Accuracy of Computer-aided Diagnosis in Colonoscopy Varies according to Polyp Location. A Systematic Review and Meta-analysis.

Artificial intelligence CADx Characterization Colonoscopy Colorectal Cancer Computer-aided diagnosis Optical diagnosis Screening

Journal

Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association
ISSN: 1542-7714
Titre abrégé: Clin Gastroenterol Hepatol
Pays: United States
ID NLM: 101160775

Informations de publication

Date de publication:
27 Aug 2024
Historique:
received: 16 04 2024
revised: 02 08 2024
accepted: 08 08 2024
medline: 31 8 2024
pubmed: 31 8 2024
entrez: 29 8 2024
Statut: aheadofprint

Résumé

Computer-Aided Diagnosis (CADx) assists endoscopists in differentiating between neoplastic and non-neoplastic polyps during colonoscopy. This study aimed to evaluate the impact of polyp location (proximal vs. distal colon) on the diagnostic performance of CADx for ≤5mm polyps. We searched for studies evaluating the performance of real-time CADx alone (i.e., independently of endoscopist judgement) for predicting the histology of colorectal polyps ≤5mm. The primary endpoints were CADx sensitivity and specificity in the proximal and distal colon. Secondary outcomes were the negative predictive value (NPV), positive predictive value (PPV), and the accuracy of the CADx alone. Distal colon was limited to the rectum and sigmoid. We included 11 studies for analysis with a total of 7,782 <5mm polyps. CADx specificity was significantly lower in the proximal colon compared to the distal colon (62% versus 85%; Risk ratio (RR): 0.74 [95% CI: 0.72-0.84]). Conversely, sensitivity was similar (89% vs 87% (EC-1); RR: 1.00 [95% CI: 0.97-1.03]. The NPV (64% versus 93%; RR: 0.71 [95% CI: 0.64-0.79]) and accuracy (81% vs 86%; RR: 0.95 [95% CI: 0.91-0.99]) were significantly lower in the proximal than distal colon, while PPV was higher in the proximal colon (87% vs 76%; RR: 1.11 [95% CI: 1.06-1.17]). The diagnostic performance of CADx for polyps in the proximal colon is inadequate, exhibiting significantly lower specificity compared to its performance for distal polyps. While current CADx systems are suitable for use in the distal colon, they should not be employed for proximal polyps until more performant systems are developed specifically for these lesions.

Sections du résumé

BACKGROUND & AIMS OBJECTIVE
Computer-Aided Diagnosis (CADx) assists endoscopists in differentiating between neoplastic and non-neoplastic polyps during colonoscopy. This study aimed to evaluate the impact of polyp location (proximal vs. distal colon) on the diagnostic performance of CADx for ≤5mm polyps.
METHODS METHODS
We searched for studies evaluating the performance of real-time CADx alone (i.e., independently of endoscopist judgement) for predicting the histology of colorectal polyps ≤5mm. The primary endpoints were CADx sensitivity and specificity in the proximal and distal colon. Secondary outcomes were the negative predictive value (NPV), positive predictive value (PPV), and the accuracy of the CADx alone. Distal colon was limited to the rectum and sigmoid.
RESULTS RESULTS
We included 11 studies for analysis with a total of 7,782 <5mm polyps. CADx specificity was significantly lower in the proximal colon compared to the distal colon (62% versus 85%; Risk ratio (RR): 0.74 [95% CI: 0.72-0.84]). Conversely, sensitivity was similar (89% vs 87% (EC-1); RR: 1.00 [95% CI: 0.97-1.03]. The NPV (64% versus 93%; RR: 0.71 [95% CI: 0.64-0.79]) and accuracy (81% vs 86%; RR: 0.95 [95% CI: 0.91-0.99]) were significantly lower in the proximal than distal colon, while PPV was higher in the proximal colon (87% vs 76%; RR: 1.11 [95% CI: 1.06-1.17]).
CONCLUSION CONCLUSIONS
The diagnostic performance of CADx for polyps in the proximal colon is inadequate, exhibiting significantly lower specificity compared to its performance for distal polyps. While current CADx systems are suitable for use in the distal colon, they should not be employed for proximal polyps until more performant systems are developed specifically for these lesions.

