Development and internal validation of a machine learning-based disease burden index for irritable bowel syndrome: a multicentre cross-sectional study

Background Irritable bowel syndrome (IBS) is one of the most common disorders of gut-brain interaction in gastroenterology clinics worldwide, becoming a significant public health burden. This study aims to provide an exploratory approach for comprehensive assessment of IBS burden and may serve as a basis for future external validation and further evaluation of its potential clinical application.Patients and Methods This multicentre cross-sectional study included IBS patients diagnosed according to the Rome III and/or Rome IV criteria. Rome criteria-based comparisons and latent class analysis (LCA) were performed to characterize clinical heterogeneity, followed by the development of the IBS burden index (IBS-BI) using machine learning.Results Compared to the Rome IV-ineligible group, the Rome IV-eligible group exhibited significantly more severe IBS symptoms, somatization symptoms, anxiety symptoms, depression symptoms, and poorer health-related quality of life (all p <0.05). Linear regression analysis showed that the severity of these symptoms was inversely related to health-related quality of life (all p <0.05). LCA identified four heterogeneous IBS burden phenotypes: high-symptom burden, low-symptom burden, somatization-dominant, and psychological comorbid phenotypes. Using machine learning, we developed the IBS-BI and an interactive clinical calculator. The validation was limited to an internal training-validation split, and no external validation was performed.Conclusions Patients with IBS who fulfilled the Rome IV criteria showed a higher disease burden, which may be related to the more stringent diagnostic requirements of these criteria. The IBS-BI may have potential value for evaluating disease burden and patient stratification. Its clinical utility and broader applicability require further validation in independent external cohorts and prospective studies.