Avenues for further research

Yulun Liu, Yong Chen

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

In this chapter, we present an overview of the recent statistical methods for diagnostic meta-analysis and suggest a few directions for future research. We discuss two important issues regarding (a) the robustness of model misspecifications and (b) the identifiability of models and the assumption of conditional independence in the absence of a gold standard. With increasing availability of biomedical data, the individual patient-level data meta-analyses offer new insights into evidence synthesis compared to traditional aggregated data-based meta-analyses. In particular, the approaches to combine individual patient-level data with aggregated data can inform personalized medical decision based on patient-level characteristics and help to identify clinically relevant subgroups. However, such integration methods for diagnostic prediction research are limited, and hence there is a growing need for developing of novel statistical methods that can address potential issues including model validation, missing predictors, and between-studies heterogeneity while combining both types of data. Despite the perceived advantages of individual patient-level data, using individual patient-level data alone may still encounter a number of challenges, such as partial verification bias and the absence of a gold standard. We discuss these challenges by two examples.

Original languageEnglish (US)
Title of host publicationDiagnostic Meta-Analysis
Subtitle of host publicationA Useful Tool for Clinical Decision-Making
PublisherSpringer International Publishing
Pages305-315
Number of pages11
ISBN (Electronic)9783319789668
ISBN (Print)9783319789651
DOIs
StatePublished - Jan 1 2018
Externally publishedYes

Fingerprint

Statistical methods
Meta-Analysis
Research
gold
Metadata
statistical analysis
Availability
model validation
meta-analysis
diagnostic techniques
synthesis
prediction
Direction compound

Keywords

  • Absence of gold standard
  • Composite likelihood
  • Diagnostic test
  • Generalized linear mixed model
  • Hierarchical model
  • Imperfect reference test
  • Individual patient-level data
  • Meta-analysis
  • Partial verification bias

ASJC Scopus subject areas

  • Medicine(all)
  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Psychology(all)

Cite this

Liu, Y., & Chen, Y. (2018). Avenues for further research. In Diagnostic Meta-Analysis: A Useful Tool for Clinical Decision-Making (pp. 305-315). Springer International Publishing. https://doi.org/10.1007/978-3-319-78966-8_20

Avenues for further research. / Liu, Yulun; Chen, Yong.

Diagnostic Meta-Analysis: A Useful Tool for Clinical Decision-Making. Springer International Publishing, 2018. p. 305-315.

Research output: Chapter in Book/Report/Conference proceedingChapter

Liu, Y & Chen, Y 2018, Avenues for further research. in Diagnostic Meta-Analysis: A Useful Tool for Clinical Decision-Making. Springer International Publishing, pp. 305-315. https://doi.org/10.1007/978-3-319-78966-8_20
Liu Y, Chen Y. Avenues for further research. In Diagnostic Meta-Analysis: A Useful Tool for Clinical Decision-Making. Springer International Publishing. 2018. p. 305-315 https://doi.org/10.1007/978-3-319-78966-8_20
Liu, Yulun ; Chen, Yong. / Avenues for further research. Diagnostic Meta-Analysis: A Useful Tool for Clinical Decision-Making. Springer International Publishing, 2018. pp. 305-315
@inbook{dd01052de5984ee8bff0633fb54394ba,
title = "Avenues for further research",
abstract = "In this chapter, we present an overview of the recent statistical methods for diagnostic meta-analysis and suggest a few directions for future research. We discuss two important issues regarding (a) the robustness of model misspecifications and (b) the identifiability of models and the assumption of conditional independence in the absence of a gold standard. With increasing availability of biomedical data, the individual patient-level data meta-analyses offer new insights into evidence synthesis compared to traditional aggregated data-based meta-analyses. In particular, the approaches to combine individual patient-level data with aggregated data can inform personalized medical decision based on patient-level characteristics and help to identify clinically relevant subgroups. However, such integration methods for diagnostic prediction research are limited, and hence there is a growing need for developing of novel statistical methods that can address potential issues including model validation, missing predictors, and between-studies heterogeneity while combining both types of data. Despite the perceived advantages of individual patient-level data, using individual patient-level data alone may still encounter a number of challenges, such as partial verification bias and the absence of a gold standard. We discuss these challenges by two examples.",
keywords = "Absence of gold standard, Composite likelihood, Diagnostic test, Generalized linear mixed model, Hierarchical model, Imperfect reference test, Individual patient-level data, Meta-analysis, Partial verification bias",
author = "Yulun Liu and Yong Chen",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-3-319-78966-8_20",
language = "English (US)",
isbn = "9783319789651",
pages = "305--315",
booktitle = "Diagnostic Meta-Analysis",
publisher = "Springer International Publishing",

}

TY - CHAP

T1 - Avenues for further research

AU - Liu, Yulun

AU - Chen, Yong

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In this chapter, we present an overview of the recent statistical methods for diagnostic meta-analysis and suggest a few directions for future research. We discuss two important issues regarding (a) the robustness of model misspecifications and (b) the identifiability of models and the assumption of conditional independence in the absence of a gold standard. With increasing availability of biomedical data, the individual patient-level data meta-analyses offer new insights into evidence synthesis compared to traditional aggregated data-based meta-analyses. In particular, the approaches to combine individual patient-level data with aggregated data can inform personalized medical decision based on patient-level characteristics and help to identify clinically relevant subgroups. However, such integration methods for diagnostic prediction research are limited, and hence there is a growing need for developing of novel statistical methods that can address potential issues including model validation, missing predictors, and between-studies heterogeneity while combining both types of data. Despite the perceived advantages of individual patient-level data, using individual patient-level data alone may still encounter a number of challenges, such as partial verification bias and the absence of a gold standard. We discuss these challenges by two examples.

AB - In this chapter, we present an overview of the recent statistical methods for diagnostic meta-analysis and suggest a few directions for future research. We discuss two important issues regarding (a) the robustness of model misspecifications and (b) the identifiability of models and the assumption of conditional independence in the absence of a gold standard. With increasing availability of biomedical data, the individual patient-level data meta-analyses offer new insights into evidence synthesis compared to traditional aggregated data-based meta-analyses. In particular, the approaches to combine individual patient-level data with aggregated data can inform personalized medical decision based on patient-level characteristics and help to identify clinically relevant subgroups. However, such integration methods for diagnostic prediction research are limited, and hence there is a growing need for developing of novel statistical methods that can address potential issues including model validation, missing predictors, and between-studies heterogeneity while combining both types of data. Despite the perceived advantages of individual patient-level data, using individual patient-level data alone may still encounter a number of challenges, such as partial verification bias and the absence of a gold standard. We discuss these challenges by two examples.

KW - Absence of gold standard

KW - Composite likelihood

KW - Diagnostic test

KW - Generalized linear mixed model

KW - Hierarchical model

KW - Imperfect reference test

KW - Individual patient-level data

KW - Meta-analysis

KW - Partial verification bias

UR - http://www.scopus.com/inward/record.url?scp=85063537337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063537337&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-78966-8_20

DO - 10.1007/978-3-319-78966-8_20

M3 - Chapter

AN - SCOPUS:85063537337

SN - 9783319789651

SP - 305

EP - 315

BT - Diagnostic Meta-Analysis

PB - Springer International Publishing

ER -