Letter: Enhancing Predictive Models for Paediatric Ulcerative Colitis—Addressing Socioeconomic, Environmental and Clinical Factors

Abstract

The longitudinal cohort study by Claßen et al. on predicting complications in paediatric ulcerative colitis (pUC) [1] provides valuable insights into predicting complications in pUC and establishes a strong foundation for clinical decision-making. However, based on the latest developments in the field, I believe there are several areas where the study could be further improved to enhance its clinical relevance and predictive accuracy.

First, the study does not fully consider the impact of socioeconomic and environmental factors on disease progression. Research shows that socioeconomic status (SES) influences healthcare access and affects immune response through stress, while factors like diet, air pollution and urbanisation are known triggers for inflammatory bowel disease (IBD) [2]. For instance, a high-fat, low-fibre diet can disrupt the gut microbiota and worsen inflammation. Future studies should integrate SES, environmental factors and gut microbiome analysis to better understand their combined effects on pUC prognosis and support targeted interventions.

Second, the study's approach to handling missing data could be improved. The authors employed a listwise deletion method which, while straightforward, can reduce sample size and introduce potential bias. To mitigate information loss, better method would be to use multiple imputation, a well-established technique in clinical research that handles missing data more effectively [3, 4]. Multiple imputation preserves the sample size and reduces bias, thereby increasing the robustness and reliability of the study's findings. Implementing this method would enhance the accuracy of the predictive models and ensure more credible conclusions.

Additionally, expanding subgroup analyses to include factors such as sex, family history, treatment regimens (e.g., immunosuppressants vs. biologics), initial disease severity, SES, extraintestinal manifestations (EIM), and regional or institutional differences would be desirable. These analyses could identify key factors influencing outcomes and inform personalised treatment strategies. For example, sex and family history may affect disease phenotype and behaviour, while regional healthcare disparities could influence access to various treatments. Including these variables would offer a more detailed understanding of pUC and help refine therapeutic approaches.

Finally, treatment adherence is a crucial aspect of managing chronic diseases, particularly in paediatric pUC. Adherence directly affects disease control and long-term outcomes [5]. Poor adherence from patients or their families can lead to increased relapse rates and disease severity. Future research should focus on strategies to improve adherence, such as educational programs, support tools or interventions that help families manage the disease more effectively. Analysing adherence data can also identify patient groups at risk of non-compliance, allowing for targeted support that optimises disease management and improves long-term outcomes.

In conclusion, while Claßen et al.'s study provides a solid foundation for predicting complications in pUC, incorporating socioeconomic, environmental and genetic factors, using advanced data handling techniques, and focusing on treatment adherence would significantly enhance its clinical utility. These improvements would further support the development of personalised disease management strategies and contribute to better long-term outcomes for patients.

Aga Luo: writing – review and editing, writing – original draft.

This article is linked to Claßen et al papers. To view these articles, visit https://doi.org/10.1111/apt.18262 and https://doi.org/10.1111/apt.18348.