Clinicians’ Agreement on Extrapulmonary Radiographic Findings in Chest X-Rays Using a Diagnostic Labelling Scheme

<b>Objective:</b> Reliable reading and annotation of chest X-ray (CXR) images are essential for both clinical decision-making and AI model development. While most of the literature emphasizes pulmonary findings, this study evaluates the consistency and reliability of annotations for extr...

Full description

Saved in:
Bibliographic Details
Main Authors: Lea Marie Pehrson, Dana Li, Alyas Mayar, Marco Fraccaro, Rasmus Bonnevie, Peter Jagd Sørensen, Alexander Malcom Rykkje, Tobias Thostrup Andersen, Henrik Steglich-Arnholm, Dorte Marianne Rohde Stærk, Lotte Borgwardt, Sune Darkner, Jonathan Frederik Carlsen, Michael Bachmann Nielsen, Silvia Ingala
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/7/902
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730663874297856
author Lea Marie Pehrson
Dana Li
Alyas Mayar
Marco Fraccaro
Rasmus Bonnevie
Peter Jagd Sørensen
Alexander Malcom Rykkje
Tobias Thostrup Andersen
Henrik Steglich-Arnholm
Dorte Marianne Rohde Stærk
Lotte Borgwardt
Sune Darkner
Jonathan Frederik Carlsen
Michael Bachmann Nielsen
Silvia Ingala
author_facet Lea Marie Pehrson
Dana Li
Alyas Mayar
Marco Fraccaro
Rasmus Bonnevie
Peter Jagd Sørensen
Alexander Malcom Rykkje
Tobias Thostrup Andersen
Henrik Steglich-Arnholm
Dorte Marianne Rohde Stærk
Lotte Borgwardt
Sune Darkner
Jonathan Frederik Carlsen
Michael Bachmann Nielsen
Silvia Ingala
author_sort Lea Marie Pehrson
collection DOAJ
description <b>Objective:</b> Reliable reading and annotation of chest X-ray (CXR) images are essential for both clinical decision-making and AI model development. While most of the literature emphasizes pulmonary findings, this study evaluates the consistency and reliability of annotations for extrapulmonary findings, using a labelling scheme. <b>Methods:</b> Six clinicians with varying experience levels (novice, intermediate, and experienced) annotated 100 CXR images using a diagnostic labelling scheme, in two rounds, separated by a three-week washout period. Annotation consistency was assessed using Randolph’s free-marginal kappa (RK), prevalence- and bias-adjusted kappa (PABAK), proportion positive agreement (PPA), and proportion negative agreement (PNA). Pairwise comparisons and the McNemar’s test were conducted to assess inter-reader and intra-reader agreement. <b>Results:</b> PABAK values indicated high overall grouped labelling agreement (novice: 0.86, intermediate: 0.90, experienced: 0.91). PNA values demonstrated strong agreement on negative findings, while PPA values showed moderate-to-low consistency in positive findings. Significant differences in specific agreement emerged between novice and experienced clinicians for eight labels, but there were no significant variations in RK across experience levels. The McNemar’s test confirmed annotation stability between rounds. <b>Conclusions:</b> This study demonstrates that clinician annotations of extrapulmonary findings in CXR are consistent and reliable across different experience levels using a pre-defined diagnostic labelling scheme. These insights aid in optimizing training strategies for both clinicians and AI models.
format Article
id doaj-art-a2f7fe3c9f07466e8e23c1b6d79ed3b3
institution DOAJ
issn 2075-4418
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-a2f7fe3c9f07466e8e23c1b6d79ed3b32025-08-20T03:08:47ZengMDPI AGDiagnostics2075-44182025-04-0115790210.3390/diagnostics15070902Clinicians’ Agreement on Extrapulmonary Radiographic Findings in Chest X-Rays Using a Diagnostic Labelling SchemeLea Marie Pehrson0Dana Li1Alyas Mayar2Marco Fraccaro3Rasmus Bonnevie4Peter Jagd Sørensen5Alexander Malcom Rykkje6Tobias Thostrup Andersen7Henrik Steglich-Arnholm8Dorte Marianne Rohde Stærk9Lotte Borgwardt10Sune Darkner11Jonathan Frederik Carlsen12Michael Bachmann Nielsen13Silvia Ingala14Department of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkUnumed Aps, 1055 Copenhagen, DenmarkUnumed Aps, 1055 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Computer Science, University of Copenhagen, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, Denmark<b>Objective:</b> Reliable reading and annotation of chest X-ray (CXR) images