Real-World Evidence to Contextualize Clinical Trial Results and Inform Regulatory Decisions: Tofacitinib Modified-Release Once-Daily vs Immediate-Release Twice-Daily for Rheumatoid Arthritis

Abstract

Introduction: Tofacitinib is an oral Janus kinase inhibitor for the treatment of rheumatoid arthritis (RA). To provide additional clinical evidence in regulatory submissions for a modified-release (MR) once-daily (QD) tofacitinib formulation, we compared real-world adherence and effectiveness between patients initiating the MR QD formulation and patients initiating an immediate-release (IR) twice-daily (BID) formulation.

Methods: Two noninterventional cohort studies were conducted. First, adherence and two effectiveness proxies were compared between patients with RA who newly initiated tofacitinib MR 11 mg QD or IR 5 mg BID in the IBM^® MarketScan^® Commercial and Medicare Supplemental US insurance claims databases (March 2016-October 2018). Second, using data collected in the Corrona US RA Registry (February 2016-August 2019), two Clinical Disease Activity Index (CDAI)-based measures of effectiveness were compared between tofacitinib MR 11 mg QD and IR 5 mg BID, and against noninferiority criteria derived from placebo-controlled clinical trials of the tofacitinib IR formulation. Multiple sensitivity analyses of the registry data were conducted to reassure regulators of consistent results across different assumptions.

Results: In each study, approximately two-thirds of patients initiated the MR formulation. In the claims database study, improved adherence and at least comparable effectiveness were observed with tofacitinib MR vs IR over 12 months, particularly in patients without prior advanced therapy. In the registry study, the noninferiority of tofacitinib MR vs IR was demonstrated for both CDAI outcomes at ~6 months; this finding was robust across multiple sensitivity analyses.

Conclusion: These results demonstrate the value of real-world evidence from complementary data sources in understanding the impact of medication adherence with a QD formulation in clinical practice. These analyses were suitable for regulatory consideration as an important component of evidence for the comparability of tofacitinib MR 11 mg QD vs IR 5 mg BID in patients with RA.

Trial registration: Claims database study: ClinicalTrials.gov identifier NCT04018001, retrospectively registered July 12, 2019. Corrona US RA Registry study: ClinicalTrials.gov identifier NCT04267380, retrospectively registered February 12, 2020.

Keywords: Claims analysis; Clinical effectiveness; Drug approval process; Registry; Rheumatoid arthritis; Rheumatology; Tofacitinib.

Fig. 1

US claims databases: cohort selection. BID twice daily, IR immediate-release, MR modified-release, MTX methotrexate, N number of patients, QD once daily, RA rheumatoid arthritis

Fig. 2

US claims databases: unadjusted proportion of patients and adjORs of patients who were highly adherent with tofacitinib treatment through 6 and 12 months: a, b PDC^a ≥ 0.80; c, d MPR^b ≥ 0.80. Data from the IBM^® MarketScan^® Commercial and Medicare Supplemental US insurance claims databases. adjOR adjusted odds ratio, bDMARD biologic disease-modifying antirheumatic drug, BID twice daily, CI confidence interval, IR immediate-release, MPR medication possession ratio, MR modified-release, N number of patients, OR odds ratio, PDC proportion of days covered, QD once daily, RA rheumatoid arthritis. *p < 0.05; **p < 0.01; ***p < 0.001 tofacitinib MR 11 mg QD vs IR 5 mg BID. ^aPDC was defined as number of days covered by arrays for each tofacitinib prescription fill, adjusted for a < 15-day overlap in days’ supply (numerator), during the 6- or 12-month post-index period (denominator). ^bMPR was defined as total tofacitinib days’ supply filled, divided by the number of days between first and last tofacitinib prescription in the 6- or 12-month post-index period. MPR was capped at 1.0. ^cNo bDMARDs, tofacitinib, or baricitinib. ^dAdjusted analyses were performed using logistic regression models, which included index medication (tofacitinib MR 11 mg QD or IR 5 mg BID), type of therapy (combination or monotherapy), insurance type, region, age, sex, index year, use of nonsteroidal anti-inflammatory drugs in the 12-month pre-index period (yes/no), and number of prior advanced therapies any time pre-index as covariates. Initially, the models included an interaction term of index medication by type of therapy; if the p value was > 0.20, it was removed and the simpler model was fitted instead

