Kim TH, et al. J Gastric Cancer. 2023 Jan;23:e11. https://doi.org/10.5230/jgc.2023.23.e11

Proton pump inhibitor (PPI)-based triple therapy consisting of PPI, amoxicillin, and clarithromycin, is the recommended first-line treatment for Helicobacter pylori infection. However, the eradication rate of triple therapy has declined over the past few decades. We analyzed the eradication rate and adverse events of triple therapy to evaluate current practices in Korea. A comprehensive literature search was performed up to August 2013 of 104 relevant studies comprising 42,124 patients. The overall eradication rate was 74.6% (95% confidence interval [CI], 72.1%-77.2%) by intention-to-treat analysis and 82.0% (95% CI, 80.8%-83.2%) by per-protocol analysis. The eradication rate decreased significantly from 1998 to 2013 (P < 0.001 for both intention-to-treat and per-protocol analyses). Adverse events were reported in 41 studies with 8,018 subjects with an overall incidence rate of 20.4% (95% CI, 19.6%-21.3%). The available data suggest that the effectiveness of standard triple therapy for H. pylori eradication has decreased to an unacceptable level. A novel therapeutic strategy is warranted to improve the effectiveness of first-line treatment for H. pylori infection in Korea.

Background: Classification of colorectal neoplasms during colonoscopic examination is important to avoid unnecessary endoscopic biopsy or resection. This study aimed to develop and validate deep learning models that automatically classify colorectal lesions histologically on white-light colonoscopy images. Methods: White-light colonoscopy images of colorectal lesions exhibiting pathological results were collected and classified into seven categories: stages T1-4 colorectal cancer (CRC), high-grade dysplasia (HGD), tubular adenoma (TA), and non-neoplasms. The images were then re-classified into four categories including advanced CRC, early CRC/HGD, TA, and non-neoplasms. Two convolutional neural network models were trained, and the performances were evaluated in an internal test dataset and an external validation dataset. Results: In total, 3828 images were collected from 1339 patients. The mean accuracies of ResNet-152 model for the seven-category and four-category classification were 60.2% and 67.3% in the internal test dataset, and 74.7% and 79.2% in the external validation dataset, respectively, including 240 images. In the external validation, ResNet-152 outperformed two endoscopists for four-category classification, and showed a higher mean area under the curve (AUC) for detecting TA+ lesions (0.818) compared to the worst-performing endoscopist. The mean AUC for detecting HGD+ lesions reached 0.876 by Inception-ResNet-v2. Conclusions: A deep learning model presented promising performance in classifying colorectal lesions on white-light colonoscopy images; this model could help endoscopists build optimal treatment strategies.

To compare the efficacy and safety between modified quadruple- and bismuth-containing quadruple therapy as first-line eradication regimen for Helicobacter pylori infection.This study was a multicen...

Background: In a previous study, we examined the use of deep learning models to classify the invasion depth (mucosa-confined versus submucosa-invaded) of gastric neoplasms using endoscopic images. The external test accuracy reached 77.3%. However, model establishment is labor intense, requiring high performance. Automated deep learning (AutoDL) models, which enable fast searching of optimal neural architectures and hyperparameters without complex coding, have been developed. Objective: The objective of this study was to establish AutoDL models to classify the invasion depth of gastric neoplasms. Additionally, endoscopist–artificial intelligence interactions were explored. Methods: The same 2899 endoscopic images that were employed to establish the previous model were used. A prospective multicenter validation using 206 and 1597 novel images was conducted. The primary outcome was external test accuracy. Neuro-T, Create ML Image Classifier, and AutoML Vision were used in establishing the models. Three doctors with different levels of endoscopy expertise were asked to classify the invasion depth of gastric neoplasms for each image without AutoDL support, with faulty AutoDL support, and with best performance AutoDL support in sequence. Results: The Neuro-T–based model reached 89.3% (95% CI 85.1%-93.5%) external test accuracy. For the model establishment time, Create ML Image Classifier showed the fastest time of 13 minutes while reaching 82.0% (95% CI 76.8%-87.2%) external test accuracy. While the expert endoscopist's decisions were not influenced by AutoDL, the faulty AutoDL misled the endoscopy trainee and the general physician. However, this was corrected by the support of the best performance AutoDL model. The trainee gained the most benefit from the AutoDL support. Conclusions: AutoDL is deemed useful for the on-site establishment of customized deep learning models. An inexperienced endoscopist with at least a certain level of expertise can benefit from AutoDL support.