Development, Validation, and Evaluation of the Pediatric Inflammatory Crohn's Magnetic Resonance Enterography Index From the ImageKids Study

Challenges in IBD Research 2024: Novel Technologies

Novel technology is one of the five focus areas of the Challenges in Inflammatory Bowel Disease (IBD) Research 2024 document. Building off the Challenges in IBD Research 2019 document, the Foundation aims to provide a comprehensive overview of current gaps in IBD research and deliver actionable approaches to address them with a focus on how these gaps can lead to advancements in interception, remission, and restoration for these diseases. The document is the result of a multidisciplinary collaboration from scientists, clinicians, patients, and funders and represents a valuable resource for patient-centric research prioritization. Specifically, the Novel Technologies section focuses on addressing key research gaps to enable interception and improve remission rates in IBD. This includes testing predictions of disease onset and progression, developing novel technologies tailored to specific phenotypes, and facilitating collaborative translation of science into diagnostics, devices, and therapeutics. Proposed priority actions outlined in the document include real-time measurement of biological changes preceding disease onset, more effective quantification of fibrosis, exploration of technologies for local treatment of fistulas, and the development of drug delivery platforms for precise, location-restricted therapies. Additionally, there is a strong emphasis on fostering collaboration between various stakeholders to accelerate progress in IBD research and treatment. Addressing these research gaps necessitates the exploration and implementation of bio-engineered novel technologies spanning a spectrum from materials to systems. By harnessing innovative ideas and technologies, there's a collective effort to enhance patient care and outcomes for individuals affected by IBD.

Precision nutrition in pediatric IBD: A position paper from the ESPGHAN special interest group for basic science and translational research, the IBD Porto group, and allied health professionals

Stratified and precision nutrition refers to disease management or prevention of disease onset, based on dietary interventions tailored to a person's characteristics, biology, gut microbiome, and environmental exposures. Such treatment models may lead to more effective management of inflammatory bowel disease (IBD) and reduce risk of disease development. This societal position paper aimed to report advances made in stratified and precision nutritional therapy in IBD. Following a structured literature search, limited to human studies, we identified four relevant themes: (a) nutritional epidemiology for risk prediction of IBD development, (b) food-based dietary interventions in IBD, (c) exclusive enteral nutrition (EEN) for Crohn's disease (CD) management, and (d) pre- and probiotics for IBD management. There is scarce literature upon which we can make recommendations for precision or stratified dietary therapy for IBD, both for risk of disease development and disease management. Certain single-nucleotide polymorphisms related to polyunsaturated fatty acid (PUFA) metabolism may modify the effect dietary PUFA have in increasing the risk of IBD development. Non-colonic CD, mild-to-moderate CD, and high microbiota richness may predict success of EEN and may be used both for prediction of treatment continuation, but also for early cessation in nonresponders. There is currently insufficient evidence to make recommendations for precision or stratified dietary therapy for patients with established IBD. Despite the great interest in stratified and precision nutrition, we currently lack data to support conclusive recommendations. Replication of early findings by independent research groups and within structured clinical interventions is required.

The Role of Noninvasive Surrogates of Inflammation in Monitoring Pediatric Inflammatory Bowel Diseases: The Old and the New

Effectiveness of limited available therapies for pediatric inflammatory bowel disease has reached stagnation. Previous non-invasive monitoring strategies have relied upon cumbersome tools to evaluate clinical symptoms and biochemical markers that do not reflect endoscopic activity or respond quickly to treatments. Novel, patient-centric, and highly accurate, monitoring strategies with a focus on intestinal ultrasound for a direct, precise monitoring of activity to achieve disease modification are now possible. Ultimately, research on the optimal tight control monitoring strategies, individualized to each pediatric inflammatory bowel disease patient, are in development and offer a hope to potential therapeutic ceiling breakthrough on the horizon.

The Pediatric Crohn Disease Morbidity Index (PCD-MI): Development of a Tool to Assess Long-Term Disease Burden Using a Data-Driven Approach

BACKGROUND/OBJECTIVE

Heterogeneity and chronicity of Crohn disease (CD) make prediction of outcomes difficult. To date, no longitudinal measure can quantify burden over a patient's disease course, preventing assessment and integration into predictive modeling. Here, we aimed to demonstrate the feasibility of constructing a data driven, longitudinal disease burden score.

METHODS

Literature was reviewed for tools used in assessment of CD activity. Themes were identified to construct a pediatric CD morbidity index (PCD-MI). Scores were assigned to variables. Data were extracted automatically from the electronic patient records at Southampton Children's Hospital, diagnosed from 2012 to 2019 (inclusive). PCD-MI scores were calculated, adjusted for duration of follow up and assessed for variation (ANOVA) and distribution (Kolmogorov-Smirnov).

