Skip to main content
2025 ASCRS Annual Scientific Meeting Main banner
Final Program


Visit ASCRS U
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
CME
CME
Invitation/Ticketed Event
Invitation/Ticketed Event
Invited Lectureship
Invited Lectureship
Award Recipient
Award Recipient
Self-Assessment
Self-Assessment
Social
Social
Industry
Industry
Back

Session: ePoster: Other Neoplasia and Endoscopy 2 (Sun1230)

EP448 - Artificial Intelligence in Polyp Detection Compared to Endoscopists: A Systematic Review and Meta-analysis

Sunday, May 11, 2025
12:35 PM – 12:40 PM PT
Location: Monitor 7, Sails Pavilion, Upper Level

    ePoster Presenter(s)

  • Peiru Zou, Bachelor (he/him/his)

    Student
    Department of Colorectal Surgery, The Sixth Affiliated Hospital, Sun Yat-Sen University
    Guangzhou, Guangdong, China (People's Republic)

    All of the relevant financial relationships listed below have been mitigated.
    This individual has no financial relationships with ineligible companies.

    • Author(s)

  • QL

    Qingfeng Lin, Bachelor

    Student
    Department of Colorectal Surgery, The Sixth Affiliated Hospital, Sun Yat-Sen University
    Guangzhou, Guangdong, China (People's Republic)

    Disclosure information not submitted.

  • WD

    Weihao Deng, Master

    Pathologist
    Department of Pathology, The Sixth Affiliated Hospital, Sun Yat-Sen University
    Guangzhou, Guangdong, China (People's Republic)

    Disclosure information not submitted.

  • ZC

    Zonglu Cai, n/a

    Technician
    Department of Colorectal Surgery, The Sixth Affiliated Hospital, Sun Yat-Sen University
    Guangzhou, Guangdong, China (People's Republic)

    Disclosure information not submitted.

  • XZ

    Xiangjun Zou, PhD

    Professor
    College of Intelligent Manufacturing and Modern Industry
    Urumqi, Xinjiang, China (People's Republic)

    Disclosure information not submitted.

  • TL

    Tian Li, PhD

    Assistant Professor
    Department of Health Technology and Informatics
    Hong Kong, Hong Kong

    Disclosure information not submitted.

  • ZY

    Zaisheng Ye, PhD

    Professor
    Department of Gastric Surgery
    Fuzhou, Fujian, China (People's Republic)

    Disclosure information not submitted.

  • SH

    Shuai Han, PhD

    Associate Professor
    General Surgery Center, Department of Gastrointestinal Surgery, Zhujiang Hospital, Southern Medical University
    Zhujiang, Guangdong, China (People's Republic)

    Disclosure information not submitted.

  • HW

    Hui Wang, PhD

    Professor
    Department of Colorectal Surgery, The Sixth Affiliated Hospital, Sun Yat-Sen University
    Guangzhou, Guangdong, China (People's Republic)

    Disclosure information not submitted.

    • Senior Author(s)

  • ZY

    Zixu Yuan, PhD

    Associate Professor
    Surgical Oncologist Department of Colorectal Surgery, The Sixth Affiliated Hospital, Sun Yat-Sen University
    Guangzhou, Guangdong, China (People's Republic)

    All of the relevant financial relationships listed below have been mitigated.
    This individual has no financial relationships with ineligible companies.

All of the relevant financial relationships listed below have been mitigated.
Peiru Zou, Bachelor: This individual has no financial relationships with ineligible companies.
Zixu Yuan, PhD: This individual has no financial relationships with ineligible companies.
Image or Table (Do Not add text here):

Purpose/Background: The main aim of this study is to compare the diagnostic accuracy of artificial intelligence (AI) to expert or junior endoscopists in the detection of neoplastic polyps with colonoscopy.

Methods/Interventions: We have conducted a comprehensive search on EMBASE, Web of Science, PubMed and Cochrane Library databases since Jan 2015 to July 2024. After screening, 9 studies were included into meta-analysis finally. The risk of bias, publication bias and certainty of evidence were assessed. The primary outcome was the sensitivity and specificity of three groups (AI, expert and junior endoscopist). R version 4.4.1, Review Manager 5.4 and STATA 18.0 were used for data analysis.

Results/Outcomes: A total of 1285 patients with 2572 lesions were included in the study. The diagnostic accuracy of AI group is comparable to expert group (sensitivity: 0.88 versus 0.84; specificity: 0.81 versus 0.86), and AI is better than junior endoscopist except for specificity (sensitivity: 0.88 versus 0.74; specificity: 0.81 versus 0.82).

Conclusion/Discussion: AI system is a useful tool in diagnosis of polyps with the similar performance to expert endoscopist and is superior to junior endoscopist, which is critical to aid endoscopists to improve the diagnostic accuracy of polyps in real-time colonoscopy.