Correlation of the detection rate of upper GI cancer with artificial intelligence score: results from a multicenter trial (with video).

BACKGROUND AND AIMS: The quality of EGD is a prerequisite for a high detection rate of upper GI lesions, especially early gastric cancer. Our previous study showed that an artificial intelligence system, named intelligent detection endoscopic assistant (IDEA), could help to monitor blind spots and provide an operation score during EGD. Here, we verified the effectiveness of IDEA to help evaluate the quality of EGD in a large-scale multicenter trial. METHODS: Patients undergoing EGD in 12 hospitals were consecutively enrolled. All hospitals were equipped with IDEA developed using deep convolutional neural networks and long short-term memory. Patients were examined by EGD, and the results were recorded by IDEA. The primary outcome was the detection rate of upper GI cancer. Secondary outcomes were part scores, total scores, and endoscopic procedure time, which were analyzed by IDEA. RESULTS: A total of 17,787 patients were recruited. The total detection rate of cancer-positive cases was 1.50%, ranging from .60% to 3.94% in each hospital. The total detection rate of early cancer-positive cases was .36%, ranging from .00% to 1.58% in each hospital. The average total score analyzed by IDEA ranged from 64.87 ± 16.87 to 83.50 ± 9.57 in each hospital. The cancer detection rate in each hospital was positively correlated with total score (r = .775, P = .003). Similarly, the early cancer detection rate was positively correlated with total score (r = .756, P = .004). CONCLUSIONS: This multicenter trial confirmed that the quality of the EGD result is positively correlated with the detection rate of cancer, which can be monitored by IDEA. (Clinical trial registration number: ChiCTR2000029001.).

Seven-day triple therapy is a better choice for Helicobacter pylori eradication in regions with low antibiotic resistance.

AIM: To investigate whether 7-d triple therapies are still valid in populations with low levels of resistance. METHODS: A total of 1106 Helicobacter pylori (H. pylori)-positive patients were divided into three groups, each of which received one type of 7-d triple therapy. Therapeutic outcomes of the patients were assessed by the (13)C-urea breath test at 8 wk after treatment. The susceptibility of H. pylori to antibiotics was determined by an agar-dilution method. Data analysis was performed by χ(2) tests. RESULTS: The eradication rates in groups A, B and C were 90.71% (332/366), 90.46% (313/346) and 90.87% (189/208), respectively (P = 0.986). The resistance rates were 8.91% for clarithromycin, 14.78% for levofloxacin and 0% for amoxicillin. The eradication rate was significantly different between clarithromycin- and levofloxacin-resistant patients (P < 0.05) in group A. Patients whose treatment failed in group A also had a higher clarithromycin resistance rate than did successive patients (P = 0.034). However, levofloxacin resistance had no obvious influence on the eradication rate. Furthermore, three main antibiotics (clarithromycin, levofloxacin and amoxicillin) had lower DID (defined daily dose per 1000 inhabitants per day) in this city. CONCLUSION: Clarithromycin resistance is the main reason for the failure of 7-d triple therapy. In populations with low levels of resistance, a 7-d triple therapy is a viable choice. The choice of therapy should not be influenced by conditions in high antibiotic resistance regions.