Background/Aims: Intestinal Behçet disease is typically associated with ileocecal punched-out ulcers and significant morbidity and mortality. Intestinal ultrasound is a noninvasive imaging technique for disease monitoring. However, no previous reports have compared intestinal ultrasound with endoscopic ulcer activity or histopathological findings for intestinal Behçet disease. We evaluated the usefulness of intestinal ultrasound for assessing the activity of ileocecal ulcers in intestinal Behçet disease. Methods: We retrospectively compared intestinal ultrasound findings with 73 corresponding endoscopic images and 6 resected specimens. The intestinal ultrasound findings were assessed for 7 parameters (bowel wall thickness, vascularity [evaluated using the modified Limberg score with color Doppler], bowel wall stratification, white-plaque sign [strong hyperechogenic lines or spots], mesenteric lymphadenopathy, extramural phlegmons, and fistulas), and endoscopic ulcer activity was classified into active, healing, and scar stages. Histopathological findings were evaluated by consensus among experienced pathologists. Results: Bowel wall thickness (P< 0.001), vascularity (P< 0.001), loss of bowel wall stratification (P= 0.015), and white-plague sign (P= 0.013) were significantly exacerbated in the endoscopic active ulcer stage. Receiver operating characteristic curve analysis revealed that a bowel wall thickness of > 5.5 mm (sensitivity 89.7%, specificity 85.3%) was potentially useful for detecting active lesions. When compared with histopathological findings, an increase in bowel wall thickness reflected the ulcer marginal ridge, and the white-plaque sign reflected the ulcer bottom. Conclusions Intestinal ultrasound is useful for monitoring intestinal ulcer activity in intestinal Behçet disease.

BACKGROUND: Previous cardiovascular risk prediction models in Japan have utilized prospective cohort studies with concise data. As the health information including health check-up records and administrative claims becomes digitalized and publicly available, application of large datasets based on such real-world data can achieve prediction accuracy and support social implementation of cardiovascular disease risk prediction models in preventive and clinical practice. In this study, classical regression and machine learning methods were explored to develop ischemic heart disease (IHD) and stroke prognostic models using real-world data. METHODS: IQVIA Japan Claims Database was searched to include 691,160 individuals (predominantly corporate employees and their families working in secondary and tertiary industries) with at least one annual health check-up record during the identification period (April 2013-December 2018). The primary outcome of the study was the first recorded IHD or stroke event. Predictors were annual health check-up records at the index year-month, comprising demographic characteristics, laboratory tests, and questionnaire features. Four prediction models (Cox, Elnet-Cox, XGBoost, and Ensemble) were assessed in the present study to develop a cardiovascular disease risk prediction model for Japan. RESULTS: The analysis cohort consisted of 572,971 invididuals. All prediction models showed similarly good performance. The Harrell's C-index was close to 0.9 for all IHD models, and above 0.7 for stroke models. In IHD models, age, sex, high-density lipoprotein, low-density lipoprotein, cholesterol, and systolic blood pressure had higher importance, while in stroke models systolic blood pressure and age had higher importance. CONCLUSION Our study analyzed classical regression and machine learning algorithms to develop cardiovascular disease risk prediction models for IHD and stroke in Japan that can be applied to practical use in a large population with predictive accuracy.
Humans ; Cardiovascular Diseases/epidemiology* ; Prognosis ; Prospective Studies ; Japan/epidemiology* ; Stroke/etiology* ; Myocardial Ischemia/epidemiology* ; Risk Assessment/methods*