RESULTS

Nineteen clinical/biological features across five themes were included in the PCD-MI including blood/fecal/radiological/endoscopic results, medication usage, surgery, growth parameters, and extraintestinal manifestations. Maximal score was 100 after accounting for follow-up duration. PCD-MI was assessed in 66 patients, mean age 12.5 years. Following quality filtering, 9528 blood/fecal test results and 1309 growth measures were included. Mean PCD-MI score was 14.95 (range 2.2-32.5); data were normally distributed ( P = 0.2) with 25% of patients having a PCD-MI < 10. There was no difference in the mean PCD-MI when split by year of diagnosis, F -statistic 1.625, P = 0.147.

CONCLUSIONS

PCD-MI is a calculatable measure for a cohort of patients diagnosed over an 8-year period, integrating a wide-range of data with potential to determine high or low disease burden. Future iterations of the PCD-MI require refinement of included features, optimized scores, and validation on external cohorts.

Prospective Validation of the Lémann Index in Children: A Report From the Multicentre Image Kids Study

BACKGROUND

The Lémann Index [LI] and the recently updated LI are tools for measuring structural bowel damage in adults with Crohn's disease [CD] but have not been evaluated in children. We aimed to validate the updated LI in the prospective multicentre ImageKids study of paediatric CD.

METHODS

We included children with CD undergoing magnetic resonance enterography [MRE], pelvic magnetic resonance imaging [MRI] and ileocolonoscopy. Half were followed for 18 months, when MRE was repeated. Serum was collected for fibrosis-related proteomic markers. The LI was calculated by central readers from the MRE, ileocolonoscopy, physical examination and surgical data. Reliability and construct validity were assessed at baseline, while responsiveness and test-retest reliability were explored longitudinally.

RESULTS

In total, 240 children were included (mean age, 14.2 ± 2.5 years; median disease duration, 2.2 years [interquartile range, IQR 0.25-4.42]; median baseline LI, 4.23 [IQR 2.0-8.8]). The updated LI had excellent inter-observer reliability (interclass correlation coefficient [ICC] = 0.94, 95% confidence interval [CI] 0.92-0.95) but poor, although statistically significant, correlation with radiologist and gastroenterologist global assessments of damage and with serum proteomic levels of fibrotic markers [rho = 0.15-0.30, most p < 0.05]. The updated LI had low discriminative validity for detecting damage (area under the receiver operating characteristic curve [AUC-ROC] 0.69, 95% CI 0.62-0.75). In 116 repeated MREs, responsiveness was suboptimal for differentiating improved from unchanged disease [AUC-ROC 0.58, 95% CI 0.45-0.71]. Test-retest reliability was high among stable patients [ICC = 0.84, 95% CI 0.72-0.91].

CONCLUSION

Overall, the updated LI had insufficient psychometric performance for recommending its use in children. An age-specific index may be needed for children with shorter disease duration than typical adult cohorts.

Development of a multimodal machine-learning fusion model to non-invasively assess ileal Crohn's disease endoscopic activity

BACKGROUND AND OBJECTIVE

Recurrent attentive non-invasive observation of intestinal inflammation is essential for the proper management of Crohn's disease (CD). The goal of this study was to develop and evaluate a multi-modal machine-learning (ML) model to assess ileal CD endoscopic activity by integrating information from Magnetic Resonance Enterography (MRE) and biochemical biomarkers.

METHODS

We obtained MRE, biochemical and ileocolonoscopy data from the multi-center ImageKids study database. We developed an optimized multimodal fusion ML model to non-invasively assess terminal ileum (TI) endoscopic disease activity in CD from MRE data. We determined the most informative features for model development using a permutation feature importance technique. We assessed model performance in comparison to the clinically recommended linear-regression MRE model in an experimental setup that consisted of stratified 2-fold validation, repeated 50 times, with the ileocolonoscopy-based Simple Endoscopic Score for CD at the TI (TI SES-CD) as a reference. We used the predictions' mean-squared-error (MSE) and the receiver operation characteristics (ROC) area under curve (AUC) for active disease classification (TI SEC-CD≥3) as performance metrics.

RESULTS

121 subjects out of the 240 subjects in the ImageKids study cohort had all required information (Non-active CD: 62 [51%], active CD: 59 [49%]). Length of disease segment and normalized biochemical biomarkers were the most informative features. The optimized fusion model performed better than the clinically recommended model determined by both a better median test MSE distribution (7.73 vs. 8.8, Wilcoxon test, p<1e-5) and a better aggregated AUC over the folds (0.84 vs. 0.8, DeLong's test, p<1e-9).

CONCLUSIONS

Optimized ML models for ileal CD endoscopic activity assessment have the potential to enable accurate and non-invasive attentive observation of intestinal inflammation in CD patients. The presented model is available at https://tcml-bme.github.io/ML_SESCD.html.