Health Screening and Promotion Center, Asan Medical Center, College of Medicine, University of Ulsan, Seoul, South Korea.
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.
Gastrointest Endosc. 2022 Mar;95(3):512-518.e1. doi: 10.1016/j.gie.2021.11.041. Epub 2021 Dec 8.
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.
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).
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).
The algorithm assessment of bowel cleanliness as measured with the BBPS showed good performance and agreement with experts including full withdrawal colonoscopies.
可靠的肠道准备评估对于确保高质量的结肠镜检查至关重要。目前的肠道准备评分系统存在观察者间变异性的限制。本研究旨在通过开发一种基于结肠镜检查视频的人工智能（AI）/卷积神经网络（CNN）算法，对肠道准备的充分性进行客观评估。
使用来自 200 例结肠镜检查的 73304 张图像的训练集开发了两个 CNN。首先，开发并训练了一个二进制 CNN，以区分适合和不适合波士顿肠道准备评分量表（BBPS）评分的视频帧。然后，在 26950 个经过专家注释的合适帧上开发并训练了第二个多类 CNN，这些帧的 BBPS 段评分（0-3）。我们使用 252 个 10 秒的视频片段对算法进行了验证，这些视频片段由 2 名专家分配了 BBPS 段评分。该算法通过计算每个帧的评分的平均 BBPS 来提供基于算法的平均 BBPS 评分（AI-BBPS）。我们通过选择与二分 BBPS 评分（即充分与不充分）密切匹配的二分 AI-BBPS 评分，最大限度地提高了算法的性能。我们使用 30 个独立的 10 秒视频片段（测试集 1）和 10 个完整退镜结肠镜视频（测试集 2），对基于算法的 AI-BBPS 平均 BBPS 评分与人类评分进行了测试。
在验证集中，该算法的曲线下面积为 0.918，对肠道清洁不充分的检测准确率为 85.3%。在测试集 1 中，对肠道准备不充分的敏感性为 100%，评分者与 AI 的一致性为 76.7%至 83.3%。在测试集 2 中，每个节段肠道准备不充分的敏感性为 100%，评分者与 AI 的一致性为 68.9%至 89.7%。评分者单独与评分者和 AI 的一致性相似（κ分别为 0.694 和 0.649）。
基于 BBPS 的肠道清洁度的算法评估与专家（包括完整退镜结肠镜检查）的评估具有良好的性能和一致性。
