Impact of Computer-aided Optical Diagnosis (CAD) in Predicting Histology of Diminutive Rectosigmoid Polyps: a Multicenter Prospective Trial (ABC Study).

NCT04607083 | Completed

• 1 other identifier: 599/2020
• Study Type: observational
• Target: 1,134
• Locations: 1 country
• Sites: 1

Brief Summary

Recently, a CNN-based artificial intelligence (AI) system for polyp characterization has been developed by Fujifilm Co., Tokyo, Japan. It works in conjunction with BLI system. In the present study we prospectively evaluate whether the evaluation of the endoscopist combined with the CAD system output achieve \> 90% accuracy in characterization (i.e. as adenomas or non-adenomas) of diminutive rectosigmoid polyps having histopathology as reference standard. Consecutive adult outpatients undergoing elective colonoscopy, in which at least one diminutive (\<5 mm) rectosigmoid polyp is detected are included. During endoscopic procedures all polyps identified by the endoscopist are documented for size, location and morphology. All diminutive polyps are characterized by a three sequential steps process: I) endoscopist prediction: the endoscopist evaluates the polyp by using BLI through the BASIC classification; the confidence level (high vs. low) in histology prediction is recorded; II) AI prediction: the AI system is switched on and the output of the automatic evaluation is recorded; this outcome is rated as stable or unstable, depending of the consistency over time of the outcome; III) combined prediction: a final classification is provided by endoscopist in light of the results of the first and of the second step; the confidence level is recorded. All polyps are resected and retrieved in separate jars and sent for pathology assessment. Only polyps characterized with high confidence will be included in the per-polyp analysis; the high-confidence characterization rate will be also calculated; the rate of polyps characterized with a CAD stable outcome will be calculated. Operative characteristics (sensitivity, specificity, positive and negative predictive value and accuracy) in distinguishing adenomatous from non-adenomatous polyps, evaluated with high confidence, will be calculated for each diminutive polyp and for each diminutive rectosigmoid polyp, having histopathology report as reference standard. The post-polypectomy surveillance intervals will be calculated on the basis of polyp histology (reference standard) in all patients according to both USMSTF and ESGE guidelines.

Conditions

Colonic Adenomatous Polyp

Outcome Measures

Primary Outcomes (1)

• Agreement of combined prediction with PIVI I statement

  To prospectively evaluate whether the evaluation of the endoscopist combined with the CAD system output achieve \> 90% accuracy in characterization (i.e. as adenomas or non-adenomas) of diminutive rectosigmoid polyps (i.e. PIVI I threshold) having histopathology as reference standard.

  6 months

Secondary Outcomes (3)

• Endoscopist prediction

  6 months

• Ai prediction

  6 months

• Agreement of combined prediction with PIVI II statement

  6 months

Study Arms (1)

Patients with at least one diminutive rectosigmoid polyp

Consecutive adult (\>18 years) outpatients undergoing elective colonoscopy, in which at least one diminutive (\<5 mm) rectosigmoid polyp is detected. Exclusion criteria: * patients with CRC history or hereditary polyposis syndromes or hereditary non-polyposis colorectal cancer * patients with inadequate bowel preparation * patients in which caecal intubation was not achieved or scheduled for partial examinations * polyps could not be resected due to ongoing anticoagulation preventing resection and pathologic assessment * patients undergoing urgent colonoscopy.

Diagnostic Test: Polyp carachterization by combing endoscopist evaluation and Ai output

Interventions

Polyp carachterization by combing endoscopist evaluation and Ai output DIAGNOSTIC_TEST

A polyp characterization (adenoma vs. non adenoma) is provided by endoscopist in light of the results of this own evaluation and of the Ai system output. The confidence level (high vs. low) in polyp characterization is recorded. The combined evaluation is compared with histopathology results.

Patients with at least one diminutive rectosigmoid polyp

Eligibility Criteria

• Age: 18 Years - 85 Years
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Consecutive adult outpatients undergoing elective colonoscopy, in which at least one diminutive (\<5 mm) rectosigmoid polyp is detected

You may qualify if:

• Consecutive adult outpatients undergoing elective colonoscopy, in which at least one diminutive (\<5 mm) rectosigmoid polyp is detected.

You may not qualify if:

• patients with CRC history or hereditary polyposis syndromes or hereditary non-polyposis colorectal cancer
• patients with inadequate bowel preparation
• patients scheduled for partial examinations
• polyps could not be resected due to ongoing anticoagulation preventing resection and pathologic assessment
• patients undergoing urgent colonoscopy

Sponsors & Collaborators

• Valduce Hospital: lead

Study Sites (1)

Gastroenterology Unit, Valduce Hospital

Como, 22100, Italy

Location

Related Publications (1)

• 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. Endoscopy. 2023 Jan;55(1):14-22. doi: 10.1055/a-1852-0330. Epub 2022 May 13.

  PMID: 35562098 DERIVED

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Head of Gastroenterology Unit

Study Record Dates

• First Submitted: October 22, 2020
• First Posted: October 28, 2020
• Study Start: October 22, 2020
• Primary Completion: February 27, 2021
• Study Completion: March 30, 2021
• Last Updated: June 10, 2021

Record last verified: 2021-06

Data Sharing

• IPD Sharing: Will not share

Locations

IT (1)