Optical Diagnosis of Neoplasia Using Artificial Intelligence

NCT07158203 | Not Yet Recruiting FDA Device

• 1 other identifier: 2025/055
• Study Type: interventional
• Target: 70
• Locations: 2 countries
• Sites: 2

Brief Summary

Computer-aided diagnosis (CADx) for colonoscopy aims to enhance optical diagnosis but often underperforms when used alongside humans due to under-reliance on AI. Psychological interventions like cognitive forcing, such as delaying CADx suggestions, may improve human-AI interaction by fostering critical assessment. However, their impact on patient-important outcomes remains unexplored. The investigators will conduct an ex-vivo randomized study with 70 endoscopists assessing 100 polyp videos (≤5 mm) using a CADx tool (GI Genius, Medtronic). Participants will be randomized to either:

• Intervention group: CADx suggestions will be shown in the last 3 seconds of the 15 second polyp video.
• Control group: CADx suggestions will be shown in real-time throughout the playback of the 15 second polyp video. The primary endpoint is sensitivity for high-confidence neoplasia detection, with secondary endpoints assessing endoscopists' reliance on AI. CADx systems on the market function in various ways, such as real-time, delayed, or on-demand diagnosis. Our study aims to inform users and manufacturers whether cognitive forcing through delayed CADx suggestions enhances human-AI interaction, leading to improved clinical outcomes.

Conditions

Polyps Colorectal; Colonoscopy; Optical Biopsy; Colorectal Cancer Control and Prevention; Colorectal Cancer Screening; Behavior Change; Psychological Factors; Psychological Intervention

Keywords

behaviour; optical biopsy; colonoscopy; CADx system; colorectal polyps; psychological intervention

Outcome Measures

Primary Outcomes (1)

• Sensitivity of the optical diagnosis of neoplastic lesions.

  \- Sensitivity of each endoscopist and in each arm in the optical diagnosis of neoplastic or non-neoplastic lesions with high confidence level

  Through study completion, an average of 1 year

Secondary Outcomes (12)

• The reliance level on artificial intelligence, measured using the C value of the signal detection theory

  Through study completion, an average of 1 year

• Discrimination (d´) level of neoplastic lesions based on the signal detection theory

  Through study completion, an average of 1 year

• Receiver Operating characteristic (ROC) curve to determine overall discrimination in the signal detection theory

  Through study completion, an average of 1 year

• Proportion of high confidence diagnosis

  Through study completion, an average of 1 year

• Association between the reliance level (C value) on AI and endoscopists age,sex, level of expertise in colonoscopy or CADx, confidence level and area of procedence

  Through study completion, an average of 1 year

Study Arms (2)

CADx suggestions will be shown in 15 second polyp video.

ACTIVE COMPARATOR

CADx suggestions will be shown in real-time throughout the playback of the 15 second polyp video.

Device: CADx simultaneously

CADx suggestions will be shown in the last 3 seconds of the 15 second polyp video.

EXPERIMENTAL

CADx suggestions will be shown in the last 3 seconds of the 15 second polyp video.

Behavioral: CADx delayed

Interventions

CADx simultaneously DEVICE

The investigators showed the CADx suggestion during the 15-second playback of the video

CADx suggestions will be shown in 15 second polyp video.

CADx delayed BEHAVIORAL

During the 15-seconds polyp video the CADx suggestion appear only in the last 3 seconds of the video

CADx suggestions will be shown in the last 3 seconds of the 15 second polyp video.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may not qualify if:

• Endoscopists who are involved in the development of the protocol of the present study.
• Videos with a duration of 15 seconds including both WL and NBI.
• Videos with no clear image of the polyps.
• Videos with more than one polyp on-screen.
• Inflammatory bowel disease
• Polyposis
• Hereditary colorectal disease
• Videos which CADx cannot provide sufficient number of outputs.

