Colon to Rectum

Endoscopy. 2023;55(1):14–22

Rondonotti E, Hassan C, Tamanini G, Antonelli G, Andrisani G, Leonetti G, Paggi S, Amato A, Scardino G, Di Paolo D, Mandelli G, Lenoci N, Terreni N, Andrealli A, Maselli R, Spadaccini M, Galtieri PA, Correale L, Repici A, Di Matteo FM, Ambrosiani L, Filippi E, Sharma P, Radaelli F

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

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 non-adenomas 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% confidence interval [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, non-experts quickly approached the performance levels of experts over time.

Conclusion: Artificial intelligence (AI)-assisted optical diagnosis matches the required PIVI thresholds. This does not, however, offset the need for endoscopists’ high-level confidence and expertise. The AI system seems to be useful, especially for non-experts.

Dr. Dr. E. Rondonotti, Gastroenterology Unit, Valduce Hospital, Como, Italy,
E-Mail: ema.rondo@gmail.com

DOI: DOI: 10.1055/a-1852-0330

Back to overview

this could be of interest:

Colon to Rectum

Post-COVID-19 irritable bowel syndrome

Gut. 2023;72(3):484–92

Marasco G, Cremon C, Barbaro MR, Cacciari G, Falangone F, Kagramanova A, Bordin D, Drug V, Miftode E, Fusaroli P, Mohamed SY, Ricci C, Bellini M, Rahman MM, Melcarne L, Santos J, Lobo B, Bor S, Yapali S, Akyol D, Sapmaz FP, Urun YY, Eskazan T, Celebi A, Kacmaz H, Ebik B, Binicier HC, Bugdayci MS, Yağcı MB, Pullukcu H, Kaya BY, Tureyen A, Hatemi İ, Koc ES, Sirin G, Calıskan AR, Bengi G, Alıs EE, Lukic S, Trajkovska M, Hod K, Dumitrascu D, Pietrangelo A, Corradini E, Simren M, Sjölund J, Tornkvist N, Ghoshal UC, Kolokolnikova O, Colecchia A, Serra J, Maconi G, De Giorgio R, Danese S, Portincasa P, Di Sabatino A, Maggio M, Philippou E, Lee YY, Salvi D, Venturi A, Borghi C, Zoli M, Gionchetti P, Viale P, Stanghellini V, Barbara G; GI-COVID19 study group

Go to article

Colon to Rectum

Early management of acute severe UC in the biologics era: Development and international validation of a prognostic clinical index to predict steroid response

Gut. 2023;72(3):433–42