人工智能模型用于自动识别肠道准备进行结肠镜检查 (AI-PREPOO):一个多中心研究
Kosuke Kojima1,2, Kazuya Takahashi1, Hiroki Maruyama1
1Division of Gastroenterology and Hepatology, Graduate School of Medical and Dental Sciences, Niigata University, Niigata, Japan.
人工智能 (AI) 模型被开发用于使用智能手机图像自动评估肠道准备进行结肠镜检查. AI-PREPOO 1实现了高精度,可能减少医疗保健负担.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 胃肠病学 胃肠病学
背景情况:
- 高质量的结肠镜取决于适当的肠道准备.
- 对患者和提供者来说,评估肠道准备常常是负担.
- 需要自动化评估工具来简化这一过程.
研究的目的:
- 开发人工智能 (AI) 模型,用于自动化肠道准备评估.
- 识别能够为结肠镜准备分类便图像的AI模型.
- 为了减轻与手动肠道准备评估相关的负担.
主要方法:
- 参与者用智能手机拍摄了便图像.
- 图像被上传并标记为"准备好"或"不准备好"进行结肠镜检查.
- 四个深度学习模型 (AI-PREPOO 1-4) 在标记图像上使用转移学习进行训练.
主要成果:
- 收集和增强了282张便图像的数据集.
- 所有开发的AI模型都表现出高性能 (AUC>0.90).
- AI-PREPOO 1获得了最佳的诊断性能 (AUC,0.95;灵敏度,0.93;特异性,0.86).
结论:
- 基于人工智能的模型可以准确地评估肠道准备的充分性.
- AI-PREPOO 1显示出有希望的,平衡的诊断性能.
- 这种人工智能工具有可能简化肠道准备评估并减轻医疗保健负担.
更多相关视频
03:43Structured Approach to Colonoscopy Technique Optimization: A Single-Center Experience with Novice Endoscopists
Published on: July 11, 2025
15:49Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System
Published on: October 16, 2013
相关概念视频
Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and...
Endoscopic Procedures II: Colonoscopy
Assessment of the Rectum and Anus
Rectal Inspection
Begin by inspecting the perianal and anal areas for color, texture, rashes,...
Endoscopic Procedures III: Video Capsule Endoscopy
