Advertisement

Artificial intelligence for the assessment of bowel preparation

  • Ji Young Lee
    Affiliations
    Health Screening and Promotion Center, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, South Korea
    Search for articles by this author
  • Audrey H. Calderwood
    Affiliations
    Department of Medicine, Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire, USA

    The Geisel School of Medicine at Dartmouth and the Dartmouth Institute of Health Policy and Clinical Practice, Hanover, New Hampshire, USA
    Search for articles by this author
  • William Karnes
    Affiliations
    Department of Gastroenterology and Department of Internal Medicine, University of California Irvine Medical Center, Orange, California, USA

    Docbot, Irvine, California
    Search for articles by this author
  • James Requa
    Affiliations
    Docbot, Irvine, California
    Search for articles by this author
  • Author Footnotes
    ∗ Drs Jacobson and Wallace contributed equally to this article.
    Brian C. Jacobson
    Footnotes
    ∗ Drs Jacobson and Wallace contributed equally to this article.
    Affiliations
    Department of Medicine, Division of Gastroenterology, Massachusetts General Hospital, Boston, Massachusetts, USA
    Search for articles by this author
  • Author Footnotes
    ∗ Drs Jacobson and Wallace contributed equally to this article.
    Michael B. Wallace
    Correspondence
    Reprint requests: Michael B. Wallace, MD, MPH, Division of Gastroenterology and Hepatology, Mayo Clinic, 4500 San Pablo Rd, Jacksonville, FL 32224.
    Footnotes
    ∗ Drs Jacobson and Wallace contributed equally to this article.
    Affiliations
    Division of Gastroenterology and Hepatology, Mayo Clinic Jacksonville, Florida, USA

    Center of Research in Computer Vision, University of Central Florida, Orlando, Florida, USA
    Search for articles by this author
  • Author Footnotes
    ∗ Drs Jacobson and Wallace contributed equally to this article.
Published:December 08, 2021DOI:https://doi.org/10.1016/j.gie.2021.11.041

      Background and Aims

      A reliable assessment of bowel preparation is important to ensure high-quality colonoscopy. Current bowel preparation scoring systems are limited by interobserver variability. This study aimed to demonstrate objective assessment of bowel preparation adequacy using an artificial intelligence (AI)/convolutional neural network (CNN) algorithm developed from colonoscopy videos.

      Methods

      Two CNNs were developed using a training set of 73,304 images from 200 colonoscopies. First, a binary CNN was developed and trained to distinguish video frames that were appropriate versus inappropriate for scoring with the Boston Bowel Preparation Scale (BBPS). A second multiclass CNN was developed and trained on 26,950 appropriate frames that were expertly annotated with BBPS segment scores (0-3). We validated the algorithm using 252 10-second video clips that were assigned BBPS segment scores by 2 experts. The algorithm provided mean BBPS scores based on the algorithm (AI-BBPS) by calculating mean BBPS based on each frame’s scoring. We maximized the algorithm’s performance by choosing a dichotomized AI-BBPS score that closely matched dichotomized BBPS scores (ie, adequate vs inadequate). We tested the mean BBPS score based on the algorithm AI-BBPS against human rating using 30 independent 10-second video clips (test set 1) and 10 full withdrawal colonoscopy videos (test set 2).

      Results

      In the validation set, the algorithm demonstrated an area under the curve of .918 and accuracy of 85.3% for detection of inadequate bowel cleanliness. In test set 1, sensitivity for inadequate bowel preparation was 100% and agreement between raters and AI was 76.7% to 83.3%. In test set 2, sensitivity for inadequate bowel preparation for each segment was 100% and agreement between raters and AI was 68.9% to 89.7%. Agreement between raters alone versus raters and AI were similar (κ = .694 and .649, respectively).

      Conclusions

      The algorithm assessment of bowel cleanliness as measured with the BBPS showed good performance and agreement with experts including full withdrawal colonoscopies.

      Graphical abstract

      Abbreviations:

      AI (artificial intelligence), AI-BBPS (mean BBPS score based on the algorithm), AUC (area under the receiver operating characteristic curve), BBPS (Boston bowel preparation scale), CNN (convolutional neural network), dAI-BBPS (dichotomized AI-BBPS)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Gastrointestinal Endoscopy
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Jacobson B.C.
        • Calderwood A.H.
        Measuring bowel preparation adequacy in colonoscopy-based research: review of key considerations.
        Gastrointest Endosc. 2020; 91: 248-256
        • Aronchick C.A.
        • Lipshutz W.H.
        • Wright S.H.
        • et al.
        Validation of an instrument to assess colon cleansing [abstract].
        Am J Gastroenterol. 1999; 94: 2667
        • Rostom A.
        • Jolicoeur E.
        Validation of a new scale for the assessment of bowel preparation quality.
        Gastrointest Endosc. 2004; 59: 482-486
        • Lai E.J.
        • Calderwood A.H.
        • Doros G.
        • et al.
        The Boston Bowel Preparation Scale: a valid and reliable instrument for colonoscopy-oriented research.
        Gastrointest Endosc. 2009; 69: 620-625
        • Calderwood A.H.
        • Jacobson B.C.
        Comprehensive validation of the Boston Bowel Preparation Scale.
        Gastrointest Endosc. 2010; 72: 686-692
        • Urban G.
        • Tripathi P.
        • Alkayali T.
        • et al.
        Deep learning localizes and identifies polyps in real time with 96% accuracy in screening colonoscopy.
        Gastroenterology. 2018; 155: 1069-1078
        • Wang P.
        • Berzin T.M.
        • Glissen Brown J.R.
        • et al.
        Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study.
        Gut. 2019; 68: 1813-1819
        • Cohen J.
        Weighted kappa: nominal scale agreement with provision for scaled disagreement or partial credit.
        Psychol Bull. 1968; 70: 213-220
        • Gottlieb K.
        • Requa J.
        • Karnes W.
        • et al.
        Central reading of ulcerative colitis clinical trial videos using neural networks.
        Gastroenterology. 2021; 160: 710-719
      1. Dowle M, Srinivasan A. data.table: extension of “data.frame.” 2020. Available at: https://r-datatable.com.

        • Bossuyt P.M.
        • Reitsma J.B.
        • Bruns D.E.
        • et al.
        STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies.
        BMJ. 2015; 351: h5527
        • Cohen J.
        A coefficient of agreement for nominal scales.
        Educ Psychol Measure. 1960; 20: 37-46
        • Fleiss J.L.
        Measuring nominal scale agreement among many raters.
        Psychol Bull. 1971; 76: 378-382
        • Zhou J.
        • Wu L.
        • Wan X.
        • et al.
        A novel artificial intelligence system for the assessment of bowel preparation (with video).
        Gastrointest Endosc. 2020; 91: 428-435

      Linked Article