Accuracy of radiologists and radiology residents in detection of paediatric appendicular fractures with and without artificial intelligence

Objectives We aim to evaluate the accuracy of radiologists and radiology residents in the detection of paediatric appendicular fractures with and without the help of a commercially available fracture detection artificial intelligence (AI) solution in the hopes of showing potential clinical benefits...

Full description

Saved in:
Bibliographic Details
Main Authors: Timothy Shao Ern Tan, Praveen M Yogendra, Adriel Guang Wei Goh, Sze Ying Yee, Freda Jawan, Kelvin Kay Nguan Koh, Tian Kai Woon, Phey Ming Yeap, Min On Tan
Format: Article
Language:English
Published: BMJ Publishing Group 2024-12-01
Series:BMJ Health & Care Informatics
Online Access:https://informatics.bmj.com/content/31/1/e101091.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255070696833024
author Timothy Shao Ern Tan
Praveen M Yogendra
Adriel Guang Wei Goh
Sze Ying Yee
Freda Jawan
Kelvin Kay Nguan Koh
Tian Kai Woon
Phey Ming Yeap
Min On Tan
author_facet Timothy Shao Ern Tan
Praveen M Yogendra
Adriel Guang Wei Goh
Sze Ying Yee
Freda Jawan
Kelvin Kay Nguan Koh
Tian Kai Woon
Phey Ming Yeap
Min On Tan
author_sort Timothy Shao Ern Tan
collection DOAJ
description Objectives We aim to evaluate the accuracy of radiologists and radiology residents in the detection of paediatric appendicular fractures with and without the help of a commercially available fracture detection artificial intelligence (AI) solution in the hopes of showing potential clinical benefits in a general hospital setting.Methods This was a retrospective study involving three associate consultants (AC) and three senior residents (SR) in radiology, who acted as readers. One reader from each human group interpreted the radiographs with the aid of AI. Cases were categorised into concordant and discordant cases between each interpreting group. Discordant cases were further evaluated by three independent subspecialty radiology consultants to determine the final diagnosis. A total of 500 anonymised paediatric patient cases (aged 2–15 years) who presented to a tertiary general hospital with a Children’s emergency were retrospectively collected. Main outcome measures include the presence of fracture, accuracy of readers with and without AI, and total time taken to interpret the radiographs.Results The AI solution alone showed the highest accuracy (area under the receiver operating characteristic curve 0.97; AC: 95% CI −0.055 to 0.320, p=0; SR: 95% CI 0.244 to 0.598, p=0). The two readers aided with AI had higher area under curves compared with readers without AI support (AC: 95% CI −0.303 to 0.465, p=0; SR: 95% CI −0.154 to 0.331, p=0). These differences were statistically significant.Conclusion Our study demonstrates excellent results in the detection of paediatric appendicular fractures using a commercially available AI solution. There is potential for the AI solution to function autonomously.
format Article
id doaj-art-d8a48183caa4407bb8aa8b0e2d6607c6
institution OA Journals
issn 2632-1009
language English
publishDate 2024-12-01
publisher BMJ Publishing Group
record_format Article
series BMJ Health & Care Informatics
spelling doaj-art-d8a48183caa4407bb8aa8b0e2d6607c62025-08-20T01:56:57ZengBMJ Publishing GroupBMJ Health & Care Informatics2632-10092024-12-0131110.1136/bmjhci-2024-101091Accuracy of radiologists and radiology residents in detection of paediatric appendicular fractures with and without artificial intelligenceTimothy Shao Ern Tan0Praveen M Yogendra1Adriel Guang Wei Goh2Sze Ying Yee3Freda Jawan4Kelvin Kay Nguan Koh5Tian Kai Woon6Phey Ming Yeap7Min On Tan82 Department of Diagnostic Radiology, Singapore General Hospital, SingaporeDepartment of Radiology, Sengkang General Hospital, Singapore, SingaporeDepartment of Radiology, Sengkang General Hospital, Singapore, SingaporeDepartment of Radiology, Sengkang General Hospital, Singapore, SingaporeDepartment of Radiology, Sengkang General Hospital, Singapore, SingaporeDepartment of Radiology, Sengkang General Hospital, Singapore, SingaporeDepartment of Diagnostic and Interventional Imaging, KK Women’s and Children’s Hospital, Singapore, SingaporeDepartment of Radiology, Sengkang General Hospital, Singapore, SingaporeDepartment of Radiology, Sengkang General Hospital, Singapore, SingaporeObjectives