Identifiants

DOI: 10.1016/j.cgh.2024.08.021 PMID: 39209199
pubmed: 39209199
pii: S1542-3565(24)00791-2
doi: 10.1016/j.cgh.2024.08.021
pii:
doi:

Types de publication

Journal Article Review

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

Copyright © 2024. Published by Elsevier Inc.

Auteurs

Tommy Rizkala (T)

IRCCS Humanitas Research Hospital, via Manzoni 56, 20089 Rozzano, Milan, Italy.

Cesare Hassan (C)

IRCCS Humanitas Research Hospital, via Manzoni 56, 20089 Rozzano, Milan, Italy; Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, 20072 Pieve Emanuele, Milan, Italy. Electronic address: cesare.hassan@hunimed.eu.

Yuichi Mori (Y)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan; University of Oslo, Clinical Effectiveness Research Group, Oslo, Norway; Department of Transplantation Medicine, Oslo University Hospital, Oslo, Norway.

Marco Spadaccini (M)

IRCCS Humanitas Research Hospital, via Manzoni 56, 20089 Rozzano, Milan, Italy.

Giulio Antonelli (G)

Gastroenterology and Digestive Endoscopy Unit, Ospedale dei Castelli, Ariccia, Rome, Italy; Department of Anatomical, Histological, Forensic Medicine and Orthopedics Sciences, "Sapienza" University of Rome, Italy.

Evelien Dekker (E)

Department of Gastroenterology and Hepatology, Amsterdam University Medical Center, Amsterdam, the Netherlands; Bergman Clinics Maag and Darm Amsterdam, Amsterdam, The Netherlands.

Britt B S L Houwen (BBSL)

Department of Gastroenterology and Hepatology, Amsterdam University Medical Center, Amsterdam, the Netherlands.

Oliver Pech (O)

Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany.

Sebastian Baumer (S)

Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany.

Emanuele Rondonotti (E)

Gastroenterology Unit, Valduce Hospital, Como, Italy.

Franco Radaelli (F)

Gastroenterology Unit, Valduce Hospital, Como, Italy.

James Weiquan Li (JW)

Department of Gastroenterology and Hepatology, Changi General Hospital, Singapore Health Services.

Daniel von Renteln (D)

Montreal University Hospital Research Center, Montreal; Division of Gastroenterology, Montreal University Hospital Center (CHUM), Montreal, Qc, Canada.

Masashi Misawa (M)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan.

Antonio Facciorusso (A)

University of Foggia, Department of Medical Sciences, Section of Gastroenterology, Foggia, Italy.

Roberta Maselli (R)

IRCCS Humanitas Research Hospital, via Manzoni 56, 20089 Rozzano, Milan, Italy; Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, 20072 Pieve Emanuele, Milan, Italy.

Silvia Carrara (S)

IRCCS Humanitas Research Hospital, via Manzoni 56, 20089 Rozzano, Milan, Italy; Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, 20072 Pieve Emanuele, Milan, Italy.

Alessandro Fugazza (A)

IRCCS Humanitas Research Hospital, via Manzoni 56, 20089 Rozzano, Milan, Italy.

Antonio Capogreco (A)

IRCCS Humanitas Research Hospital, via Manzoni 56, 20089 Rozzano, Milan, Italy.

Kareem Khalaf (K)

Division of Gastroenterology, St. Michael's Hospital, University of Toronto, Toronto, ON M5S 1A1, Canada.

Harsh Patel (H)

Kansas City VA Medical Center, Gastroenterology and Hepatology, Kansas City, United States.

Prateek Sharma (P)

Kansas City VA Medical Center, Gastroenterology and Hepatology, Kansas City, United States.

Douglas Rex (D)

Indiana University School of Medicine, Division of Gastroenterology, Indianapolis, Indiana, USA.

Alessandro Repici (A)

IRCCS Humanitas Research Hospital, via Manzoni 56, 20089 Rozzano, Milan, Italy; Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, 20072 Pieve Emanuele, Milan, Italy.

Classifications MeSH