Multi-step validation of a deep learning-based system for the quantification of bowel preparation: a prospective, observational study
- Wei Zhou, MD
- Liwen Yao, MD
- Huiling Wu, MD
- Biqing Zheng, MD
- Shan Hu, PhD
- Lihui Zhang, MD
- Xun Li, MD
- Chunping He, MD
- Zhengqiang Wang, MD
- Yanxia Li, MD
- Chao Huang, MD
- Mingwen Guo, MD
- Xiaoqing Zhang, MD
- Qingxi Zhu, MD
- Lianlian Wu, MD
- Yunchao Deng, MD
- Jun Zhang, MD
- Wei Tan, MD
- Chao Li, MD
- Chenxia Zhang, MA
- Rongrong Gong, MA
- Hongliu Du, MD
- Jie Zhou, MD
- Prateek Sharma, ProfMD
- Honggang Yu, ProfMD
DOIAbstract
Summary: Background: Inadequate bowel preparation is associated with a decrease in adenoma detection rate (ADR). A deep learning-based bowel preparation assessment system based on the Boston bowel preparation scale (BBPS) has been previously established to calculate the automatic BBPS (e-BBPS) score (ranging 0–20). The aims of this study were to investigate whether there was a statistically inverse relationship between the e-BBPS score and the ADR, and to determine the threshold of e-BBPS score for adequate bowel preparation in colonoscopy screening. Methods: In this prospective, observational study, we trained and internally validated the e-BBPS system using retrospective colonoscopy images and videos from the Endoscopy Center of Wuhan Un...
Add to ORKG