Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis - 16/10/20

Doi : 10.1016/j.gie.2020.06.059

Cesare Hassan, MD, PhD, Marco ^1,^{^{∗
Drs Hassan and Spadaccini contributed equally to this article.}}, Marco Spadaccini, MD ^2,^3,^⁎^{^{∗
Drs Hassan and Spadaccini contributed equally to this article.}}, Andrea Iannone, MD, PhD ⁴, Roberta Maselli, MD, PhD ², Manol Jovani, MD ^5,⁶, Viveksandeep Thoguluva Chandrasekar, MD ⁷, Giulio Antonelli, MD ¹, Honggang Yu, MD ⁸, Miguel Areia, MD, PhD ⁹, Mario Dinis-Ribeiro, MD ¹⁰, Pradeep Bhandari, MD ¹¹, Prateek Sharma, MD, PhD ⁷, Douglas K. Rex, MD ¹², Thomas Rösch, MD, PhD ¹³, Michael Wallace, MD, PhD ¹⁴, Alessandro Repici, MD ^2,³
¹ Digestive Endoscopy Unit, Nuovo Regina Margherita Hospital, Rome, Italy
² Endoscopy Unit, Humanitas Clinical and Research Center–IRCCS, Rozzano, Italy
³ Department of Biomedical Sciences, Humanitas University, Rozzano, Italy
⁴ Section of Gastroenterology, Department of Emergency and Organ Transplantation, University of Bari, Bari, Italy
⁵ Division of Gastroenterology and Hepatology, Johns Hopkins Hospital, Baltimore, Maryland, USA
⁶ Division of Gastroenterology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
⁷ Gastroenterology and Hepatology, Kansas City VA Medical Center, Kansas City, Missouri, USA
⁸ Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
⁹ Department of Gastroenterology, Portuguese Oncology Institute of Coimbra, Coimbra, Portugal
¹⁰ MEDCIDS-Department of Community Medicine, Information and Decision in Health, Faculty of Porto, University of Medicine, Porto, Portugal
¹¹ Department of Gastroenterology, Queen Alexandra Hospital, Portsmouth, UK
¹² Division of Gastroenterology/Hepatology, Indiana University School of Medicine, Indianapolis, Indiana, USA
¹³ Department of Interdisciplinary Endoscopy, University Hospital Hamburg-Eppendorf, Hamburg, Germany
¹⁴ Department of Gastroenterology, Mayo Clinic, Jacksonville, Florida, USA

^∗Reprint requests: Marco Spadaccini, MD, Humanitas Research Hospital and University, Via Manzoni 56, 20089 Rozzano (Milano) Italy.Humanitas Research Hospital and UniversityVia Manzoni 56Rozzano (Milano)20089Italy

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Friday 16 October 2020

Abstract

Background and Aims

One-fourth of colorectal neoplasia are missed at screening colonoscopy, representing the main cause of interval colorectal cancer. Deep learning systems with real-time computer-aided polyp detection (CADe) showed high accuracy in artificial settings, and preliminary randomized controlled trials (RCTs) reported favorable outcomes in the clinical setting. The aim of this meta-analysis was to summarize available RCTs on the performance of CADe systems in colorectal neoplasia detection.

Methods

We searched MEDLINE, EMBASE, and Cochrane Central databases until March 2020 for RCTs reporting diagnostic accuracy of CADe systems in the detection of colorectal neoplasia. The primary outcome was pooled adenoma detection rate (ADR), and secondary outcomes were adenoma per colonoscopy (APC) according to size, morphology, and location; advanced APC; polyp detection rate; polyps per colonoscopy; and sessile serrated lesions per colonoscopy. We calculated risk ratios (RRs), performed subgroup and sensitivity analyses, and assessed heterogeneity and publication bias.

Results

Overall, 5 randomized controlled trials (4354 patients) were included in the final analysis. Pooled ADR was significantly higher in the CADe group than in the control group (791/2163 [36.6%] vs 558/2191 [25.2%]; RR, 1.44; 95% confidence interval [CI], 1.27-1.62; P < .01; I² = 42%). APC was also higher in the CADe group compared with control (1249/2163 [.58] vs 779/2191 [.36]; RR, 1.70; 95% CI, 1.53-1.89; P < .01; I² = 33%). APC was higher for ≤5-mm (RR, 1.69; 95% CI, 1.48-1.84), 6- to 9-mm (RR, 1.44; 95% CI, 1.19-1.75), and ≥10-mm adenomas (RR, 1.46; 95% CI, 1.04-2.06) and for proximal (RR, 1.59; 95% CI, 1.34-1.88), distal (RR, 1.68; 95% CI, 1.50-1.88), flat (RR, 1.78; 95% CI, 1.47-2.15), and polypoid morphology (RR, 1.54; 95% CI, 1.40-1.68). Regarding histology, CADe resulted in a higher sessile serrated lesion per colonoscopy (RR, 1.52; 95% CI, 1.14-2.02), whereas a nonsignificant trend for advanced ADR was found (RR, 1.35; 95% CI, .74-2.47; P = .33; I² = 69%). Level of evidence for RCTs was graded as moderate.

Conclusions

According to available evidence, the incorporation of artificial intelligence as aid for detection of colorectal neoplasia results in a significant increase in the detection of colorectal neoplasia, and such effect is independent from main adenoma characteristics.

Le texte complet de cet article est disponible en PDF.

Abbreviations : ADR, APC, CADe, CNN, RR, RCT

Plan

Methods

Data sources and search strategy

Selection process

Data extraction

Inclusion and exclusion criteria

Outcomes

Quality assessment

Data synthesis and analysis

Results

Study characteristics and quality

ADR and polyp detection rate

APCs, sessile serrated lesions, and polyps per colonoscopy

Withdrawal time

Quality of evidence

Discussion

DISCLOSURE: The following authors disclosed financial relationships: C. Hassan, A. Repici: Consultant for and equipment loan from Medtronic and Fujifilm. P. Sharma: equipment loan from Medtronic Italy; consultant for and grant support from Olympus, Medtronic USA, and Fujifilm; consultant for Lumendi, Boston Scientific, and Bausch; grant support from US Endoscopy, Ironwood, Erbe, Docbot, Cosmo Pharmaceuticals, and CDx Labs; D.K. Rex: owner of Satisfai Health, consultant for Medtronic, Boston Scientific, Aries Pharmaceutical, Lumenid Ltd, Braintree Laboratories, Norgine, Endokey, and GI Supply; consultant for and research support from Olympus Corporation; research support from EndoAid, Medivators, and Erbe USA, Inc; M. Wallace: consultant for Virgo Inc, Cosmo/Aries Pharmaceuticals, Anx Robotica (2019), Covidien, and GI Supply; research grants from Fujifilm, Boston Scientific, Olympus, Medtronic, Ninepoint Medical, and Cosmo/Aries Pharmaceuticals; stock options from Virgo; consulting on behalf of Mayo Clinic, GI Supply (2018), Endokey, Endostart, Boston Scientific, and Microtek; minor food/beverage from Synergy Pharmaceuticals, Boston Scientific, and Cook Medical. All other authors disclosed no financial relationships.

If you would like to chat with an author of this article, you may contact Dr Spadaccini at marco.spadaccini@humanitas.it.