The diagnostic accuracy of artificial intelligence and computer-aided diagnosis for the detection and characterisation of colorectal polyps: A systematic review and meta-analysis.
File(s)
Published version
Author(s)
Nazarian, Scarlet
Glover, Ben
Ashrafian, Hutan
Darzi, Ara
Teare, Julian
Type
Journal Article
Abstract
Aims
Colonoscopy reduces the incidence of colorectal cancer by allowing detection and resection of neoplastic polyps. Evidence shows that many small polyps are missed on a single colonoscopy. There has been a successful adoption of AI technologies to tackle the issues around missed polyps and as a tool to increase adenoma detection rate (ADR). The aim of this review was to examine the diagnostic accuracy of AI-based technologies in assessing colorectal polyps.
Method
A comprehensive literature search was undertaken using the databases of EMBASE, Medline and the Cochrane Library. PRISMA guidelines were followed. Studies reporting use of computer-aided diagnosis for polyp detection or characterisation during colonoscopy were included. Independent proportion and their differences were calculated and pooled through DerSimonian and Laird random-effects modelling.
Results
A total of 48 studies were included. The meta-analysis showed a significant increase in pooled PDR in patients with the use of AI for polyp detection during colonoscopy compared with patients who had standard colonoscopy (OR 1.75; 95% CI 1.56-1.96; p= 0.0005). When comparing patients undergoing colonoscopy with the use of AI to those without, there was also a significant increase in ADR (OR 1.53; 95% CI 1.32-1.77; p= 0005).
Conclusion
With the aid of machine learning, there is potential to improve ADR and consequently reduce the incidence of CRC. The current generation of AI-based systems demonstrate impressive accuracy for the detection and characterisation of colorectal polyps. However, this is an evolving field and before its adoption into a clinical setting, AI systems must prove worthy to patients and clinicians.
Colonoscopy reduces the incidence of colorectal cancer by allowing detection and resection of neoplastic polyps. Evidence shows that many small polyps are missed on a single colonoscopy. There has been a successful adoption of AI technologies to tackle the issues around missed polyps and as a tool to increase adenoma detection rate (ADR). The aim of this review was to examine the diagnostic accuracy of AI-based technologies in assessing colorectal polyps.
Method
A comprehensive literature search was undertaken using the databases of EMBASE, Medline and the Cochrane Library. PRISMA guidelines were followed. Studies reporting use of computer-aided diagnosis for polyp detection or characterisation during colonoscopy were included. Independent proportion and their differences were calculated and pooled through DerSimonian and Laird random-effects modelling.
Results
A total of 48 studies were included. The meta-analysis showed a significant increase in pooled PDR in patients with the use of AI for polyp detection during colonoscopy compared with patients who had standard colonoscopy (OR 1.75; 95% CI 1.56-1.96; p= 0.0005). When comparing patients undergoing colonoscopy with the use of AI to those without, there was also a significant increase in ADR (OR 1.53; 95% CI 1.32-1.77; p= 0005).
Conclusion
With the aid of machine learning, there is potential to improve ADR and consequently reduce the incidence of CRC. The current generation of AI-based systems demonstrate impressive accuracy for the detection and characterisation of colorectal polyps. However, this is an evolving field and before its adoption into a clinical setting, AI systems must prove worthy to patients and clinicians.
Date Issued
2021-07-14
Date Acceptance
2021-05-06
Citation
Journal of Medical Internet Research, 2021, 23 (7), pp.1-18
ISSN
1438-8871
Publisher
JMIR Publications
Start Page
1
End Page
18
Journal / Book Title
Journal of Medical Internet Research
Volume
23
Issue
7
Copyright Statement
© Scarlet Nazarian, Ben Glover, Hutan Ashrafian, Ara Darzi, Julian Teare. Originally published in the Journal of Medical Internet
Research (https://www.jmir.org), 14.07.2021. This is an open-access article distributed under the terms of the Creative Commons
Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction
in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The
complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and
license information must be included.
Research (https://www.jmir.org), 14.07.2021. This is an open-access article distributed under the terms of the Creative Commons
Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction
in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The
complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and
license information must be included.
License URL
Identifier
https://www.jmir.org/2021/7/e27370
Subjects
Medical Informatics
08 Information and Computing Sciences
11 Medical and Health Sciences
17 Psychology and Cognitive Sciences
Publication Status
Published
Date Publish Online
2021-07-14