A Bayesian Hierarchical Summary Receiver Operating Characteristic Model for Network Meta-Analysis of Diagnostic Tests

Qinshu Lian; James S Hodges; Haitao Chu

doi:10.1080/01621459.2018.1476239

A Bayesian Hierarchical Summary Receiver Operating Characteristic Model for Network Meta-Analysis of Diagnostic Tests

Qinshu Lian, James S Hodges, Haitao Chu

Biostatistics

Research output: Contribution to journal › Article › peer-review

9 Scopus citations

Abstract

In studies evaluating the accuracy of diagnostic tests, three designs are commonly used, crossover, randomized, and non-comparative. Existing methods for meta-analysis of diagnostic tests mainly consider the simple cases in which the reference test in all or none of the studies can be considered a gold standard test, and in which all studies use either a randomized or non-comparative design. The proliferation of diagnostic instruments and the diversity of study designs create a need for more general methods to combine studies that include or do not include a gold standard test and that use various designs. This paper extends the Bayesian hierarchical summary receiver operating characteristic model to network meta-analysis of diagnostic tests to simultaneously compare multiple tests within a missing data framework. The method accounts for correlations between multiple tests and for heterogeneity between studies. It also allows different studies to include different subsets of diagnostic tests and provides flexibility in the choice of summary statistics. The model is evaluated using simulations and illustrated using real data on tests for deep vein thrombosis, with sensitivity analyses.

Original language	English (US)
Pages (from-to)	949-961
Number of pages	13
Journal	Journal of the American Statistical Association
Volume	114
Issue number	527
DOIs	https://doi.org/10.1080/01621459.2018.1476239
State	Published - Jul 3 2019

Bibliographical note

Funding Information:
Research reported in this publication was supported in part by NIDCR R03 DE024750 (H.C.), NLM R21 LM012197 (H.C.), NLM R21 LM012744 (H.C., J.H.), NIDDK U01 DK106786 (H.C.), AHRQ R03HS024743 (H.C.), and NHLBI T32HL129956 (Q.L). The content is solely the responsibility of the authors and does not necessarily represent official views of the National Institutes of Health. The authors thank the editor Professor Joseph G. Ibrahim, an associate editor, and two anonymous reviewers for many constructive comments. Conflict of Interest: None declared.

Publisher Copyright:
© 2018, © 2018 American Statistical Association.

Keywords

Bayesian hierarchical model
Diagnostic tests
Missing data
Multiple tests comparison
Network meta-analysis

Publisher link

10.1080/01621459.2018.1476239

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6880940

Find It

Find It at U of M Libraries

Cite this

@article{964cb836178e4b5190e58664fb239c8d,

title = "A Bayesian Hierarchical Summary Receiver Operating Characteristic Model for Network Meta-Analysis of Diagnostic Tests",

abstract = "In studies evaluating the accuracy of diagnostic tests, three designs are commonly used, crossover, randomized, and non-comparative. Existing methods for meta-analysis of diagnostic tests mainly consider the simple cases in which the reference test in all or none of the studies can be considered a gold standard test, and in which all studies use either a randomized or non-comparative design. The proliferation of diagnostic instruments and the diversity of study designs create a need for more general methods to combine studies that include or do not include a gold standard test and that use various designs. This paper extends the Bayesian hierarchical summary receiver operating characteristic model to network meta-analysis of diagnostic tests to simultaneously compare multiple tests within a missing data framework. The method accounts for correlations between multiple tests and for heterogeneity between studies. It also allows different studies to include different subsets of diagnostic tests and provides flexibility in the choice of summary statistics. The model is evaluated using simulations and illustrated using real data on tests for deep vein thrombosis, with sensitivity analyses.",

keywords = "Bayesian hierarchical model, Diagnostic tests, Missing data, Multiple tests comparison, Network meta-analysis",

