Artificial intelligence (AI) using deep-learning (DL) has emerged as a breakthrough computer technology. By the era of big data, the accumulation of an enormous number of digital images and medical records drove the need for the utilization of AI to efficiently deal with these data, which have become fundamental resources for a machine to learn by itself. Among several DL models, the convolutional neural network showed outstanding performance in image analysis. In the field of gastroenterology, physicians handle large amounts of clinical data and various kinds of image devices such as endoscopy and ultrasound. AI has been applied in gastroenterology in terms of diagnosis, prognosis, and image analysis. However, potential inherent selection bias cannot be excluded in the form of retrospective study. Because overfitting and spectrum bias (class imbalance) have the possibility of overestimating the accuracy, external validation using unused datasets for model development, collected in a way that minimizes the spectrum bias, is mandatory. For robust verification, prospective studies with adequate inclusion/exclusion criteria, which represent the target populations, are needed. DL has its own lack of interpretability. Because interpretability is important in that it can provide safety measures, help to detect bias, and create social acceptance, further investigations should be performed.

Background Visual inspection, lesion detection, and differentiation between malignant and benign features are key aspects of an endoscopist’s role. The use of machine learning for the recognition and differentiation of images has been increasingly adopted in clinical practice. This study aimed to establish convolutional neural network (CNN) models to automatically classify gastric neoplasms based on endoscopic images. Methods Endoscopic white-light images of pathologically confirmed gastric lesions were collected and classified into five categories: advanced gastric cancer, early gastric cancer, high grade dysplasia, low grade dysplasia, and non-neoplasm. Three pretrained CNN models were fine-tuned using a training dataset. The classifying performance of the models was evaluated using a test dataset and a prospective validation dataset. Results A total of 5017 images were collected from 1269 patients, among which 812 images from 212 patients were used as the test dataset. An additional 200 images from 200 patients were collected and used for prospective validation. For the five-category classification, the weighted average accuracy of the Inception-Resnet-v2 model reached 84.6 %. The mean area under the curve (AUC) of the model for differentiating gastric cancer and neoplasm was 0.877 and 0.927, respectively. In prospective validation, the Inception-Resnet-v2 model showed lower performance compared with the endoscopist with the best performance (five-category accuracy 76.4 % vs. 87.6 %; cancer 76.0 % vs. 97.5 %; neoplasm 73.5 % vs. 96.5 %; P < 0.001). However, there was no statistical difference between the Inception-Resnet-v2 model and the endoscopist with the worst performance in the differentiation of gastric cancer (accuracy 76.0 % vs. 82.0 %) and neoplasm (AUC 0.776 vs. 0.865). Conclusion The evaluated deep-learning models have the potential for clinical application in classifying gastric cancer or neoplasm on endoscopic white-light images.

The prevalence of osteoporosis and sarcopenia is significantly higher in patients with liver disease than in those without liver disease and osteoporosis and sarcopenia negatively influence morbidity and mortality in liver disease, yet these musculoskeletal disorders are frequently overlooked in clinical practice for patients with chronic liver disease. The objective of this review is to provide a comprehensive understanding of the molecular mechanisms of musculoskeletal disorders accompanying the pathogenesis of liver disease. The increased bone resorption through the receptor activator of nuclear factor kappa (RANK)-RANK ligand (RANKL)-osteoprotegerin (OPG) system and upregulation of inflammatory cytokines and decreased bone formation through increased bilirubin and sclerostin and lower insulin-like growth factor-1 are important mechanisms for osteoporosis in patients with liver disease. Sarcopenia is associated with insulin resistance and obesity in non-alcoholic fatty liver disease, whereas hyperammonemia, low amount of branched chain amino acids, and hypogonadism contributes to sarcopenia in liver cirrhosis. The bidirectional crosstalk between muscle and bone through myostatin, irisin, β-aminoisobutyric acid (BAIBA), osteocalcin, as well as the activation of the RANK and the Wnt/β-catenin pathways are associated with osteosarcopenia. The increased understandings for these musculoskeletal disorders would be contributes to the development of effective therapies targeting the pathophysiological mechanism involved.

Controversies persist regarding the effect of prokinetics for the treatment of functional dyspepsia (FD). This study aimed to assess the comparative efficacy of prokinetic agents for the treatment of FD. Randomized controlled trials (RCTs) of prokinetics for the treatment of FD were identified from core databases. Symptom response rates were extracted and analyzed using odds ratios (ORs). A Bayesian network meta-analysis was performed using the Markov chain Monte Carlo method in WinBUGS and NetMetaXL. In total, 25 RCTs, which included 4473 patients with FD who were treated with 6 different prokinetics or placebo, were identified and analyzed. Metoclopramide showed the best surface under the cumulative ranking curve (SUCRA) probability (92.5%), followed by trimebutine (74.5%) and mosapride (63.3%). However, the therapeutic efficacy of metoclopramide was not significantly different from that of trimebutine (OR:1.32, 95% credible interval: 0.27–6.06), mosapride (OR: 1.99, 95% credible interval: 0.87–4.72), or domperidone (OR: 2.04, 95% credible interval: 0.92–4.60). Metoclopramide showed better efficacy than itopride (OR: 2.79, 95% credible interval: 1.29–6.21) and acotiamide (OR: 3.07, 95% credible interval: 1.43–6.75). Domperidone (SUCRA probability 62.9%) showed better efficacy than itopride (OR: 1.37, 95% credible interval: 1.07–1.77) and acotiamide (OR: 1.51, 95% credible interval: 1.04–2.18). Metoclopramide, trimebutine, mosapride, and domperidone showed better efficacy for the treatment of FD than itopride or acotiamide. Considering the adverse events related to metoclopramide or domperidone, the short-term use of these agents or the alternative use of trimebutine or mosapride could be recommended for the symptomatic relief of FD.

Capsule endoscopy has revolutionized the management of small-bowel diseases owing to its convenience and noninvasiveness. Capsule endoscopy is a common method for the evaluation of obscure gastrointestinal bleeding, Crohn's disease, small-bowel tumors, and polyposis syndrome. However, the laborious reading process, oversight of small-bowel lesions, and lack of locomotion are major obstacles to expanding its application. Along with recent advances in artificial intelligence, several studies have reported the promising performance of convolutional neural network systems for the diagnosis of various small-bowel lesions including erosion/ulcers, angioectasias, polyps, and bleeding lesions, which have reduced the time needed for capsule endoscopy interpretation. Furthermore, colon capsule endoscopy and capsule endoscopy locomotion driven by magnetic force have been investigated for clinical application, and various capsule endoscopy prototypes for active locomotion, biopsy, or therapeutic approaches have been introduced. In this review, we will discuss the recent advancements in artificial intelligence in the field of capsule endoscopy, as well as studies on other technological improvements in capsule endoscopy.

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.