Fig. 3

US claims databases: unadjusted proportion of patients and adjORs of patients meeting effectiveness (proxy) criteria^a: a, b overall; c, d no prior advanced therapy. Data from the IBM^® MarketScan^® Commercial and Medicare Supplemental insurance US claims databases. adjOR adjusted odds ratio, bDMARD biologic disease-modifying antirheumatic drug, BID twice daily, CI confidence interval, csDMARD conventional synthetic disease-modifying antirheumatic drug, IR immediate-release, MR modified-release, N number of patients, NE not estimable, OR odds ratio, PDC proportion of days covered, QD once daily. *p < 0.05; **p < 0.01; ***p < 0.001 tofacitinib MR 11 mg QD vs IR 5 mg BID. ^aAn algorithm-based proxy measure of effectiveness during the 12-month post-index period was based on the six criteria shown in a, c; patients meeting all criteria were considered effectively treated [22]. ^bORs were NE for “No dose escalation”, owing to rates at or close to 100%. ^c≤ 30 days of oral glucocorticoid between months 3 and 12 post-index in patients with no glucocorticoid prescriptions for 6 months pre-index. ^dNo increase in oral glucocorticoid dose ≥ 20% during months 6–12 post-index (for those with 6 months of pre-index glucocorticoid use). ^eAdjusted analyses were performed using logistic models, which included index medication (tofacitinib MR 11 mg QD or IR 5 mg BID), type of therapy (combination or monotherapy), insurance type, region, age, sex, index year, use of nonsteroidal anti-inflammatory drugs in the 12-month pre-index period (yes/no), and number of prior advanced therapies any time pre-index as covariates. Initially, the models included an interaction term of index medication by type of therapy; if the p value was > 0.20, it was removed and the simpler model was fitted instead. ^fNo bDMARDs, tofacitinib, or baricitinib

Fig. 4

US claims databases: a mean duration of tofacitinib treatment^a over 6 and 12 months (unadjusted); b risk for tofacitinib discontinuation over 6 and 12 months (adjusted^b); c proportion of patients who were persistent^c with tofacitinib treatment through 6 and 12 months (unadjusted); d ORs of persistent tofacitinib treatment through 6 and 12 months (adjusted^b). Data from the IBM^® MarketScan^® Commercial and Medicare Supplemental US insurance claims databases. bDMARD biologic disease-modifying antirheumatic drug, BID twice daily, CI confidence interval, HR hazard ratio, IR immediate-release, MR modified-release, N number of patients, OR odds ratio, QD once daily, SD standard deviation. *p < 0.05; **p < 0.01 tofacitinib MR 11 mg QD vs IR 5 mg BID. ^aDuration of therapy was defined as the number of days between tofacitinib initiation and the first of the following: date of last tofacitinib prescription followed by a 60-day gap after days’ supply expiration without evidence of another advanced therapy; day before receipt of another advanced therapy; or end of follow-up period. ^bAdjusted analyses were performed using Cox (duration of therapy) and logistic regression (persistence) models, which included index medication (tofacitinib MR 11 mg QD or IR 5 mg BID), type of therapy (combination or monotherapy), insurance type, region, age, sex, index year, use of nonsteroidal anti-inflammatory drugs in the 12-month pre-index period (yes/no), and number of prior advanced therapies any time pre-index as covariates. Initially, the models included an interaction term of index medication by type of therapy; if the p value was > 0.20, it was removed and the simpler model was fitted instead. ^cDefined as the continuation of index medication without a ≥ 60-day gap after prior prescription days’ supply had run out or advanced therapy (bDMARD or baricitinib) switch, and associated duration of therapy. ^dNo bDMARDs, tofacitinib, or baricitinib

Fig. 5

US registry: patients included in the primary analysis and post hoc sensitivity analyses. Percentages are with respect to all tofacitinib initiators (i.e., patients included in sensitivity analysis 3). BID twice daily, CDAI Clinical Disease Activity Index, IR immediate-release, MR modified-release, N number of patients, PS propensity score, QD once daily, RA rheumatoid arthritis