Proportion Of Non-progressors Research Articles

Development and validation of a machine learning-supported strategy of patient selection for osteoarthritis clinical trials: the IMI-APPROACH study

ObjectivesTo efficiently assess the disease-modifying potential of new osteoarthritis treatments, clinical trials need progression-enriched patient populations. To assess whether the application of machine learning results in patient selection enrichment, we developed a machine learning recruitment strategy targeting progressive patients and validated it in the IMI-APPROACH knee osteoarthritis prospective study. DesignWe designed a two-stage recruitment process supported by machine learning models trained to rank candidates by the likelihood of progression. First stage models used data from pre-existing cohorts to select patients for a screening visit. The second stage model used screening data to inform the final inclusion. The effectiveness of this process was evaluated using the actual 24-month progression. ResultsFrom 3500 candidate patients, 433 with knee osteoarthritis were screened, 297 were enrolled, and 247 completed the 2-year follow-up visit. We observed progression related to pain (P, 30%), structure (S, 13%), and combined pain and structure (P ​+ ​S, 5%), and a proportion of non-progressors (N, 52%) ∼15% lower vs an unenriched population. Our model predicted these outcomes with AUC of 0.86 [95% CI, 0.81–0.90] for pain-related progression and AUC of 0.61 [95% CI, 0.52–0.70] for structure-related progression. Progressors were ranked higher than non-progressors for P ​+ ​S (median rank 65 vs 143, AUC = 0.75), P (median rank 77 vs 143, AUC = 0.71), and S patients (median rank 107 vs 143, AUC = 0.57). ConclusionsThe machine learning-supported recruitment resulted in enriched selection of progressive patients. Further research is needed to improve structural progression prediction and assess this strategy in an interventional trial.

Spinal Radiographic Progression and Predictors of Progression in Patients With Radiographic Axial Spondyloarthritis Receiving Ixekizumab Over 2 Years.

To evaluate the long-term effect of ixekizumab (IXE) on radiographic changes in the spine in patients with radiographic axial spondyloarthritis (r-axSpA) by measuring change from baseline through 2 years in modified Stoke Ankylosing Spondylitis Spinal Score (mSASSS), and to identify potential predictors of progression. This study evaluates patients from COAST-V (ClinicalTrials.gov: NCT02696785, biologic disease-modifying antirheumatic drug-naïve) and COAST-W (NCT02696798, tumor necrosis factor inhibitor-experienced) who had mSASSS data at baseline in the originating studies and 108 weeks after baseline in the extension study COAST-Y (NCT03129100). We examined the proportion of patients who did not have spinal radiographic progression through 2 years (108 weeks) of treatment with IXE (80 mg every 2 or 4 weeks) and the change from baseline to year 2 in mSASSS. Potential predictors of spinal radiographic progression were also evaluated. Among patients with evaluable radiographs who were originally assigned to IXE (n = 230), mean (SD) change in mSASSS from baseline at year 2 was 0.3 (1.8). The proportion of nonprogressors over 2 years was 89.6% if defined as mSASSS change from baseline < 2 and 75.7% if defined as mSASSS change from baseline ≤ 0. Predictors of structural progression at year 2 (mSASSS change > 0) were age ≥ 40, baseline syndesmophytes, HLA-B27 positivity, and male sex. Week 52 inflammation in Spondyloarthritis Research Consortium of Canada spine was also a predictor of radiographic progression at year 2 in patients with magnetic resonance imaging data in COAST-V (n = 109). The majority of patients with r-axSpA receiving IXE had no radiographic progression in the spine through 2 years of treatment. Predictors were generally consistent with previous studies.

POS0918 EVALUATION OF SPINAL RADIOGRAPHIC PROGRESSION IN PATIENTS WITH RADIOGRAPHIC AXIAL SPONDYLOARTHRITIS RECEIVING IXEKIZUMAB THERAPY OVER 2 YEARS

