Withdrawal of infliximab or concomitant immunosuppressant therapy in patients with Crohn's disease on combination therapy (SPARE): a multicentre, open-label, randomised controlled trial

Abstract

Background: The combination of infliximab and immunosuppressant therapy is a standard management strategy for patients with Crohn's disease. Concerns regarding the implications of long-term combination therapy provided the rationale for a formal clinical trial of treatment de-escalation. Our aim was to compare the relapse rate and the time spent in remission over 2 years between patients continuing combination therapy and those stopping infliximab or immunosuppressant therapy.

Methods: This multicentre, open-label, randomised controlled trial was performed in 64 hospitals in seven countries in Europe and Australia. Adult patients with Crohn's disease in steroid-free clinical remission for more than 6 months, on combination therapy of infliximab and immunosuppressant therapy for at least 8 months were randomly assigned (1:1:1) to either continue combination therapy (combination group), discontinue infliximab (infliximab withdrawal group), or discontinue immunosuppressant therapy (immunosuppressant withdrawal group). Randomisation was stratified according to disease duration before start of first anti-TNF treatment (≤2 or >2 years), failure of immunosuppressant therapy before start of infliximab, and presence of ulcers at baseline endoscopy. The patient number and group of each stratum were assigned by a central online randomisation website. Treatment was optimised or resumed in case of relapse in all groups. Participants, those assessing outcomes, and those analysing the data were not masked to group assignment. The coprimary endpoints were the relapse rate (superiority analysis) and time in remission over 2 years (non-inferiority analysis, non-inferiority margin 35 days). Analyses were done on an intention-to-treat basis. This study is registered with ClinicalTrials.gov, NCT02177071, and with EU Clinical Trials Register, EUDRACT 2014-002311-41. The trial was completed in April, 2021.

Findings: Between Nov 2, 2015, and April 24, 2019, 254 patients were screened. Of these, 211 were randomised and 207 were included in the final analysis (n=67 in the combination group, n=71 in the infliximab withdrawal group, and n=69 in the immunosuppressant withdrawal group). 39 patients had a relapse (eight [12%] of 67 in the combination group, 25 [35%] of 71 in the infliximab withdrawal group, six [9%] of 69 in the immunosuppressant withdrawal group). 2-year relapse rates were 14% (95% CI 4-23) in the combination group, 36% (24-47) in the infliximab withdrawal group, and 10% (2-18) in the immunosuppressant withdrawal group (hazard ratio [HR] 3·45 [95% CI 1·56-7·69], p=0·003, for infliximab withdrawal vs combination, and 4·76 [1·92-11·11], p=0·0004, for infliximab withdrawal vs immunosuppressant withdrawal). Of 28 patients who had a relapse and were retreated or optimised according to protocol, remission was achieved in 25 patients (one of two in the combination group, 22 of 23 in the infliximab withdrawal group, and two of three in the immunosuppressant withdrawal group). The mean time spent in remission over 2 years was 698 days (95% CI 668-727) in the combination group, 684 days (651-717) in the infliximab withdrawal group, and 706 days (682-730) in the immunosuppressant withdrawal group. The difference in restricted mean survival time in remission was -14 days (95% CI -56 to 27) between the infliximab withdrawal group and the combination group and -22 days (-62 to 16) between the infliximab withdrawal group and the immunosuppressant withdrawal group. The 95% CIs contained the non-inferiority threshold (-35 days). We recorded 31 serious adverse events, in 20 patients, with no difference in frequency between groups. The most frequent serious adverse events were infections (four in the combination group, two in the infliximab withdrawal group, and one in the immunosuppressant withdrawal group) and Crohn's disease exacerbation (three in the combination group, four in the infliximab withdrawal group, and one in the immunosuppressant withdrawal group). No death nor malignancy was recorded.

Interpretation: In patients with Crohn's disease in sustained steroid-free remission under combination therapy with infliximab and immunosuppressant therapy, withdrawal of infliximab should only be considered after careful assessment of risks and benefits for each patient, whereas withdrawal of immunosuppressant therapy could generally represent a preferable strategy when considering treatment de-escalation.

Funding: European Union's Horizon 2020.

Figure 1

Study design *Indicates that colonoscopy was done at that timepoint.

Figure 2

Trial profile Reasons for a follow-up duration shorter than 2 years (<100 weeks, per protocol) in the trial were: Combination group: treatment failure (n=6), patient's decision (n=5), physician's decision (n=2), and last follow-up visit performed too early (n=1); infliximab withdrawal group: treatment failure (n=5), physician decision (n=1), patient's decision (n=4), and last follow-up visit performed too early (n=3); immunosuppressant withdrawal group: treatment failure (n=11), physician's decision (n=1), patient's decision (n=1), last follow-up visit performed too early (n=1), lost to follow-up (n=2), and pregnancy (n=2).

Figure 3

Relapse-free survival Relapse-free survival was estimated by Kaplan–Meier estimators with their 95% CIs in the three groups, over 104 weeks.

Figure 4

Probability of being in remission by time Patients who had a relapse, were considered not to be in remission until subsequent regained remissions (CDAI <150). Patients for whom remission was not achieved or who met other definitions of treatment failure terminated the trial and were considered not to be in remission for the remainder of the study (except for the treatment failures linked to treatment side-effects who were censored at the time of treatment failure).

Figure 5

Failure-free survival Failure-free survival was estimated by Kaplan–Meier estimators with their 95% CIs in the three groups of the trial, over 2 years.