We aim to evaluate the accuracy of radiologists and radiology residents in the detection of paediatric appendicular fractures with and without the help of a commercially available fracture detection artificial intelligence (AI) solution in the hopes of showing potential clinical benefits in a general hospital setting.Methods This was a retrospective study involving three associate consultants (AC) and three senior residents (SR) in radiology, who acted as readers. One reader from each human group interpreted the radiographs with the aid of AI. Cases were categorised into concordant and discordant cases between each interpreting group. Discordant cases were further evaluated by three independent subspecialty radiology consultants to determine the final diagnosis. A total of 500 anonymised paediatric patient cases (aged 2–15 years) who presented to a tertiary general hospital with a Children’s emergency were retrospectively collected. Main outcome measures include the presence of fracture, accuracy of readers with and without AI, and total time taken to interpret the radiographs.Results The AI solution alone showed the highest accuracy (area under the receiver operating characteristic curve 0.97; AC: 95% CI −0.055 to 0.320, p=0; SR: 95% CI 0.244 to 0.598, p=0). The two readers aided with AI had higher area under curves compared with readers without AI support (AC: 95% CI −0.303 to 0.465, p=0; SR: 95% CI −0.154 to 0.331, p=0). These differences were statistically significant.Conclusion Our study demonstrates excellent results in the detection of paediatric appendicular fractures using a commercially available AI solution. There is potential for the AI solution to function autonomously.https://informatics.bmj.com/content/31/1/e101091.full
spellingShingle Timothy Shao Ern Tan
Praveen M Yogendra
Adriel Guang Wei Goh
Sze Ying Yee
Freda Jawan
Kelvin Kay Nguan Koh
Tian Kai Woon
Phey Ming Yeap
Min On Tan
Accuracy of radiologists and radiology residents in detection of paediatric appendicular fractures with and without artificial intelligence
BMJ Health & Care Informatics
title Accuracy of radiologists and radiology residents in detection of paediatric appendicular fractures with and without artificial intelligence
title_full Accuracy of radiologists and radiology residents in detection of paediatric appendicular fractures with and without artificial intelligence
title_fullStr Accuracy of radiologists and radiology residents in detection of paediatric appendicular fractures with and without artificial intelligence
title_full_unstemmed Accuracy of radiologists and radiology residents in detection of paediatric appendicular fractures with and without artificial intelligence
title_short Accuracy of radiologists and radiology residents in detection of paediatric appendicular fractures with and without artificial intelligence
title_sort accuracy of radiologists and radiology residents in detection of paediatric appendicular fractures with and without artificial intelligence
url https://informatics.bmj.com/content/31/1/e101091.full
work_keys_str_mv AT timothyshaoerntan accuracyofradiologistsandradiologyresidentsindetectionofpaediatricappendicularfractureswithandwithoutartificialintelligence
AT praveenmyogendra accuracyofradiologistsandradiologyresidentsindetectionofpaediatricappendicularfractureswithandwithoutartificialintelligence
AT adrielguangweigoh accuracyofradiologistsandradiologyresidentsindetectionofpaediatricappendicularfractureswithandwithoutartificialintelligence
AT szeyingyee accuracyofradiologistsandradiologyresidentsindetectionofpaediatricappendicularfractureswithandwithoutartificialintelligence
AT fredajawan accuracyofradiologistsandradiologyresidentsindetectionofpaediatricappendicularfractureswithandwithoutartificialintelligence
AT kelvinkaynguankoh accuracyofradiologistsandradiologyresidentsindetectionofpaediatricappendicularfractureswithandwithoutartificialintelligence
AT tiankaiwoon accuracyofradiologistsandradiologyresidentsindetectionofpaediatricappendicularfractureswithandwithoutartificialintelligence
AT pheymingyeap accuracyofradiologistsandradiologyresidentsindetectionofpaediatricappendicularfractureswithandwithoutartificialintelligence
AT minontan accuracyofradiologistsandradiologyresidentsindetectionofpaediatricappendicularfractureswithandwithoutartificialintelligence