receive the test. We propose a Bayesian selection model which models the joint distribution of the disease outcome and whether testing was received. The sensitivity analysis allows us to assess how the association of the risk factors with the disease outcome as well as the disease prevalence change with the sensitivity parameter. Results: We illustrated our model using a retrospective cohort study of children with asthma exacerbation that were evaluated for pneumonia in the emergency department. Our model found that female gender, having fever during ED or at triage, and having severe hypoxia are significantly associated with having radiographic pneumonia. In addition, simulation studies demonstrate that the Bayesian selection model works well even under circumstances when both the disease prevalence and the screening proportion is low. Conclusion: The Bayesian selection model is a viable tool to consider for estimating the disease prevalence and in studying risk factors of the disease, when only a subset of the target population receive the test.",
keywords = "Misclassification, Radiographic pneumonia, Selection model, Underscreening",
author = "Nanhua Zhang and Si Cheng and Lilliam Ambroggio and Florin, {Todd A.} and Maurizio Macaluso",
year = "2017",
month = "12",
day = "12",
doi = "10.1186/s12874-017-0447-9",
language = "English (US)",
volume = "17",
journal = "BMC Medical Research Methodology",
issn = "1471-2288",
publisher = "BioMed Central",
number = "1",

}

Accounting for misclassification bias of binary outcomes due to underscreening : A sensitivity analysis. / Zhang, Nanhua; Cheng, Si; Ambroggio, Lilliam; Florin, Todd A.; Macaluso, Maurizio.

In: BMC Medical Research Methodology, Vol. 17, No. 1, 168, 12.12.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Accounting for misclassification bias of binary outcomes due to underscreening

T2 - A sensitivity analysis

AU - Zhang, Nanhua

AU - Cheng, Si

AU - Ambroggio, Lilliam

AU - Florin, Todd A.

AU - Macaluso, Maurizio

PY - 2017/12/12

Y1 - 2017/12/12

N2 - Background: Diagnostic tests are performed in a subset of the population who are at higher risk, resulting in undiagnosed cases among those who do not receive the test. This poses a challenge for estimating the prevalence of the disease in the study population, and also for studying the risk factors for the disease. Methods: We formulate this problem as a missing data problem because the disease status is unknown for those who do not receive the test. We propose a Bayesian selection model which models the joint distribution of the disease outcome and whether testing was received. The sensitivity analysis allows us to assess how the association of the risk factors with the disease outcome as well as the disease prevalence change with the sensitivity parameter. Results: We illustrated our model using a retrospective cohort study of children with asthma exacerbation that were evaluated for pneumonia in the emergency department. Our model found that female gender, having fever during ED or at triage, and having severe hypoxia are significantly associated with having radiographic pneumonia. In addition, simulation studies demonstrate that the Bayesian selection model works well even under circumstances when both the disease prevalence and the screening proportion is low. Conclusion: The Bayesian selection model is a viable tool to consider for estimating the disease prevalence and in studying risk factors of the disease, when only a subset of the target population receive the test.

AB - Background: Diagnostic tests are performed in a subset of the population who are at higher risk, resulting in undiagnosed cases among those who do not receive the test. This poses a challenge for estimating the prevalence of the disease in the study population, and also for studying the risk factors for the disease. Methods: We formulate this problem as a missing data problem because the disease status is unknown for those who do not receive the test. We propose a Bayesian selection model which models the joint distribution of the disease outcome and whether testing was received. The sensitivity analysis allows us to assess how the association of the risk factors with the disease outcome as well as the disease prevalence change with the sensitivity parameter. Results: We illustrated our model using a retrospective cohort study of children with asthma exacerbation that were evaluated for pneumonia in the emergency department. Our model found that female gender, having fever during ED or at triage, and having severe hypoxia are significantly associated with having radiographic pneumonia. In addition, simulation studies demonstrate that the Bayesian selection model works well even under circumstances when both the disease prevalence and the screening proportion is low. Conclusion: The Bayesian selection model is a viable tool to consider for estimating the disease prevalence and in studying risk factors of the disease, when only a subset of the target population receive the test.

KW - Misclassification

KW - Radiographic pneumonia

KW - Selection model

KW - Underscreening

UR - http://www.scopus.com/inward/record.url?scp=85037854785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85037854785&partnerID=8YFLogxK

U2 - 10.1186/s12874-017-0447-9

DO - 10.1186/s12874-017-0447-9

M3 - Article

C2 - 29233110

AN - SCOPUS:85037854785

VL - 17

JO - BMC Medical Research Methodology

JF - BMC Medical Research Methodology

SN - 1471-2288

IS - 1

M1 - 168

ER -