author = "Qinshu Lian and Hodges, {James S} and Haitao Chu",

note = "Funding Information: Research reported in this publication was supported in part by NIDCR R03 DE024750 (H.C.), NLM R21 LM012197 (H.C.), NLM R21 LM012744 (H.C., J.H.), NIDDK U01 DK106786 (H.C.), AHRQ R03HS024743 (H.C.), and NHLBI T32HL129956 (Q.L). The content is solely the responsibility of the authors and does not necessarily represent official views of the National Institutes of Health. The authors thank the editor Professor Joseph G. Ibrahim, an associate editor, and two anonymous reviewers for many constructive comments. Conflict of Interest: None declared. Publisher Copyright: {\textcopyright} 2018, {\textcopyright} 2018 American Statistical Association.",

year = "2019",

month = jul,

day = "3",

doi = "10.1080/01621459.2018.1476239",

language = "English (US)",

volume = "114",

pages = "949--961",

journal = "Journal of the American Statistical Association",

issn = "0162-1459",

publisher = "Taylor and Francis Ltd.",

number = "527",

}

TY - JOUR

T1 - A Bayesian Hierarchical Summary Receiver Operating Characteristic Model for Network Meta-Analysis of Diagnostic Tests

AU - Lian, Qinshu

AU - Hodges, James S

AU - Chu, Haitao

N1 - Funding Information: Research reported in this publication was supported in part by NIDCR R03 DE024750 (H.C.), NLM R21 LM012197 (H.C.), NLM R21 LM012744 (H.C., J.H.), NIDDK U01 DK106786 (H.C.), AHRQ R03HS024743 (H.C.), and NHLBI T32HL129956 (Q.L). The content is solely the responsibility of the authors and does not necessarily represent official views of the National Institutes of Health. The authors thank the editor Professor Joseph G. Ibrahim, an associate editor, and two anonymous reviewers for many constructive comments. Conflict of Interest: None declared. Publisher Copyright: © 2018, © 2018 American Statistical Association.

PY - 2019/7/3

Y1 - 2019/7/3

N2 - In studies evaluating the accuracy of diagnostic tests, three designs are commonly used, crossover, randomized, and non-comparative. Existing methods for meta-analysis of diagnostic tests mainly consider the simple cases in which the reference test in all or none of the studies can be considered a gold standard test, and in which all studies use either a randomized or non-comparative design. The proliferation of diagnostic instruments and the diversity of study designs create a need for more general methods to combine studies that include or do not include a gold standard test and that use various designs. This paper extends the Bayesian hierarchical summary receiver operating characteristic model to network meta-analysis of diagnostic tests to simultaneously compare multiple tests within a missing data framework. The method accounts for correlations between multiple tests and for heterogeneity between studies. It also allows different studies to include different subsets of diagnostic tests and provides flexibility in the choice of summary statistics. The model is evaluated using simulations and illustrated using real data on tests for deep vein thrombosis, with sensitivity analyses.

AB - In studies evaluating the accuracy of diagnostic tests, three designs are commonly used, crossover, randomized, and non-comparative. Existing methods for meta-analysis of diagnostic tests mainly consider the simple cases in which the reference test in all or none of the studies can be considered a gold standard test, and in which all studies use either a randomized or non-comparative design. The proliferation of diagnostic instruments and the diversity of study designs create a need for more general methods to combine studies that include or do not include a gold standard test and that use various designs. This paper extends the Bayesian hierarchical summary receiver operating characteristic model to network meta-analysis of diagnostic tests to simultaneously compare multiple tests within a missing data framework. The method accounts for correlations between multiple tests and for heterogeneity between studies. It also allows different studies to include different subsets of diagnostic tests and provides flexibility in the choice of summary statistics. The model is evaluated using simulations and illustrated using real data on tests for deep vein thrombosis, with sensitivity analyses.

KW - Bayesian hierarchical model

KW - Diagnostic tests

KW - Missing data

KW - Multiple tests comparison

KW - Network meta-analysis

UR - http://www.scopus.com/inward/record.url?scp=85052080661&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052080661&partnerID=8YFLogxK

U2 - 10.1080/01621459.2018.1476239

DO - 10.1080/01621459.2018.1476239

M3 - Article

C2 - 31777410

AN - SCOPUS:85052080661

SN - 0162-1459

VL - 114

SP - 949

EP - 961

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

IS - 527

ER -

A Bayesian Hierarchical Summary Receiver Operating Characteristic Model for Network Meta-Analysis of Diagnostic Tests

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this