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.
Paediatric-onset inflammatory bowel disease (IBD) is a complex and heterogenous condition. Incidence of disease in those aged <18 years has doubled over the last 25 years, with concurrent increased prevalence and no decrease in disease severity. The tools available at diagnosis for investigation have developed over the last 10 years, including better utilisation of faecal calprotectin, improved small bowel imaging and video capsule endoscopy. Alongside this, management options have increased and include biological and small molecule therapies targeting alternative pathways (such as interleukin 12/23, integrins and Janus kinase/signal transducers and activators of transcription, JAK-STAT pathways) and better understanding of therapeutic drug monitoring for more established agents, such as infliximab. Dietary manipulation remains an interesting but contentious topic.This review summarises some of the recent developments in the diagnosis, investigation and management of IBD in children and young people. IBD is increasingly recognised as a continuum of disease, with a proportion of patients presenting with classical Crohn’s disease or ulcerative colitis phenotypes. Future implementation of personalisation and stratification strategies, including clinical and molecular biomarkers, implementation of predictors of response and outcome and use of additional therapies, will continue to require working within clinical networks and multiprofessional teams.
Up to 25% of inflammatory bowel disease (IBD) presents during childhood, often with severe and extensive disease, leading to significant morbidity including delayed growth and nutritional impairment. The classical approach to management has centred on differentiation into Crohn’s disease (CD) or ulcerative colitis (UC), with subsequent treatment based on symptoms, results and complications. However, IBD is a heterogeneous condition with substantial variation in phenotype, disease course and outcome, so whilst effective treatment exists one size does not fit all. The ability to predict disease course at diagnosis, alongside tailoring medications based on response gives the potential for a more ‘personalised approach’. The move to a pre-emptive strategy to prevent IBD-related complications, whilst simultaneously minimising side effects and long-term toxicity from therapy, particularly in those with relatively indolent disease, has the potential to revolutionise care. In very early-onset IBD, personalised approaches to diagnosis and management have become the standard of treatment enabling clinicians to significantly alter the outcomes of the few children with monogenic disease. However, the promise of discoveries in genomics, microbiome and transcriptomics in paediatric IBD has not yet translated to clinical application for the vast majority of patients. Despite this, the opportunity presents itself to apply data gathered at diagnosis and follow-up to predict which patients are likely to progress to complicated disease, which will respond well and which will require additional therapy. Using complex mathematics and innovative, cutting-edge machine learning (ML) techniques gives the potential to use this data to develop personalised clinical care algorithms to treat patients more effectively, reduce toxicity and improve outcome. In this review, we will consider current management of paediatric IBD, discuss how precision medicine is making inroads into clinical practice already, examine the contemporary studies applying data to stratify patients and explore how future management may be revolutionised by personalisation with clinical, genomic and other multi-omic data.
22 August 2018 in Archives of Disease in Childhood - Fetal and Neonatal Edition
Background Previously published data have demonstrated that preterm infants experience a fall across marked centile lines for weight in early life with early poor head growth also reported. This study describes a single neonatal unit’s experience of longitudinal change in weight, head circumference (HC) and length in a cohort of preterm infants born <32 weeks’ gestation. Methods Data were collected from a single neonatal unit between July 2012 and June 2017. This period followed the introduction of improved nutritional guidelines. Patients were grouped according to their gestational age at birth. Growth lines were constructed for weight, HC and length in each gestational age group from the median measures and compared with reference centile lines. Results Data were analysed from 396 patients consisting of 2808, 1991 and 2004 measures for weight, HC and length, respectively. Longitudinal growth plots did not show an initial absolute weight loss in any of the subgroups. Across all groups, the mean change in SD score between birth and 36 weeks was −0.27 (95% CI −0.39 to −0.15). Conclusions This description of longitudinal growth in a cohort of preterm infants demonstrates that early postnatal growth failure is not inevitable, with most infants growing along a trajectory close to their birth centile. There is no evidence of a 2 marked centile line weight decrease or weight loss. These data provide evidence to suggest that extrauterine weight gain tracking centile lines can be achieved.
1 May 2019 in The Lancet Child & Adolescent Health