are essential for both clinical decision-making and AI model development. While most of the literature emphasizes pulmonary findings, this study evaluates the consistency and reliability of annotations for extrapulmonary findings, using a labelling scheme. <b>Methods:</b> Six clinicians with varying experience levels (novice, intermediate, and experienced) annotated 100 CXR images using a diagnostic labelling scheme, in two rounds, separated by a three-week washout period. Annotation consistency was assessed using Randolph’s free-marginal kappa (RK), prevalence- and bias-adjusted kappa (PABAK), proportion positive agreement (PPA), and proportion negative agreement (PNA). Pairwise comparisons and the McNemar’s test were conducted to assess inter-reader and intra-reader agreement. <b>Results:</b> PABAK values indicated high overall grouped labelling agreement (novice: 0.86, intermediate: 0.90, experienced: 0.91). PNA values demonstrated strong agreement on negative findings, while PPA values showed moderate-to-low consistency in positive findings. Significant differences in specific agreement emerged between novice and experienced clinicians for eight labels, but there were no significant variations in RK across experience levels. The McNemar’s test confirmed annotation stability between rounds. <b>Conclusions:</b> This study demonstrates that clinician annotations of extrapulmonary findings in CXR are consistent and reliable across different experience levels using a pre-defined diagnostic labelling scheme. These insights aid in optimizing training strategies for both clinicians and AI models.https://www.mdpi.com/2075-4418/15/7/902annotationextrapulmonary findingsconsistencyartificial intelligence
spellingShingle Lea Marie Pehrson
Dana Li
Alyas Mayar
Marco Fraccaro
Rasmus Bonnevie
Peter Jagd Sørensen
Alexander Malcom Rykkje
Tobias Thostrup Andersen
Henrik Steglich-Arnholm
Dorte Marianne Rohde Stærk
Lotte Borgwardt
Sune Darkner
Jonathan Frederik Carlsen
Michael Bachmann Nielsen
Silvia Ingala
Clinicians’ Agreement on Extrapulmonary Radiographic Findings in Chest X-Rays Using a Diagnostic Labelling Scheme
Diagnostics
annotation
extrapulmonary findings
consistency
artificial intelligence
title Clinicians’ Agreement on Extrapulmonary Radiographic Findings in Chest X-Rays Using a Diagnostic Labelling Scheme
title_full Clinicians’ Agreement on Extrapulmonary Radiographic Findings in Chest X-Rays Using a Diagnostic Labelling Scheme
title_fullStr Clinicians’ Agreement on Extrapulmonary Radiographic Findings in Chest X-Rays Using a Diagnostic Labelling Scheme
title_full_unstemmed Clinicians’ Agreement on Extrapulmonary Radiographic Findings in Chest X-Rays Using a Diagnostic Labelling Scheme
title_short Clinicians’ Agreement on Extrapulmonary Radiographic Findings in Chest X-Rays Using a Diagnostic Labelling Scheme
title_sort clinicians agreement on extrapulmonary radiographic findings in chest x rays using a diagnostic labelling scheme
topic annotation
extrapulmonary findings
consistency
artificial intelligence
url https://www.mdpi.com/2075-4418/15/7/902
work_keys_str_mv AT leamariepehrson cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT danali cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT alyasmayar cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT marcofraccaro cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT rasmusbonnevie cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT peterjagdsørensen cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT alexandermalcomrykkje cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT tobiasthostrupandersen cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT henriksteglicharnholm cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT dortemariannerohdestærk cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT lotteborgwardt cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT sunedarkner cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT jonathanfrederikcarlsen cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT michaelbachmannnielsen cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme
AT silviaingala cliniciansagreementonextrapulmonaryradiographicfindingsinchestxraysusingadiagnosticlabellingscheme