Prevalence of extraintestinal manifestations in ulcerative colitis and associated risk factors

Ulcerative Colitis, LAIR1 and TOX2 Expression, and Colorectal Cancer Deep Learning Image Classification Using Convolutional Neural Networks

BACKGROUND

Ulcerative colitis is a chronic inflammatory bowel disease of the colon mucosa associated with a higher risk of colorectal cancer.

OBJECTIVE

This study classified hematoxylin and eosin (H&E) histological images of ulcerative colitis, normal colon, and colorectal cancer using artificial intelligence (deep learning).

METHODS

A convolutional neural network (CNN) was designed and trained to classify the three types of diagnosis, including 35 cases of ulcerative colitis (n = 9281 patches), 21 colon control (n = 12,246), and 18 colorectal cancer (n = 63,725). The data were partitioned into training (70%) and validation sets (10%) for training the network, and a test set (20%) to test the performance on the new data. The CNNs included transfer learning from ResNet-18, and a comparison with other CNN models was performed. Explainable artificial intelligence for computer vision was used with the Grad-CAM technique, and additional LAIR1 and TOX2 immunohistochemistry was performed in ulcerative colitis to analyze the immune microenvironment.

RESULTS

Conventional clinicopathological analysis showed that steroid-requiring ulcerative colitis was characterized by higher endoscopic Baron and histologic Geboes scores and LAIR1 expression in the lamina propria, but lower TOX2 expression in isolated lymphoid follicles (all p values < 0.05) compared to mesalazine-responsive ulcerative colitis. The CNN classification accuracy was 99.1% for ulcerative colitis, 99.8% for colorectal cancer, and 99.1% for colon control. The Grad-CAM heatmap confirmed which regions of the images were the most important. The CNNs also differentiated between steroid-requiring and mesalazine-responsive ulcerative colitis based on H&E, LAIR1, and TOX2 staining. Additional classification of 10 new cases of colorectal cancer (adenocarcinoma) were correctly classified.

CONCLUSIONS

CNNs are especially suited for image classification in conditions such as ulcerative colitis and colorectal cancer; LAIR1 and TOX2 are relevant immuno-oncology markers in ulcerative colitis.

Ulcerative colitis and nephrotic syndrome: a two-sample Mendelian randomization study

To investigate the potential causal relationship between ulcerative colitis and nephrotic syndrome. We obtained the whole-genome association study data of ulcerative colitis in the European population from the GWAS database. Relevant single nucleotide polymorphisms (SNPs) were selected for analysis. We employed the inverse variance-weighted meta-analysis of multiplicative random effects models to obtain SNP-specific Wald ratio estimates, which assume horizontal pleiotropy. In addition, we performed sensitivity analyses using MR-Egger, weighted median, and IVW. Our findings suggest a strong association between ulcerative colitis and nephrotic syndrome (P < 0.05). After conducting sensitivity analyses, we found no evidence of horizontal pleiotropy or heterogeneity (P > 0.05). This study provides evidence for an association between ulcerative colitis and nephrotic syndrome, which may help us better understand the conditions of ulcerative colitis and nephropathy.

Prevalence of Extraintestinal Manifestations in Inflammatory Bowel Disease: A Systematic Review and Meta-analysis

BACKGROUND

Inflammatory bowel disease (IBD) is a multisystem disease impacting various body systems including musculoskeletal, ocular, skin, hepatobiliary, pulmonary, cardiac, and haematological systems. The extraintestinal manifestations of IBD are frequent, common in both ulcerative colitis (UC) and Crohn's disease (CD), and impact the morbidity and mortality of patients.

METHODS

The Embase, Embase classic, and PubMed databases were searched between January 1979 and December 2021. A random effects model was performed to find the pooled prevalence of joint, ocular, and skin extraintestinal manifestations of UC and CD.

RESULTS

Fifty-two studies were included that reported on 352 454 patients. The prevalence of at least 1 joint, ocular, or skin extraintestinal manifestation in all IBD, UC, and CD was 24%, 27%, and 35% respectively. The prevalence between UC and CD were similar for pyoderma gangrenosum and axial joint manifestations. Ocular manifestations were found to be more common in CD than in UC. Peripheral joint manifestations and erythema nodosum were found to be more common in CD than UC.

DISCUSSION

To our knowledge, this is the first meta-analysis that reports on the prevalence of at least 1 joint, ocular, or skin extraintestinal manifestation in IBD. Our results are largely consistent with figures and statements quoted in the literature. However, our findings are based on significantly larger cohort sizes. Thus, our results have the potential to better power studies and more accurately counsel patients.