Paediatric inflammatory bowel disease (PIBD), comprising Crohn’s disease (CD), ulcerative colitis (UC) and inflammatory bowel disease unclassified (IBDU) is a complex and multifactorial condition with increasing incidence. An accurate diagnosis of PIBD is necessary for a prompt and effective treatment. This study utilises machine learning (ML) to classify disease using endoscopic and histological data for 287 children diagnosed with PIBD. Data were used to develop, train, test and validate a ML model to classify disease subtype. Unsupervised models revealed overlap of CD/UC with broad clustering but no clear subtype delineation, whereas hierarchical clustering identified four novel subgroups characterised by differing colonic involvement. Three supervised ML models were developed utilising endoscopic data only, histological only and combined endoscopic/histological data yielding classification accuracy of 71.0%, 76.9% and 82.7% respectively. The optimal combined model was tested on a statistically independent cohort of 48 PIBD patients from the same clinic, accurately classifying 83.3% of patients. This study employs mathematical modelling of endoscopic and histological data to aid diagnostic accuracy. While unsupervised modelling categorises patients into four subgroups, supervised approaches confirm the need of both endoscopic and histological evidence for an accurate diagnosis. Overall, this paper provides a blueprint for ML use with clinical data.

Exclusive enteral nutrition (EEN) is the first line therapy for paediatric Crohn's disease, providing a complete nutritional feed whilst simultaneously inducing remission in up to 80% of cases. The effect of EEN on systemic/local intestinal immune function and subsequent inflammation (including barrier permeability, direct anti-inflammatory effects and cytokine signalling pathways), alongside changes in the microbiome (specific species and broad taxonomic shifts, functional changes) are becoming clearer, however the exact mechanism for induction of remission in Crohn's disease remains uncertain. The evidence of efficacy in paediatric Crohn's disease is strong, with selected adult populations also benefiting from EEN. However despite recommendations from all major societies (ECCO, ESPGHAN, NASPGHAN and ESPEN) first-line use of EEN is varied and Europe/Australasia/Canada show significantly more routine use than other parts of North America. Growth and nutritional status are significantly improved with EEN compared to corticosteroids but long-term outcomes are sparse. This review discusses the evidence underlying the use of EEN, highlighting the mechanisms thought to underlie how EEN induces remission in Crohn's disease, when and how to use EEN, including practical issues in both paediatric and adult practice (formulation, compliance, volumes and administration), and summarises the ongoing research priorities.

Young people must be kept at the center of interactions in recognition of their stated needs of engagement, of individually tailored information and support unproxied by parents/family. Age-appropriate information and support services that help young people deal with the impact of cancer on daily life and life after cancer must be made available. If we are to develop services that meet need, patient experience surveys must be influenced by patient involvement. Young people can be successfully involved in planning research relevant to their experience.