Recommendations for research design and reporting in computer-assisted diagnosis to facilitate meta-analysis

Leila H. Eadie, Paul Taylor, Adam P. Gibson

Research output: Contribution to journalLiterature review

6 Citations (Scopus)

Abstract

Computer-assisted diagnosis (CAD) describes a diverse, heterogeneous range of applications rather than a single entity. The aims and functions of CAD systems vary considerably and comparing studies and systems is challenging due to methodological and design differences. In addition, poor study quality and reporting can reduce the value of some publications. Meta-analyses of CAD are therefore difficult and may not provide reliable conclusions. Aiming to determine the major sources of heterogeneity and thereby what CAD researchers could change to allow this sort of assessment, this study reviews a sample of 147 papers concerning CAD used with imaging for cancer diagnosis. It discusses sources of variability, including the goal of the CAD system, learning methodology, study population, design, outcome measures, inclusion of radiologists, and study quality. Based upon this evidence, recommendations are made to help researchers optimize the quality and comparability of their trial design and reporting. (C) 2011 Elsevier Inc. All rights reserved.

Original languageEnglish
Pages (from-to)390-397
Number of pages8
JournalJournal of Biomedical Informatics
Volume45
Issue number2
DOIs
Publication statusPublished - Apr 2012

Keywords

  • computer-assisted diagnosis
  • radiological imaging
  • trial design
  • methodology
  • standardization
  • reporting

Cite this

Recommendations for research design and reporting in computer-assisted diagnosis to facilitate meta-analysis. / Eadie, Leila H.; Taylor, Paul; Gibson, Adam P.

In: Journal of Biomedical Informatics, Vol. 45, No. 2, 04.2012, p. 390-397.

Research output: Contribution to journalLiterature review

Eadie, Leila H. ; Taylor, Paul ; Gibson, Adam P. / Recommendations for research design and reporting in computer-assisted diagnosis to facilitate meta-analysis. In: Journal of Biomedical Informatics. 2012 ; Vol. 45, No. 2. pp. 390-397.
@article{f810fd917c49493e8e90960364a42533,
title = "Recommendations for research design and reporting in computer-assisted diagnosis to facilitate meta-analysis",
abstract = "Computer-assisted diagnosis (CAD) describes a diverse, heterogeneous range of applications rather than a single entity. The aims and functions of CAD systems vary considerably and comparing studies and systems is challenging due to methodological and design differences. In addition, poor study quality and reporting can reduce the value of some publications. Meta-analyses of CAD are therefore difficult and may not provide reliable conclusions. Aiming to determine the major sources of heterogeneity and thereby what CAD researchers could change to allow this sort of assessment, this study reviews a sample of 147 papers concerning CAD used with imaging for cancer diagnosis. It discusses sources of variability, including the goal of the CAD system, learning methodology, study population, design, outcome measures, inclusion of radiologists, and study quality. Based upon this evidence, recommendations are made to help researchers optimize the quality and comparability of their trial design and reporting. (C) 2011 Elsevier Inc. All rights reserved.",
keywords = "computer-assisted diagnosis, radiological imaging, trial design, methodology, standardization, reporting",
author = "Eadie, {Leila H.} and Paul Taylor and Gibson, {Adam P.}",
year = "2012",
month = "4",
doi = "10.1016/j.jbi.2011.07.009",
language = "English",
volume = "45",
pages = "390--397",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Recommendations for research design and reporting in computer-assisted diagnosis to facilitate meta-analysis

AU - Eadie, Leila H.

AU - Taylor, Paul

AU - Gibson, Adam P.

PY - 2012/4

Y1 - 2012/4

N2 - Computer-assisted diagnosis (CAD) describes a diverse, heterogeneous range of applications rather than a single entity. The aims and functions of CAD systems vary considerably and comparing studies and systems is challenging due to methodological and design differences. In addition, poor study quality and reporting can reduce the value of some publications. Meta-analyses of CAD are therefore difficult and may not provide reliable conclusions. Aiming to determine the major sources of heterogeneity and thereby what CAD researchers could change to allow this sort of assessment, this study reviews a sample of 147 papers concerning CAD used with imaging for cancer diagnosis. It discusses sources of variability, including the goal of the CAD system, learning methodology, study population, design, outcome measures, inclusion of radiologists, and study quality. Based upon this evidence, recommendations are made to help researchers optimize the quality and comparability of their trial design and reporting. (C) 2011 Elsevier Inc. All rights reserved.

AB - Computer-assisted diagnosis (CAD) describes a diverse, heterogeneous range of applications rather than a single entity. The aims and functions of CAD systems vary considerably and comparing studies and systems is challenging due to methodological and design differences. In addition, poor study quality and reporting can reduce the value of some publications. Meta-analyses of CAD are therefore difficult and may not provide reliable conclusions. Aiming to determine the major sources of heterogeneity and thereby what CAD researchers could change to allow this sort of assessment, this study reviews a sample of 147 papers concerning CAD used with imaging for cancer diagnosis. It discusses sources of variability, including the goal of the CAD system, learning methodology, study population, design, outcome measures, inclusion of radiologists, and study quality. Based upon this evidence, recommendations are made to help researchers optimize the quality and comparability of their trial design and reporting. (C) 2011 Elsevier Inc. All rights reserved.

KW - computer-assisted diagnosis

KW - radiological imaging

KW - trial design

KW - methodology

KW - standardization

KW - reporting

U2 - 10.1016/j.jbi.2011.07.009

DO - 10.1016/j.jbi.2011.07.009

M3 - Literature review

VL - 45

SP - 390

EP - 397

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

IS - 2

ER -