Prevalence, incidence, and mortality of inflammatory bowel disease in the Netherlands - development and external validation of machine learning models

Aug 5, 2026

Upload by Miles

Large registries offer strong opportunities for studying inflammatory bowel disease epidemiology. This study developed and validated machine learning models to identify IBD cases in administrative data, with the goal of estimating prevalence, incidence, and mortality in the Netherlands. Models were trained in a population-based cohort and externally validated in a hospital cohort, using Brier score, AUC, calibration, and accuracy. Best-performing models were applied to 2013–2020 data, revealing high case identification performance and increasing mortality alongside stable incidence trends.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Abstract

Background and aims

Methods

Results

Conclusion

Introduction

Epidemiological stages of IBD in the Netherlands

Methods and validation approach

Model development and external validation

Evaluation metrics

Findings

Prevalence, incidence, and mortality results

Conclusion and implications

EUR Research Information Portal Prevalence, incidence, and mortality of inflammatory bowel disease in the Netherlands Published in: Journal of Crohn's & colitis Publication status and date: Published: 04/02/2025 DOI (link to publisher): 10.1093/ecco-jcc/jjaf017 Document Version Publisher's PDF, also known as Version of record Document License/Available under: CC BY-NC Citation for the published version (APA): van Linschoten, R. C. A. , van Leeuwen, N. , van Klaveren, D. , Pierik, M. J. , Creemers, R. , Hendrix, E. M. B. , Hazelzet, J. A. , van der Woude, C. J. , West, R. L. , & van Noord, D. (2025) . Prevalence, incidence, and mortality of inflammatory bowel disease in the Netherlands: development and external validation of machine learning models. Journal of Crohn's & colitis, 19(2), Article jjaf017 . [https://doi.org/10.1093/ecco-jcc/jjaf017](https://doi.org/10.1093/ecco-jcc/jjaf017) Link to publication on the EUR Research Information Portal Terms and Conditions of Use Except as permitted by the applicable copyright law, you may not reproduce or make this material available to any third party without the prior written permission from the copyright holder(s) . Copyright law allows the following uses of this material without prior permission: • you may download, save and print a copy of this material for your personal use only; • you may share the EUR portal link to this material. In case the material is published with an open access license (e.g. a Creative Commons (CC) license), other uses may be allowed. Please check the terms and conditions of the specific license. Take-down policy If you believe that this material infringes your copyright and/or any other intellectual property rights, you may request its removal by contacting us at the following email address: [openaccess.library@eur.nl. Please](openaccess.library@eur.nl. Please) provide us with all the relevant information, including the reasons why you believe any of your rights have been infringed. In case of a legitimate complaint, we will make the material inaccessible and/or remove it from the website. Prevalence, incidence, and mortality of inflammatory bowel disease in the Netherlands: development and external validation of machine learning models Reinier C.A. van Linschoten1,2,3,*,, Nikki van Leeuwen3, David van Klaveren3, Marieke J. Pierik4,5,, Rob Creemers5,6,, Evelien M. B. Hendrix4,5,, Jan A. Hazelzet3,, C. Janneke van der Woude2, Rachel L. West1,\#, Desirée van Noord1,\#, 1Department of Gastroenterology & Hepatology, Franciscus Gasthuis & Vlietland, P. O. Box 10900, 3004 BA, Rotterdam, The Netherlands 2Department of Gastroenterology & Hepatology, Erasmus MC, P. O. Box 2040, 3000 CA, Rotterdam, The Netherlands 3Department of Public Health, Erasmus MC, P. O. Box 2040, 3000 CA, Rotterdam, The Netherlands 4Department of Gastroenterology and Hepatology, MUMC+, P. O. Box 5800, 6202 AZ, Maastricht, The Netherlands 5 NUTRIM School of Nutrition and Translational Research in Metabolism, Faculty of Health, Medicine and Life Sciences, Maastricht University, P. O. Box 616, 6200 MD, Maastricht, The Netherlands 6Department of Gastroenterology, Geriatrics, Internal and Intensive Care Medicine (Co-MIK), Sittard-Geleen, Zuyderland Medical Centre, P. O. Box 5, 6130 AA, Heerlen, The Netherlands * Corresponding author: Reinier C.A. van Linschoten, Franciscus Gasthuis & Vlietland, P. O. Box 10900, 3004 BA Rotterdam, The Netherlands (r.vanlinschoten@ [erasmusmc.nl](erasmusmc.nl)) . \#Rachel L. West and Desirée van Noord share last authorship. Abstract Background and aims: Large registries are promising tools to study the epidemiology of inflammatory bowel disease (IBD) . We aimed to develop and validate machine learning models to identify IBD cases in administrative data, aiming to determine the prevalence, incidence, and mortality of IBD in the Netherlands. Methods: We developed machine learning models for administ

FAQs

What was the main goal of this study?

To develop and externally validate machine learning models that identify inflammatory bowel disease cases in administrative data, enabling estimation of prevalence, incidence, and mortality in the Netherlands.

How were the machine learning models evaluated?

Models were assessed using Brier score, area under the ROC curve (AUC), calibration, and accuracy, and then used to derive epidemiological estimates for 2013–2020.

Which models performed best for key tasks?

Random forest performed best for identifying IBD cases, gradient-boosted trees performed best for subtype classification, and random forest performed best for incidence year.

Aug 5, 2026

Upload by Miles