Sponsors & Collaborators

• Fundacin Biomedica Galicia Sur: lead

Study Sites (2)

Clinical Effectiveness Research Group

Oslo, 0424, Norway

Location

Research Group in Gastrointestinal Oncology Ourense

Ourense, 32005, Spain

Location

Related Publications (13)

• Zana Buçinca, Maja Barbara Malaya, and Krzysztof Z. Gajos. 2021. To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 188 (April 2021), 21 pages. https://doi.org/10.1145/3449287

  BACKGROUND

• Kunar MA, Watson DG. Framing the fallibility of Computer-Aided Detection aids cancer detection. Cogn Res Princ Implic. 2023 May 24;8(1):30. doi: 10.1186/s41235-023-00485-y.

  PMID: 37222932 BACKGROUND

• Kaminski MF, Anderson J, Valori R, Kraszewska E, Rupinski M, Pachlewski J, Wronska E, Bretthauer M, Thomas-Gibson S, Kuipers EJ, Regula J. Leadership training to improve adenoma detection rate in screening colonoscopy: a randomised trial. Gut. 2016 Apr;65(4):616-24. doi: 10.1136/gutjnl-2014-307503. Epub 2015 Feb 10.

  PMID: 25670810 BACKGROUND

• Mori Y, Kudo SE, Chiu PW, Singh R, Misawa M, Wakamura K, Kudo T, Hayashi T, Katagiri A, Miyachi H, Ishida F, Maeda Y, Inoue H, Nimura Y, Oda M, Mori K. Impact of an automated system for endocytoscopic diagnosis of small colorectal lesions: an international web-based study. Endoscopy. 2016 Dec;48(12):1110-1118. doi: 10.1055/s-0042-113609. Epub 2016 Aug 5.

  PMID: 27494455 BACKGROUND

• Mori Y, Jin EH, Lee D. Enhancing artificial intelligence-doctor collaboration for computer-aided diagnosis in colonoscopy through improved digital literacy. Dig Liver Dis. 2024 Jul;56(7):1140-1143. doi: 10.1016/j.dld.2023.11.033. Epub 2023 Dec 16.

  PMID: 38105144 BACKGROUND

• Meinikheim M, Mendel R, Palm C, Probst A, Muzalyova A, Scheppach MW, Nagl S, Schnoy E, Rommele C, Schulz DAH, Schlottmann J, Prinz F, Rauber D, Ruckert T, Matsumura T, Fernandez-Esparrach G, Parsa N, Byrne MF, Messmann H, Ebigbo A. Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett's esophagus: a tandem randomized and video trial. Endoscopy. 2024 Sep;56(9):641-649. doi: 10.1055/a-2296-5696. Epub 2024 Mar 28.

  PMID: 38547927 BACKGROUND

• Stanislaw H, Todorov N. Calculation of signal detection theory measures. Behav Res Methods Instrum Comput. 1999 Feb;31(1):137-49. doi: 10.3758/bf03207704.

  PMID: 10495845 BACKGROUND

• Kim J, Lim SH, Kang HY, Song JH, Yang SY, Chung GE, Jin EH, Choi JM, Bae JH. Impact of 3-second rule for high confidence assignment on the performance of endoscopists for the real-time optical diagnosis of colorectal polyps. Endoscopy. 2023 Oct;55(10):945-951. doi: 10.1055/a-2073-3411. Epub 2023 May 12.

  PMID: 37172938 BACKGROUND

• Jin EH, Lee D, Bae JH, Kang HY, Kwak MS, Seo JY, Yang JI, Yang SY, Lim SH, Yim JY, Lim JH, Chung GE, Chung SJ, Choi JM, Han YM, Kang SJ, Lee J, Chan Kim H, Kim JS. Improved Accuracy in Optical Diagnosis of Colorectal Polyps Using Convolutional Neural Networks with Visual Explanations. Gastroenterology. 2020 Jun;158(8):2169-2179.e8. doi: 10.1053/j.gastro.2020.02.036. Epub 2020 Feb 29.

