Endoscopy 2023; 55(01): 14-22
DOI: 10.1055/a-1852-0330
Original article

Artificial intelligence-assisted optical diagnosis for the resect-and-discard strategy in clinical practice: the Artificial intelligence BLI Characterization (ABC) study

Emanuele Rondonotti*
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
,
Cesare Hassan*
 2   Digestive Endoscopy Unit, Nuovo Regina Margherita Hospital, Rome, Italy
,
Giacomo Tamanini
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
,
Giulio Antonelli
 2   Digestive Endoscopy Unit, Nuovo Regina Margherita Hospital, Rome, Italy
 3   Department of Translational and Precision Medicine, Sapienza University of Rome, Rome, Italy
,
Gianluca Andrisani
 4   Digestive Endoscopy Unit, Campus Bio-Medico, University of Rome, Rome, Italy
,
Giovanni Leonetti
 2   Digestive Endoscopy Unit, Nuovo Regina Margherita Hospital, Rome, Italy
 5   Endoscopy Unit, Casa di Cura Nuova Santa Teresa, Viterbo, Italy
,
Silvia Paggi
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
,
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
,
Giulia Scardino
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
,
Dhanai Di Paolo
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
 6   Department of Gastroenterology and Hepatology, Foundation IRCCS Ca’ Granda Ospedale Maggiore Policlinico, Milan, Italy
,
Giovanna Mandelli
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
,
Nicoletta Lenoci
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
,
Natalia Terreni
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
,
Alida Andrealli
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
,
Roberta Maselli
 7   Department of Biomedical Sciences, Humanitas University, Rozzano, Milan, Italy
 8   Endoscopy Unit, Humanitas Clinical and Research Center IRCCS, Rozzano, Milan, Italy
,
Marco Spadaccini
 7   Department of Biomedical Sciences, Humanitas University, Rozzano, Milan, Italy
 8   Endoscopy Unit, Humanitas Clinical and Research Center IRCCS, Rozzano, Milan, Italy
,
Piera Alessia Galtieri
 8   Endoscopy Unit, Humanitas Clinical and Research Center IRCCS, Rozzano, Milan, Italy
,
Loredana Correale
 2   Digestive Endoscopy Unit, Nuovo Regina Margherita Hospital, Rome, Italy
,
Alessandro Repici
 7   Department of Biomedical Sciences, Humanitas University, Rozzano, Milan, Italy
 8   Endoscopy Unit, Humanitas Clinical and Research Center IRCCS, Rozzano, Milan, Italy
,
Francesco Maria Di Matteo
 4   Digestive Endoscopy Unit, Campus Bio-Medico, University of Rome, Rome, Italy
,
Luciana Ambrosiani
 9   Pathology Department, Valduce Hospital, Como, Italy
,
Emanuela Filippi
 9   Pathology Department, Valduce Hospital, Como, Italy
,
Prateek Sharma
10   Department of Gastroenterology, Kansas City VA Medical Center, Kansas City, Missouri, USA
11   Department of Gastroenterology and Hepatology, University of Kansas Medical Center, Kansas City, Kansas, USA
,
Franco Radaelli
 1   Gastroenterology Unit, Valduce Hospital, Como, Italy
› Author Affiliations
Trial Registration: ClinicalTrials.gov Registration number (trial ID): NCT04607083 Type of study: Prospective, Multicenter study

Abstract

Background Optical diagnosis of colonic polyps is poorly reproducible outside of high volume referral centers. The present study aimed to assess whether real-time artificial intelligence (AI)-assisted optical diagnosis is accurate enough to implement the leave-in-situ strategy for diminutive (≤ 5 mm) rectosigmoid polyps (DRSPs).

Methods Consecutive colonoscopy outpatients with ≥ 1 DRSP were included. DRSPs were categorized as adenomas or nonadenomas by the endoscopists, who had differing expertise in optical diagnosis, with the assistance of a real-time AI system (CAD-EYE). The primary end point was ≥ 90 % negative predictive value (NPV) for adenomatous histology in high confidence AI-assisted optical diagnosis of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations [PIVI-1] threshold), with histopathology as the reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (≥ 90 %; PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines.

Results Overall 596 DRSPs were retrieved for histology in 389 patients; an AI-assisted high confidence optical diagnosis was made in 92.3 %. The NPV of AI-assisted optical diagnosis for DRSPs (PIVI-1) was 91.0 % (95 %CI 87.1 %–93.9 %). The PIVI-2 threshold was met with 97.4 % (95 %CI 95.7 %–98.9 %) and 92.6 % (95 %CI 90.0 %–95.2 %) of patients according to ESGE and USMSTF, respectively. AI-assisted optical diagnosis accuracy was significantly lower for nonexperts (82.3 %, 95 %CI 76.4 %–87.3 %) than for experts (91.9 %, 95 %CI 88.5 %–94.5 %); however, nonexperts quickly approached the performance levels of experts over time.

Conclusion AI-assisted optical diagnosis matches the required PIVI thresholds. This does not however offset the need for endoscopistsʼ high level confidence and expertise. The AI system seems to be useful, especially for nonexperts.

* Joint first authors


Supplementary material



Publication History

Received: 15 October 2021

Accepted after revision: 13 May 2022

Accepted Manuscript online:
13 May 2022

Article published online:
12 July 2022

© 2022. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany