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.

Background and Aims: Inflammatory bowel disease (IBD) may be associated with anxiety and depression. The aim of this study was to evaluate the incidence of anxiety and depression in patients with IBD compared to the general population. Methods: A nationwide population-based cohort study was conducted using claims data from the National Healthcare Insurance service in Korea. We compared the incidence of anxiety and depression between 15,569 IBD patients and 46,707 non-IBD controls, age and sex matched at a ratio of 1:3. Results: During a mean follow-up of six years, IBD patients experienced significantly more anxiety (12.2% vs. 8.7%; p < 0.001) and depression (8.0% vs. 4.7%; p < 0.001) compared to controls. The curves showing cumulative incidences of anxiety and depression showed a steep rise within one year following a diagnosis of IBD, leading to lines with a constant slope. The hazard ratio (HR) for new onset anxiety following a diagnosis of Crohn’s disease (CD) and ulcerative colitis (UC) was 1.63 and 1.60, respectively, compared to controls (p < 0.001). Compared to controls, the HR for developing depression after a diagnosis of CD and UC was 2.09 and 2.00, respectively (p < 0.001). The risks of anxiety and depression in patients with IBD were higher compared to controls, except in those with diabetes mellitus, hypertension, and dyslipidemia, or who required immunomodulators and biologics within one year of the IBD diagnosis. Conclusions: The risk of anxiety and depression increased after a diagnosis of IBD compared to the general population.

The association of diabetes with inflammatory bowel disease (IBD) remains unclear. The risk of diabetes in patients with IBD compared with non-IBD controls was investigated. Using the National Health Insurance database of South Korea, 8070 patients with IBD based on the International Classification of Disease 10th revision (ICD-10) codes and rare intractable disease codes for Crohn’s disease (CD) and ulcerative colitis (UC) were compared with 40,350 non-IBD individuals (2010–2014). Newly diagnosed diabetes identified using ICD-10 codes and the prescription of anti-diabetic medication by the end of the follow-up period (2016) was investigated. During a mean follow-up of 5.1 years, the incidence of diabetes in patients with IBD was significantly higher compared with controls after adjusting for serum glucose levels and steroid use (23.19 vs. 22.02 per 1000 person-years; hazard ratio (HR), 1.135; 95% confidence interval (CI), 1.048–1.228). The risk of diabetes was significantly higher in patients with CD (HR, 1.677; 95% CI, 1.408–1.997), but not in UC (HR, 1.061; 95% CI, 0.973–1.156). The effect of IBD on the development of diabetes was significantly more prominent in younger patients (p < 0.001). Patients with CD are at a higher risk of diabetes. Regular monitoring for diabetes is recommended, even in younger CD patients who do not use steroid medication.

Background and Aims: It is not known whether inflammatory bowel disease (IBD) enhances the risk of Parkinson’s disease (PD) or whether PD diagnosis is the result of increased health care use. We determined the risk of developing PD among patients with IBD in terms of health care and medication use. Methods: A nationwide population-based study was conducted using claims data from the Korean National Health care Insurance service. From 2010 to 2013, patients with Crohn’s disease (CD) and ulcerative colitis (UC) were identified through both International Classification of Disease, Tenth Revision (ICD-10) and national rare intractable disease (RID) registration program codes. We compared 38,861 IBD patients with age and sex-matched non-IBD individuals at a ratio of 1:3. Patients with newly diagnosed PD were identified through both ICD-10 and RID codes. Results: The incidence of PD among patients with IBD was 49 per 100,000 person-years. The risk of developing PD in patients with IBD was significantly higher than controls even after adjustment for health care use (adjusted hazard ratio (aHR), 1.87; P < 0.001). Compared to controls, the risk of PD was significantly higher in patients with CD (aHR, 2.23; P = 0.023) and UC (aHR, 1.85; P < 0.001). Corticosteroid use showed a preventive effect on developing PD in patients with CD (aHR 0.08; P < 0.001), but not UC (aHR, 0.75; P = 0.213). Among 2110 patients receiving anti-tumor necrosis factor (anti-TNF), none of the treated patients experienced PD during 9950 person-years. Conclusion: Patients with IBD are at an increased risk of PD, regardless of health care use. Corticosteroid and anti-TNF use may prevent PD in patients with IBD.

Increased end-stage renal disease risk in patients with inflammatory bowel disease: A nationwide population-based study