Advancing Predictive Modeling of Inflammatory Bowel Disease (IBD) Flares: A Data-Driven Approach Using Lifestyle and Psychosocial Factors from a Remote Monitoring Platform

作者：Y. Okegunna, M. Sekar, G. M. Adriaans, M. Cloots, J. Zhang, A. Aliu, E. Hendrix, M. Romberg-Camps, A. Rezazadeh Ardabili, Z. Mujagić, A. Dekker, M. Pierik, R. Fijten · 发表于：Digestive Diseases and Sciences · 年份：2026 · DOI：10.1007/s10620-026-09750-8 · 被引用次数：2 · 研究领域：Medicine

BACKGROUND Recurrent flares are associated with disease progression and have a pronounced impact on the quality of life of people with Inflammatory Bowel Disease (IBD). Models using clinical characteristics only moderately predict flares and therefore difficult to implement in clinical practice. With the rise of remote monitoring platforms such as myIBDcoach, which capture besides clinical disease activity, modifiable lifestyle and psychosocial risk factors and patient-reported outcome measures (PROMs), harnessing real-world data may help improve flare prediction. The aim of this study was to develop and compare five predictive models for flares. METHOD The baseline demographic and clinical data and PROMs related to lifestyle and psychosocial factors were collected from the myIBDcoach telemedicine platform from November 2022 to June 2024. Associations between flares, baseline clinical variables alone, and PROMs variable categories from the myIBDcoach platform were estimated using stepwise group-LASSO logistic regression (G-LASSO) model, which was evaluated with performance matrices using accuracy, area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULT Four hundred and twenty-nine patients from a prospective observational cohort were selected to create the models. The performance of the G-LASSO regression model with baseline variables and myIBDcoach PROMs (psychosocial and lifestyle factors) was be...