Park Kwangbeom, Lim Jisup, Shin Seung Hwan, Ryu Minkyeong, Shin Hyungeun, Lee Minyoung, Hong Seung Wook, Hwang Sung Wook, Park Sang Hyoung, Yang Dong-Hoon, Ye Byong Duk, Myung Seung-Jae, Yang Suk-Kyun, Kim Namkug, Byeon Jeong-Sik
Department of Internal Medicine, Nowon Eulji Medical Center, Eulji University, Seoul, South Korea.
Department of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea.
J Gastroenterol Hepatol. 2025 Jan;40(1):115-122. doi: 10.1111/jgh.16788. Epub 2024 Nov 4.
Differentiating between Crohn's disease (CD) and gastrointestinal tuberculosis (GITB) is challenging. We aimed to evaluate the clinical applicability of an artificial intelligence (AI) model for this purpose.
The AI model was developed and assessed using an internal dataset comprising 1,132 colonoscopy images of CD and 1,045 colonoscopy images of GITB at a tertiary referral center. Its stand-alone performance was further evaluated in an external dataset comprising 67 colonoscopy images of 17 CD patients and 63 colonoscopy images of 14 GITB patients from other institutions. Additionally, a crossover trial involving three expert endoscopists and three trainee endoscopists compared AI-assisted and unassisted human interpretations.
In the internal dataset, the sensitivity, specificity, and accuracy of the AI model in distinguishing between CD and GITB were 95.3%, 100.0%, and 97.7%, respectively, with an area under the ROC curve of 0.997. In the external dataset, the AI model exhibited a sensitivity, specificity, and accuracy of 77.8%, 85.1%, and 81.5%, respectively, with an area under the ROC curve of 0.877. In the human endoscopist trial, AI assistance increased the pooled accuracy of the six endoscopists from 86.2% to 88.8% (P = 0.010). While AI did not significantly enhance diagnostic accuracy for the experts (96.7% with AI vs 95.6% without, P = 0.360), it significantly improved accuracy for the trainees (81.0% vs 76.7%, P = 0.002).
This AI model shows potential in aiding the accurate differential diagnosis between CD and GITB, particularly benefiting less experienced endoscopists.
区分克罗恩病（CD）和胃肠道结核（GITB）具有挑战性。我们旨在评估一种人工智能（AI）模型在此方面的临床适用性。
使用一个内部数据集开发并评估该AI模型，该数据集包含一家三级转诊中心的1132张CD结肠镜检查图像和1045张GITB结肠镜检查图像。在一个外部数据集中进一步评估其独立性能，该外部数据集包含来自其他机构的17例CD患者的67张结肠镜检查图像和14例GITB患者的63张结肠镜检查图像。此外，一项涉及三名专家内镜医师和三名实习内镜医师的交叉试验比较了AI辅助和非辅助的人工解读。
在内部数据集中，AI模型区分CD和GITB的敏感性、特异性和准确性分别为95.3%、100.0%和97.7%，ROC曲线下面积为0.997。在外部数据集中，AI模型的敏感性、特异性和准确性分别为77.8%、85.1%和81.5%，ROC曲线下面积为0.877。在人类内镜医师试验中，AI辅助使六名内镜医师的合并准确率从86.2%提高到88.8%（P = 0.010）。虽然AI没有显著提高专家的诊断准确率（有AI时为96.7%，无AI时为95.6%，P = 0.360），但它显著提高了实习生的准确率（从76.7%提高到81.0%，P = 0.002）。
这种AI模型在辅助CD和GITB的准确鉴别诊断方面显示出潜力，尤其对经验较少的内镜医师有益。