Background:It is important to understand the potential effect long-term therapy with biologics can have on structural changes in the spine among patients with active radiographic axial spondyloarthritis (r-axSpA, ankylosing spondylitis).Objectives:We examined radiographic progression in the spine among patients with active r-axSpA treated with ixekizumab, an IL-17A antagonist, for 2 years, and potential predictors of spinal radiographic progression.Methods:Patients with active r-axSpA, biologic-naive (COAST-V, NCT02696785) or with prior experience with a maximum of 2 TNF inhibitors (COAST-W, NCT02696798), received 80 mg ixekizumab every 2 or 4 weeks for 2 years (108 weeks, of which 56 weeks were the COAST-Y extension study, NCT03129100). Mean change from baseline of modified Stoke Ankylosing Spondylitis Spinal Score (mSASSS) (average score from 2 selected readers, blinded for time order) for patients treated with ixekizumab for 2 years with data at both baseline and year 2 is presented (N=230; 54% of total randomized patients). Non-progression is presented for all patients and subgroups based on TNFi-experience. Predictors were identified in multivariate logistic regression models with stepwise selection criteria of p-value &lt;0.1. All data are observed.Results:At baseline, patients (N=230) were predominately male (82%) with an average age of 43 years, mean symptom duration of 16 years, 52% were TNFi-experienced, mean (SD) ASDAS score was 4.0 (0.7), most were HLA-B27 positive (87%) and 40% had syndesmophytes (identified by both selected readers at the same location). Baseline mSASSS (SD) was 11.0 (16.3) and change from baseline at year 2 of treatment was 0.3 (1.8) (Table 1). The proportion of non-progressors (mSASSS change from baseline &lt;2) over 2 years was 89.6% (total IXE [all patients]), 90.9% (biologic-naive) and 88.3% (TNFi-experienced), and, if defined as mSASSS change from baseline ≤0, 75.7% (total IXE [all patients]), 78.2% (biologic-naive) and 73.3% (TNFi-experienced) (Table 1). Predictors of structural progression at year 2 (mSASSS change &gt;0) were age, baseline syndesmophytes, HLA-B27 status and gender (Table 1). Week 52 inflammation in MRI SPARCC spine was also identified as a predictor for structural progression at year 2 in a separate model for patients from COAST-V where MRI measures were available at baseline and Week 52 (N=109).Conclusion:The majority of patients treated with ixekizumab for 2 years did not show radiographic progression, and the overall mean progression was low. Similar levels of non-progression were observed in biologic-naive patients and patients previously exposed to TNFis. Predictors were generally consistent with previous studies.Table 1.Spinal radiographic changes for patients with active r-axSpA treated with ixekizumab for 2 yearsChange in mSASSS at year 2All patientsaN=230Biologic-naiveN=110TNFi-experiencedN=120 Baseline mSASSS, mean (SD)11.0 (16.3)10.1 (15.5)11.7 (17.0) Change at year 2, mean (SD)0.3 (1.8)0.3 (2.0)0.4 (1.6) Change in total mSASSS &lt;2, n (%)206 (89.6)100 (90.9)106 (88.3) Change in total mSASSS ≤0, n (%)174 (75.7)86 (78.2)88 (73.3)Multivariable logistic regression modelPrediction for change in total mSASSS &gt;0, OR (95% CI), p-valueAll patientsa,bN=228 Age (≥40 years vs. &lt;40 years)2.97 (1.41, 6.28)p=0.004c Baseline syndesmophytesb (yes vs. no)2.31 (1.18, 4.54)p=0.015c Baseline HLA-B27 (positive vs. negative)3.78 (1.04, 13.75)p=0.044c Gender (male vs. female)3.16 (1.01, 9.86)p=0.047c Baseline ASDAS state (&gt;3.5 vs. [2.1, 3.5])2.26 (0.96, 5.34)p=0.063aCombined ixekizumab group of Q2W and Q4W patients with baseline and year-2 mSASSS databIdentified by both selected readers at the same location (2 patients were not evaluable by both readers)cp&lt;0.05Abbreviations: ASDAS=Assessment of Disease Activity, CI=confidence interval, IXE=ixekizumab, mSASSS=modified Stoke Ankylosing Spondylitis Spinal Score, OR=odds ratio, Q2W=every 2 weeks, Q4W=every 4 weeks, SD=standard deviation, TNFi=tumor necrosis factor inhibitorDisclosure of Interests:Désirée van der Heijde Consultant of: AbbVie, Amgen, Astellas, AstraZeneca, Bayer, BMS, Boehringer Ingelheim, Celgene, Cyxone, Daiichi, Eisai, Eli-Lilly, Galapagos, Gilead, Glaxo-Smith-Kline, Janssen, Merck, Novartis, Pfizer, Regeneron, Roche, Sanofi, Takeda, UCB Pharma, Employee of: Director of Imaging Rheumatology bv., Mikkel Østergaard Consultant of: AbbVie, BMS, Boehringer-Ingelheim, Eli Lilly and Company, Janssen, Merck, Pfizer, Roche, UCB, Celgene, Sanofi, Regeneron, Novartis, Grant/research support from: AbbVie, BMS, Merck, UCB, Celgene, Novartis, John D Reveille Paid instructor for: UCB, Eli Lilly and Company, Consultant of: UCB, Eli Lilly and Company, Pfizer, Novartis, Grant/research support from: Janssen, Eli Lilly and Company, Xenofon Baraliakos Speakers bureau: Abbvie, BMS, Lilly, Janssen, Novartis, MSD, Pfizer, Galapagos, Gilead, UCB, Paid instructor for: Abbvie, BMS, Lilly, Janssen, Novartis, MSD, Pfizer, Galapagos, Gilead, UCB, Consultant of: Abbvie, BMS, Lilly, Janssen, Novartis, MSD, Pfizer, Galapagos, Gilead, UCB, Andris Kronbergs Shareholder of: Eli Lilly and Company, Employee of: Eli Lilly and Company, David Sandoval Shareholder of: Eli Lilly and Company, Employee of: Eli Lilly and Company, Xiaoqi Li Shareholder of: Eli Lilly and Company, Employee of: Eli Lilly and Company, Hilde Carlier Shareholder of: Eli Lilly and Company, Employee of: Eli Lilly and Company, David Adams Shareholder of: Eli Lilly and Company, Employee of: Eli Lilly and Company, Walter P Maksymowych Speakers bureau: Abbvie, Janssen, Novartis, Pfizer, UCB, Consultant of: Abbvie, Boehringer, BMS, Eli Lilly and Company, Novartis, Pfizer, UCB, Grant/research support from: Abbvie, Novartis, Pfizer

SAT0290 Effect of tnf antagonists on radiographic progression in psoriatic arthritis: Systematic review and meta-analysis of randomized controlled trials

BackgroundPsoriatic arthritis (PsA) can cause important structural damages which can lead to disability. TNF antagonists have shown their clinical efficacy in PsA, but only a few data are available regarding...