Obesity in adult patients with inflammatory bowel disease: Clinical features and impact on disability. A cross-sectional survey from the GETAID.

BACKGROUND: In recent years, an increasing prevalence of obesity in inflammatory bowel disease (IBD) has been observed. However, only a few studies have focused on the impact of overweight and obesity on IBD-related disability. AIMS: To identify the factors associated with obese and overweight patients with IBD, including IBD-related disability. PATIENTS AND METHODS: In this cross-sectional study, we included 1704 consecutive patients with IBD in 42 centres affiliated with the Groupe d'Etude Therapeutique des Affections Inflammatoires du tube Digestif (GETAID) using a 4-page questionnaire. Factors associated with obesity and overweight were assessed using univariate and multivariate analyses (odds ratios (ORs) are provided with 95% confidence intervals). RESULTS: The prevalence rates of overweight and obesity were 24.1% and 12.2%, respectively. Multivariable analyses were stratified by age, sex, type of IBD, clinical remission and age at diagnosis of IBD. Overweight was significantly associated with male sex (OR = 0.52, 95% CI [0.39-0.68], p < 0.001), age (OR = 1.02, 95% CI [1.01-1.03], p < 0.001) and body image subscore (OR = 1.15, 95% CI [1.10-1.20], p < 0.001) (Table 2). Obesity was significantly associated with age (OR = 1.03, 95% CI [1.02-1.04], p < 0.001), joint pain subscore (OR = 1.08, 95% CI [1.02-1.14], p < 0.001) and body image subscore (OR = 1.25, 95% CI [1.19-1.32], p < 0.001) (Table 3). CONCLUSION: The increasing prevalence of overweight and obesity in patients with IBD is associated with age and poorer body image. A holistic approach to IBD patient care should be encouraged to improve IBD-related disability and to prevent rheumatological and cardiovascular complications.

Multi-expert annotation of Crohn's disease images of the small bowel for automatic detection using a convolutional recurrent attention neural network.

Background and study aims Computer-aided diagnostic tools using deep neural networks are efficient for detection of lesions in endoscopy but require a huge number of images. The impact of the quality of annotation has not been tested yet. Here we describe a multi-expert annotated dataset of images extracted from capsules from Crohn's disease patients and the impact of the quality of annotations on the accuracy of a recurrent attention neural network. Methods Images of capsule were annotated by a reader first and then reviewed by three experts in inflammatory bowel disease. Concordance analysis between experts was evaluated by Fleiss' kappa and all the discordant images were, again, read by all the endoscopists to obtain a consensus annotation. A recurrent attention neural network developed for the study was tested before and after the consensus annotation. Available neural networks (ResNet and VGGNet) were also tested under the same conditions. Results The final dataset included 3498 images with 2124 non-pathological (60.7 %), 1360 pathological (38.9 %), and 14 (0.4 %) inconclusive. Agreement of the experts was good for distinguishing pathological and non-pathological images with a kappa of 0.79 ( P  < 0.0001). The accuracy of our classifier and the available neural networks increased after the consensus annotation with a precision of 93.7 %, sensitivity of 93 %, and specificity of 95 %. Conclusions The accuracy of the neural network increased with improved annotations, suggesting that the number of images needed for the development of these systems could be diminished using a well-designed dataset.