Computational Learning of microRNA-Based Prediction of Pouchitis Outcome After Restorative Proctocolectomy in Patients With Ulcerative Colitis

AGA Clinical Practice Guideline on the Management of Pouchitis and Inflammatory Pouch Disorders

BACKGROUND & AIMS

Pouchitis is the most common complication after restorative proctocolectomy with ileal pouch-anal anastomosis for ulcerative colitis. This American Gastroenterological Association (AGA) guideline is intended to support practitioners in the management of pouchitis and inflammatory pouch disorders.

METHODS

A multidisciplinary panel of content experts and guideline methodologists used the Grading of Recommendations Assessment, Development and Evaluation framework to prioritize clinical questions, identify patient-centered outcomes, conduct an evidence synthesis, and develop recommendations for the prevention and treatment of pouchitis, Crohn's-like disease of the pouch, and cuffitis.

RESULTS

The AGA guideline panel made 9 conditional recommendations. In patients with ulcerative colitis who have undergone ileal pouch-anal anastomosis and experience intermittent symptoms of pouchitis, the AGA suggests using antibiotics for the treatment of pouchitis. In patients who experience recurrent episodes of pouchitis that respond to antibiotics, the AGA suggests using probiotics for the prevention of recurrent pouchitis. In patients who experience recurrent pouchitis that responds to antibiotics but relapses shortly after stopping antibiotics (also known as "chronic antibiotic-dependent pouchitis"), the AGA suggests using chronic antibiotic therapy to prevent recurrent pouchitis; however, in patients who are intolerant to antibiotics or who are concerned about the risks of long-term antibiotic therapy, the AGA suggests using advanced immunosuppressive therapies (eg, biologics and/or oral small molecule drugs) approved for treatment of inflammatory bowel disease. In patients who experience recurrent pouchitis with inadequate response to antibiotics (also known as "chronic antibiotic-refractory pouchitis"), the AGA suggests using advanced immunosuppressive therapies; corticosteroids can also be considered in these patients. In patients who develop symptoms due to Crohn's-like disease of the pouch, the AGA suggests using corticosteroids and advanced immunosuppressive therapies. In patients who experience symptoms due to cuffitis, the AGA suggests using therapies that have been approved for the treatment of ulcerative colitis, starting with topical mesalamine or topical corticosteroids. The panel also proposed key implementation considerations for optimal management of pouchitis and Crohn's-like disease of the pouch and identified several knowledge gaps and areas for future research.

CONCLUSIONS

This guideline provides a comprehensive, patient-centered approach to the management of patients with pouchitis and other inflammatory conditions of the pouch.

Shedding New Light on High-Risk Phenotypes for Pouchitis

Identifying those patients at the greatest risk for pouchitis at the time of ileal pouch-anal anastomosis for ulcerative colitis remains a challenge. We discuss the importance of this topic by reviewing recent data regarding the impact of acute severe ulcerative colitis on risk of pouchitis and the implications for future clinical decisions and studies of risk stratification.

Personalized risk predictor for acute cellular rejection in lung transplant using soluble CD31

We evaluated the contribution of artificial intelligence in predicting the risk of acute cellular rejection (ACR) using early plasma levels of soluble CD31 (sCD31) in combination with recipient haematosis, which was measured by the ratio of arterial oxygen partial pressure to fractional oxygen inspired (PaO₂/FiO₂) and respiratory SOFA (Sequential Organ Failure Assessment) within 3 days of lung transplantation (LTx). CD31 is expressed on endothelial cells, leukocytes and platelets and acts as a "peace-maker" at the blood/vessel interface. Upon nonspecific activation, CD31 can be cleaved, released, and detected in the plasma (sCD31). The study included 40 lung transplant recipients, seven (17.5%) of whom experienced ACR. We modelled the plasma levels of sCD31 as a nonlinear dependent variable of the PaO₂/FiO₂ and respiratory SOFA over time using multivariate and multimodal models. A deep convolutional network classified the time series models of each individual associated with the risk of ACR to each individual in the cohort.

Repairing the human with artificial intelligence in oncology

Artificial intelligence is a groundbreaking tool to learn and analyse higher features extracted from any dataset at large scale. This ability makes it ideal to facing any complex problem that may generally arise in the biomedical domain or oncology in particular. In this work, we envisage to provide a global vision of this mathematical discipline outgrowth by linking some other related subdomains such as transfer, reinforcement or federated learning. Complementary, we also introduce the recently popular method of topological data analysis that improves the performance of learning models.

Improving prediction of disease outcome for inflammatory bowel disease: progress through systems medicine

Introduction: Inflammatory bowel diseases (IBDs) are lifelong conditions causing relapsing inflammation of the intestine. In the absence of a cure, clinical management of IBDs is extremely challenging since they present with a wide range of phenotypes and disease behaviors. Hence, there is an urgent need for markers that could guide physicians in making the right choice of the rapidly growing treatment options toward a personalized care that could improve the overall outcome.Areas covered: In this review, the authors summarize existing biomarkers in IBD, discuss the challenges with the development of prognostic biomarkers and propose alternative options such as focusing on the prediction of the response to individual treatments, i.e. predictive biomarkers. The problems related to developing disease prognostic and predictive biomarkers in the field of IBDs are discussed including the difficulties in dealing with phenotypic heterogeneity particularly when performing studies in a real-life setting. The authors reviewed literature from PubMed.Expert opinion: Systems biology provides potential solutions to this problem by offering an unbiased, holistic approach to adjusting for variation in larger datasets thereby increasing the chances of identifying true associations between molecular profiles and clinical phenotypes.