In early gastric cancer (EGC), tumor invasion depth is an important factor for determining the treatment method. However, as endoscopic ultrasonography has limitations when measuring the exact depth in a clinical setting as endoscopists often depend on gross findings and personal experience. The present study aimed to develop a model optimized for EGC detection and depth prediction, and we investigated factors affecting artificial intelligence (AI) diagnosis. We employed a visual geometry group(VGG)-16 model for the classification of endoscopic images as EGC (T1a or T1b) or non-EGC. To induce the model to activate EGC regions during training, we proposed a novel loss function that simultaneously measured classification and localization errors. We experimented with 11,539 endoscopic images (896 T1a-EGC, 809 T1b-EGC, and 9834 non-EGC). The areas under the curves of receiver operating characteristic curves for EGC detection and depth prediction were 0.981 and 0.851, respectively. Among the factors affecting AI prediction of tumor depth, only histologic differentiation was significantly associated, where undifferentiated-type histology exhibited a lower AI accuracy. Thus, the lesion-based model is an appropriate training method for AI in EGC. However, further improvements and validation are required, especially for undifferentiated-type histology.

Probiotics confer health benefits to the host. However, its clinical effect on irritable bowel syndrome (IBS) is controversial. This study was aimed to evaluate the effects of Saccharomyces boulardii on quality of life (QOL) and symptoms in patients with diarrhea-predominant IBS or mixed-type IBS. Sixty-seven patients with IBS were randomized either to receive S. boulardii at 2×10 live cells as a daily dose (n=34), or placebo (n=33) for 4 weeks. IBS-QOL was assessed at the beginning and end of the treatment phase. IBS-related symptoms, bowel movement frequency, and stool consistency were recorded on a daily basis and assessed each week. The overall improvement in IBS-QOL was higher in S. boulardii group than placebo (15.4% vs 7.0%; P<0.05). All eight domains of IBS-QOL were significantly improved in S. boulardii group; however, placebo group only showed improvements in dysphoria and health worry. Composite scores for IBS symptoms were significantly reduced in both groups to a similar extent. Bowel frequency and stool consistency did not change in either group. S. boulardii improved IBS-QOL better than placebo but was not superior for individual symptoms in patients with diarrhea-predominant IBS or mixed-type IBS.

Gastro‐oesophageal reflux disease (GORD) occurs more frequently in Europe and North America than in Asia but its prevalence is now increasing in many Asian countries. Many reasons have been given for the lower prevalence of GORD in Asia. Low dietary fat and genetically determined factors, such as body mass index and maximal acid output, may be important. Other dietary factors appear to be less relevant. Increased intake of carbonated drinks or aggravating medicines may influence the increasing rates of GORD in some Asian countries but no strong evidence links other factors, such as the age of the population, smoking or alcohol consumption, to GORD. The management of GORD in Asia is similar to that in Europe and North America but the lower incidence of severe oesophagitis in Asia may alter the approach slightly. Also, because Asians tend to develop stomach cancer at an earlier age, endoscopy is used routinely at an earlier stage of investigation. Gastro‐oesophageal reflux disease is essentially a motility disorder, so short‐term management of the disease can usually be achieved using prokinetic agents (or histamine (H₂)‐receptor antagonists). More severe and recurrent GORD may require proton pump inhibitors (PPI) or a combination of prokinetic agents and PPI. The choice of long‐term treatment may be influenced by the relative costs of prokinetic agents and PPI.© 2000 Blackwell Science Asia Pty Ltd