Validation and update of a prediction model for risk of relapse after cessation of anti-TNF treatment in Crohn's disease

Sebastiaan Ten Bokkel Huinink, Djuna C. de Jong, Daan Nieboer, Doranne Thomassen, Ewout W. Steyerberg, Marcel G.W. Dijkgraaf, Alexander G.L. Bodelier, Rachel L. West, Tessa E.H. Römkens, Frank Hoentjen, Rosalie C. Mallant, Bas A.C. van Tuyl, Wout G.N. Mares, Frank H.J. Wolfhagen, Gerard Dijkstra, Jurriën G.P. Reijnders, Nanne K. de Boer, Adriaan C.I.T.L. Tan, Petra G.A. van Boeckel, Greetje J. TackDirk P. van Asseldonk, Geert R.A.M. D'Haens, C. Janneke van der Woude, Marjolijn Duijvestein, Annemarie C. de Vries*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review


BACKGROUND: Anti-tumor necrosis factor (TNF) therapy is effective for the treatment of Crohn's disease. Cessation may be considered in patients with a low risk of relapse. We aimed to externally validate and update our previously developed prediction model to estimate the risk of relapse after cessation of anti-TNF therapy. METHODS: We performed a retrospective cohort study in 17 Dutch hospitals. Crohn's disease patients in clinical, biochemical or endoscopic remission were included after anti-TNF cessation. Primary outcome was a relapse necessitating treatment. Discrimination and calibration of the previously developed model were assessed. After external validation, the model was updated. The performance of the updated prediction model was assessed in internal-external validation and by using decision curve analysis. RESULTS: 486 patients were included with a median follow-up of 1.7 years. Relapse rates were 35 and 54% after 1 and 2 years. At external validation, the discriminative ability of the prediction model was equal to that found at the development of the model [c-statistic 0.58 (95% confidence interval (CI) 0.54-0.62)], though the model was not well-calibrated on our cohort [calibration slope: 0.52 (0.28-0.76)]. After an update, a c-statistic of 0.60 (0.58-0.63) and calibration slope of 0.89 (0.69-1.09) were reported in internal-external validation. CONCLUSION: Our previously developed and updated prediction model for the risk of relapse after cessation of anti-TNF in Crohn's disease shows reasonable performance. The use of the model may support clinical decision-making to optimize patient selection in whom anti-TNF can be withdrawn. Clinical validation is ongoing in a prospective randomized trial.

Original languageEnglish
Pages (from-to)983-992
Number of pages10
JournalEuropean journal of gastroenterology & hepatology
Issue number10
Publication statusPublished - Oct 2022

Bibliographical note

Publisher Copyright:
Copyright © 2022 Wolters Kluwer Health, Inc. All rights reserved.


Dive into the research topics of 'Validation and update of a prediction model for risk of relapse after cessation of anti-TNF treatment in Crohn's disease'. Together they form a unique fingerprint.

Cite this