Prediction of Relapse After Anti–Tumor Necrosis Factor Cessation in Crohn's Disease: Individual Participant Data Meta-analysis of 1317 Patients From 14 Studies

Background & Aims: Tools for stratification of relapse risk of Crohn's disease (CD) after anti–tumor necrosis factor (TNF) therapy cessation are needed. We aimed to validate a previously developed prediction model from the diSconTinuation in CrOhn's disease patients in stable Remission on combined therapy with Immunosuppressants (STORI) trial, and to develop an updated model. Methods: Cohort studies were selected that reported on anti-TNF cessation in 30 or more CD patients in remission. Individual participant data were requested for luminal CD patients and anti-TNF treatment duration of 6 months or longer. The discriminative ability (concordance-statistic [C-statistic]) and calibration (agreement between observed and predicted risks) were explored for the STORI model. Next, an updated prognostic model was constructed, with performance assessment by cross-validation. Results: This individual participant data meta-analysis included 1317 patients from 14 studies in 11 countries. Relapses after anti-TNF cessation occurred in 632 of 1317 patients after a median of 13 months. The pooled 1-year relapse rate was 38%. The STORI prediction model showed poor discriminative ability (C-statistic, 0.51). The updated model reached a moderate discriminative ability (C-statistic, 0.59), and included clinical symptoms at cessation (hazard ratio [HR], 2.2; 95% CI, 1.2–4), younger age at diagnosis (HR, 1.5 for A1 (age at diagnosis ≤16 years) vs A2 (age at diagnosis 17 - 40 years); 95% CI, 1.11–1.89), no concomitant immunosuppressants (HR, 1.4; 95% CI, 1.18–172), smoking (HR, 1.4; 95% CI, 1.15–1.67), second line anti-TNF (HR, 1.3; 95% CI, 1.01–1.69), upper gastrointestinal tract involvement (HR, 1.3 for L4 vs non-L4; 95% CI, 0.96–1.79), adalimumab (HR, 1.22 vs infliximab; 95% CI, 0.99–1.50), age at cessation (HR, 1.2 per 10 years younger; 95% CI, 1–1.33), C-reactive protein (HR, 1.04 per doubling; 95% CI, 1.00–1.08), and longer disease duration (HR, 1.07 per 5 years; 95% CI, 0.98–1.17). In subanalysis, the discriminative ability of the model improved by adding fecal calprotectin (C-statistic, 0.63). Conclusions: This updated prediction model showed a reasonable discriminative ability, exceeding the performance of a previously published model. It might be useful to guide clinical decisions on anti-TNF therapy cessation in CD patients after further validation.