  PMID: 32119927 BACKGROUND

• Cherubini A, Dinh NN. A Review of the Technology, Training, and Assessment Methods for the First Real-Time AI-Enhanced Medical Device for Endoscopy. Bioengineering (Basel). 2023 Mar 24;10(4):404. doi: 10.3390/bioengineering10040404.

  PMID: 37106592 BACKGROUND

• Suna N, Koksal AS, Yildiz H, Parlak E, Kuzu UB, Yuksel M, Aydinli O, Turhan N, Sakaogullari SZ, Yalinkilic ZM, Ozin Y, Sasmaz N. Prevalence of advanced histologic features in diminutive colon polyps. Acta Gastroenterol Belg. 2015 Jul-Sep;78(3):287-91.

  PMID: 26448409 BACKGROUND

• Vleugels JLA, Hassan C, Senore C, Cassoni P, Baron JA, Rex DK, Ponugoti PL, Pellise M, Parejo S, Bessa X, Arnau-Collell C, Kaminski MF, Bugajski M, Wieszczy P, Kuipers EJ, Melson J, Ma KH, Holman R, Dekker E, Pohl H. Diminutive Polyps With Advanced Histologic Features Do Not Increase Risk for Metachronous Advanced Colon Neoplasia. Gastroenterology. 2019 Feb;156(3):623-634.e3. doi: 10.1053/j.gastro.2018.10.050. Epub 2018 Nov 2.

  PMID: 30395813 BACKGROUND

• Djinbachian R, Haumesser C, Taghiakbari M, Pohl H, Barkun A, Sidani S, Liu Chen Kiow J, Panzini B, Bouchard S, Deslandres E, Alj A, von Renteln D. Autonomous Artificial Intelligence vs Artificial Intelligence-Assisted Human Optical Diagnosis of Colorectal Polyps: A Randomized Controlled Trial. Gastroenterology. 2024 Jul;167(2):392-399.e2. doi: 10.1053/j.gastro.2024.01.044. Epub 2024 Feb 7.

  PMID: 38331204 BACKGROUND

MeSH Terms

Conditions

Behavior

Study Officials

• Yuichi Mori, MD, PhD

  Clinical Effectiveness Research group

  PRINCIPAL INVESTIGATOR

• Pedro Davila Piñón, Masters degree biotechnology

  Research Group in Gastrointestinal Oncology Ourense / Galicia-Sur Public Galician Foundation

  PRINCIPAL INVESTIGATOR

• Joaquin Cubiella, MD, PhD

  University Hospital of Ourense

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Pedro Davila Piñón, Master degree in biotechnology

CONTACT

+34 988385047; pedro.davila@iisgaliciasur.es

Joaquin Cubiella, MD, PhD

CONTACT

+34 988385047; joaquin.cubiella.fernandez@sergas.es

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: The endoscopists are not blinded to study intervention. Those who analyze the data will be blinded to randomization allocation.
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: The investigators will conduct an ex vivo image-interpretation study where the endoscopists are going to watch 100 short colonoscopy videos of 100 diminutive (\<=5mm) colonic lesions and make optical diagnoses of them. The endoscopists will be given support of computer-aided diagnosis (CADx) before making their decision. The endoscopists will be randomized to the following two arms with a 1:1 ratio, and they are given CADx support accordingly: * Intervention group: CADx suggestions will be shown in the last 3 seconds of the 15 second polyp video. * Control group: CADx suggestions will be shown in real-time throughout the playback of the 15 second polyp video. The endoscopists are going to classify the lesions in the videos as neoplastic (i.e. cancer, adenomas, serrated lesions) or non-neoplastic (i.e. hyperplastic lesions and non-epithelial neoplastic). In each diagnosis, the endoscopists give their confidence level (i.e. high or low) in optical diagnosis.

Study Record Dates

• First Submitted: April 29, 2025
• First Posted: September 5, 2025
• Study Start: September 1, 2025
• Primary Completion: November 1, 2025
• Study Completion: December 1, 2025
• Last Updated: September 5, 2025

Record last verified: 2025-04

Data Sharing

• IPD Sharing: Will not share

Locations

NO (1); ES (1)