Efficacy of a real-time intelligent quality-control system for the detection of early upper gastrointestinal neoplasms: a multicentre, single-blinded, randomised controlled trialResearch in context

• Published in: EClinicalMedicine Vol. 75; p. 102803
• Main Authors: Ruchen Zhou, Jing Liu, Chenchen Zhang, Yusha Zhao, Jingran Su, Qiong Niu, Chengxia Liu, Zhuang Guo, Zhenqin Cui, Xiaoqin Zhong, Weidong Zhao, Jing Li, Xiaodong Zhang, Hongyan Wang, Shidong Sun, Ruiguang Ma, Xinyu Chen, Xinyan Xu, Yiqing Zhu, Zhen Li, Xiuli Zuo, Yanqing Li
• Format: Journal Article
• Language: English
• Published: Elsevier 01.09.2024
• Subjects: Artificial intelligence; Early gastric cancer; Gastrointestinal neoplasms; Oesophagogastroduodenoscopy; Quality control
• ISSN: 2589-5370

Background: Oesophagogastroduodenoscopy (OGD) quality and identification of the early upper gastrointestinal (UGI) neoplasm play an important role in detecting the UGI neoplasm. However, the optimal method for quality control in daily OGD procedures is currently lacking. We aimed to evaluate the efficacy of a real-time intelligent quality-control system (IQCS), which combines OGD quality control with lesion detection of early UGI neoplasms. Methods: We performed a multicentre, single-blinded, randomised controlled trial at 6 hospitals in China. Patients aged 40–80 years old who underwent painless OGD were screened for enrolment in this study. Patients with a history of advanced UGI cancer, stenosis, or obstruction in UGI tract were excluded. Eligible subjects were randomly assigned (1:1) to either the routine or IQCS group to undergo standard OGD examination and OGD examination aided by IQCS, respectively. Patients were masked to the randomisation status. The primary outcome was the detection of early UGI neoplasms. All analyses were done on a per-protocol basis. This trial is registered with ClinicalTrials.gov, NCT04720924. Findings: Between January 16, 2021 and December 23, 2022, 1840 patients were randomised (IQCS group: 919, routine group: 921). The full analysis set consisted of 914 in the IQCS group and 915 in the routine group. The early UGI neoplasms detection rate in the IQCS group (6.1%, 56/914) was significantly higher than in the routine group (2.3%, 21/915; P = 0.0001). The IQCS group had fewer blind spots (2.3 vs. 6.2, P < 0.0001). The IQCS group had higher stomach cleanliness on cardia or fundus (99.5% vs. 87.9%, P < 0.0001), body (98.9% vs. 88.0%, P < 0.0001), angulus (99.8% vs. 88.4%, P < 0.0001) and antrum or pylorus (100.0% vs. 87.4%, P < 0.0001). The inspection time (576.2 vs. 574.5s, P = 0.91) and biopsy rate (57.2% vs. 56.6%, P = 0.83) were not different between the groups. The early UGI neoplasms detection rate in the IQCS group increased in both non-academic centres (RR = 3.319, 95% CI 1.277–9.176; P = 0.0094) and academic centres (RR = 2.416, 95% CI 1.301–4.568; P = 0.0034). The same improvements were observed for both less-experienced endoscopists (RR = 2.650, 95% CI 1.330–5.410; P = 0.0034) and experienced endoscopists (RR = 2.710, 95% CI 1.226–6.205; P = 0.010). No adverse events or serious adverse events were reported in the two groups. Interpretation: The IQCS improved the OGD quality and increased early UGI neoplasm detection in different hospital types and endoscopist experiences. IQCS could play an important role in primary basic hospitals and non-expert endoscopists to improve the diagnostic accuracy of early UGI neoplasms. The effectiveness of IQCS in real-world clinical settings needs a larger population validation. Funding: Key R&D Program of Shandong Province, China (Major Scientific and Technological Innovation Project), National Natural Science Foundation of China, the Taishan Scholars Program of Shandong Province, the National Key Research and Development Program of China, and the Shandong Provincial Natural Science Foundation.