Dataset Information

Deterioration of Health-Related Quality of Life After Withdrawal of Risankizumab Treatment in Patients with Moderate-to-Severe Plaque Psoriasis: A Machine Learning Predictive Model.

ABSTRACT:

Introduction

Risankizumab has demonstrated efficacy in treating moderate-to-severe psoriasis. The phase-3 IMMhance trial (NCT02672852) examined the effect of continuing versus withdrawing from risankizumab treatment on psoriasis severity, including the Psoriasis Area and Severity Index (PASI) and static Physician Global Assessment (sPGA). However, the effect of withdrawal on health-related quality of life (HRQL) was not assessed. Therefore, this study was conducted to evaluate the impact of risankizumab withdrawal on HRQL measured by the Dermatology Life Quality Index (DLQI). Because DLQI was not measured beyond week 16 in IMMhance, a machine learning predictive model for DLQI was developed.

Methods

A machine learning model for DLQI was fitted using repeated measures data from three phase-3 trials (NCT02684370, NCT02684357, NCT02694523) (pooled N = 1602). An elastic-net algorithm performed automated variable selection among candidate predictors including concurrent PASI and sPGA, demographics, and interaction terms. The machine learning model was used to predict DLQI at weeks 28-104 of IMMhance among patients re-randomized to continue (N = 111) or withdraw from (N = 225) risankizumab after achieving response (sPGA = 0/1) at week 28.

Results

The machine learning predictive model demonstrated good statistical fit during tenfold cross-validation and external validation against observed DLQI at weeks 0-16 of IMMhance (N = 507). Predicted improvements in DLQI from baseline were lower in the withdrawal versus the continuation cohort (mean DLQI change at week 104, -5.9 versus -11.5, difference [95% CI] = 5.6 [4.1, 7.3]). Predicted DLQI deteriorated more extensively than PASI (49.7% versus 36.4%) after treatment withdrawal.

Conclusions

The predicted DLQI score deteriorated more rapidly after risankizumab withdrawal than the PASI score, an objective measure of disease. These findings suggest that the deterioration in HRQL reflects more substantial impacts after risankizumab discontinuation than those measured by PASI only.

