A hybrid model for combining case-control and cohort studies in systematic reviews of diagnostic tests

Yong Chen, Yulun Liu, Jing Ning, Janice Cormier, Haitao Chu

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Systematic reviews of diagnostic tests often involve a mixture of case-control and cohort studies. The standard methods for evaluating diagnostic accuracy focus only on sensitivity and specificity and ignore the information on disease prevalence that is contained in cohort studies. Consequently, such methods cannot provide estimates of measures related to disease prevalence, such as population-averaged or overall positive and negative predictive values, which reflect the clinical utility of a diagnostic test. We propose a hybrid approach that jointly models the disease prevalence along with diagnostic test sensitivity and specificity in cohort studies, and sensitivity and specificity in case-control studies. To overcome the potential computational difficulties in the standard full likelihood inference of the hybrid model proposed, we propose an alternative inference procedure based on composite likelihood. Such composite-likelihood-based inference does not suffer computational problems and maintains high relative efficiency. In addition, it is more robust to model misspecifications compared with standard full likelihood inference. We apply our approach to a review of the performance of contemporary diagnostic imaging modalities for detecting metastases in patients with melanoma.

Original languageEnglish (US)
Pages (from-to)469-489
Number of pages21
JournalJournal of the Royal Statistical Society. Series C: Applied Statistics
Volume64
Issue number3
DOIs
StatePublished - Apr 1 2015
Externally publishedYes

Fingerprint

Cohort Study
Diagnostic Tests
Case-control Study
Hybrid Model
Composite Likelihood
Specificity
Likelihood Inference
Diagnostic Accuracy
Melanoma
Model Misspecification
Metastasis
Relative Efficiency
Hybrid Approach
Modality
High Efficiency
Diagnostics
Imaging
Alternatives
Estimate
Review

Keywords

  • Composite likelihood
  • Diagnostic accuracy study
  • Independence likelihood
  • Multivariate meta-analysis
  • Prevalence

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

A hybrid model for combining case-control and cohort studies in systematic reviews of diagnostic tests. / Chen, Yong; Liu, Yulun; Ning, Jing; Cormier, Janice; Chu, Haitao.

In: Journal of the Royal Statistical Society. Series C: Applied Statistics, Vol. 64, No. 3, 01.04.2015, p. 469-489.

Research output: Contribution to journalArticle

@article{cd59b4e8ffcf4cf9833d4c8173901207,
title = "A hybrid model for combining case-control and cohort studies in systematic reviews of diagnostic tests",
abstract = "Systematic reviews of diagnostic tests often involve a mixture of case-control and cohort studies. The standard methods for evaluating diagnostic accuracy focus only on sensitivity and specificity and ignore the information on disease prevalence that is contained in cohort studies. Consequently, such methods cannot provide estimates of measures related to disease prevalence, such as population-averaged or overall positive and negative predictive values, which reflect the clinical utility of a diagnostic test. We propose a hybrid approach that jointly models the disease prevalence along with diagnostic test sensitivity and specificity in cohort studies, and sensitivity and specificity in case-control studies. To overcome the potential computational difficulties in the standard full likelihood inference of the hybrid model proposed, we propose an alternative inference procedure based on composite likelihood. Such composite-likelihood-based inference does not suffer computational problems and maintains high relative efficiency. In addition, it is more robust to model misspecifications compared with standard full likelihood inference. We apply our approach to a review of the performance of contemporary diagnostic imaging modalities for detecting metastases in patients with melanoma.",
keywords = "Composite likelihood, Diagnostic accuracy study, Independence likelihood, Multivariate meta-analysis, Prevalence",
author = "Yong Chen and Yulun Liu and Jing Ning and Janice Cormier and Haitao Chu",
year = "2015",
month = "4",
day = "1",
doi = "10.1111/rssc.12087",
language = "English (US)",
volume = "64",
pages = "469--489",
journal = "Journal of the Royal Statistical Society. Series C: Applied Statistics",
issn = "0035-9254",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - A hybrid model for combining case-control and cohort studies in systematic reviews of diagnostic tests

AU - Chen, Yong

AU - Liu, Yulun

AU - Ning, Jing

AU - Cormier, Janice

AU - Chu, Haitao

PY - 2015/4/1

Y1 - 2015/4/1

N2 - Systematic reviews of diagnostic tests often involve a mixture of case-control and cohort studies. The standard methods for evaluating diagnostic accuracy focus only on sensitivity and specificity and ignore the information on disease prevalence that is contained in cohort studies. Consequently, such methods cannot provide estimates of measures related to disease prevalence, such as population-averaged or overall positive and negative predictive values, which reflect the clinical utility of a diagnostic test. We propose a hybrid approach that jointly models the disease prevalence along with diagnostic test sensitivity and specificity in cohort studies, and sensitivity and specificity in case-control studies. To overcome the potential computational difficulties in the standard full likelihood inference of the hybrid model proposed, we propose an alternative inference procedure based on composite likelihood. Such composite-likelihood-based inference does not suffer computational problems and maintains high relative efficiency. In addition, it is more robust to model misspecifications compared with standard full likelihood inference. We apply our approach to a review of the performance of contemporary diagnostic imaging modalities for detecting metastases in patients with melanoma.

AB - Systematic reviews of diagnostic tests often involve a mixture of case-control and cohort studies. The standard methods for evaluating diagnostic accuracy focus only on sensitivity and specificity and ignore the information on disease prevalence that is contained in cohort studies. Consequently, such methods cannot provide estimates of measures related to disease prevalence, such as population-averaged or overall positive and negative predictive values, which reflect the clinical utility of a diagnostic test. We propose a hybrid approach that jointly models the disease prevalence along with diagnostic test sensitivity and specificity in cohort studies, and sensitivity and specificity in case-control studies. To overcome the potential computational difficulties in the standard full likelihood inference of the hybrid model proposed, we propose an alternative inference procedure based on composite likelihood. Such composite-likelihood-based inference does not suffer computational problems and maintains high relative efficiency. In addition, it is more robust to model misspecifications compared with standard full likelihood inference. We apply our approach to a review of the performance of contemporary diagnostic imaging modalities for detecting metastases in patients with melanoma.

KW - Composite likelihood

KW - Diagnostic accuracy study

KW - Independence likelihood

KW - Multivariate meta-analysis

KW - Prevalence

UR - http://www.scopus.com/inward/record.url?scp=84924333316&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924333316&partnerID=8YFLogxK

U2 - 10.1111/rssc.12087

DO - 10.1111/rssc.12087

M3 - Article

C2 - 25897179

AN - SCOPUS:84924333316

VL - 64

SP - 469

EP - 489

JO - Journal of the Royal Statistical Society. Series C: Applied Statistics

JF - Journal of the Royal Statistical Society. Series C: Applied Statistics

SN - 0035-9254

IS - 3

ER -