SUBMITTER: Papp KA

PROVIDER: S-EPMC8322223 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ImportanceRisankizumab selectively inhibits interleukin 23, a cytokine that contributes to psoriatic inflammation.ObjectiveTo evaluate the efficacy and safety of risankizumab vs placebo and continuous treatment vs withdrawal in adults with moderate to severe plaque psoriasis.Design, setting, and participantsMultinational, phase 3, randomized, double-blind, placebo-controlled trial conducted from March 6, 2016, to July 26, 2018. A total of 507 eligible patients had stable moderate to severe chronic plaque psoriasis for 6 months or longer, body surface area involvement greater than or equal to 10%, Psoriasis Area and Severity Index (PASI) greater than or equal to 12, and a static Physician's Global Assessment (sPGA) score greater than or equal to 3. Intention-to-treat analysis was conducted.InterventionsPatients were randomized (4:1, interactive response technology) to risankizumab, 150 mg, subcutaneously, or placebo at weeks 0 and 4 (part A1). All patients received risankizumab at week 16. At week 28, patients randomized to risankizumab who achieved an sPGA score of 0/1 were rerandomized 1:2 to risankizumab or placebo every 12 weeks (part B).Main outcomes and measuresCo-primary end points for the part A1 phase included proportions of patients achieving greater than or equal to 90% improvement in PASI (PASI 90) and sPGA score of 0/1 at week 16. The PASI measures severity of erythema, infiltration, and desquamation weighted by area of skin involvement over the head, trunk, upper extremities, and lower extremities; scores range from 0 (no disease) to 72 (maximal disease activity). The sPGA assesses average thickness, erythema, and scaling of all psoriatic lesions; scores range from 0 (clear) to 4 (severe), with 0/1 indicating clear or almost clear. Primary and secondary end points in part B included proportion of rerandomized patients achieving an sPGA score of 0/1 at week 52 (primary) and week 104 (secondary).ResultsOf 563 patients screened, 507 were randomized to risankizumab (n = 407) or placebo (n = 100). Most patients were men (356 [70.2%]); median age was 51 years (interquartile range, 38-60 years). At week 16, 298 patients (73.2%) in the treatment group vs 2 patients (2.0%) receiving placebo achieved a PASI 90 response, and 340 patients (83.5%) receiving risankizumab vs 7 patients (7.0%) receiving placebo achieved sPGA 0/1 scores (placebo-adjusted differences: PASI 90: 70.8%; 95% CI, 65.7%-76.0%; sPGA 0/1: 76.5%; 95% CI, 70.4%-82.5%; P < .001 for both). At week 28, 336 responders were rerandomized to risankizumab (n = 111) or treatment withdrawal (n = 225). At week 52, the sPGA 0/1 score was achieved by 97 patients (87.4%) receiving risankizumab vs 138 patients (61.3%) receiving placebo. At week 104, the sPGA 0/1 score was achieved by 90 patients (81.1%) receiving risankizumab vs 16 patients (7.1%) receiving placebo (placebo-adjusted differences: week 52: 25.9%; 95% CI, 17.3%-34.6%; week 104: 73.9%; 95% CI, 66.0%-81.9%; P < .001 for both). Rates of treatment-emergent adverse events were similar between risankizumab (186 [45.7%]) and placebo (49 [49.0%]) in part A1 and remained stable over time.Conclusions and relevanceRisankizumab showed superior efficacy compared with placebo through 16 weeks and treatment withdrawal through 2 years. Risankizumab was well tolerated, with no unexpected safety findings during the 2-year trial.Trial registrationClinicalTrials.gov Identifier: NCT02672852.

Project description:BackgroundRisankizumab has demonstrated durable, high rates of efficacy in patients with moderate-to-severe plaque psoriasis as assessed by the achievement of relative Psoriasis Area and Severity Index (PASI) improvement and Dermatology Life Quality Index (DLQI) 0/1.ObjectivesThe aim of this post hoc analysis is to assess the achievement of absolute PASI thresholds and related improvements in health-related quality of life (HRQoL) in patients with moderate-to-severe plaque psoriasis treated with (i) risankizumab compared with ustekinumab, and (ii) long-term (>52 weeks to 172 weeks) risankizumab.MethodsData from patients randomised to 150 mg risankizumab or 45 or 90 mg ustekinumab in replicate randomised controlled trials UltIMMa-1 and UltIMMa-2 were analysed for the achievement of absolute PASI thresholds PASI ≤ 3, PASI ≤ 1, and PASI = 0, time to achieve these thresholds, and combined PASI and DLQI endpoints. Data from pat ients initially randomised to risankizumab who continued on risankizumab in the open-label extension study LIMMitless were analysed for the achievement of absolute PASI levels, mean DLQI scores, and DLQI 0/1.ResultsSignificantly greater proportions of patients treated with risankizumab compared with ustekinumab achieved PASI ≤ 3, PASI ≤ 1, and PASI = 0, as well as combined endpoints for absolute PASI and DLQI [(PASI ≤ 3 and DLQI ≤ 5) or (PASI ≤ 1 and DLQI 0/1)]. The median time to first achieve PASI ≤ 3, PASI ≤ 1, and PASI = 0 was significantly lower for risankizumab-treated patients compared with ustekinumab-treated patients. Among patients treated with long-term risankizumab, more than 90% achieved PASI ≤ 3 though week 172 and more than 80% achieved DLQI 0/1. Low absolute PASI scores corresponded with low mean absolute DLQI scores through week 172 of continuous risankizumab treatment.ConclusionsRisankizumab treatment demonstrated high rates of rapid and durable efficacy as measured by absolute PASI thresholds and improvements in patient HRQoL.