A Machine Learning Approach to Predict Remission in Patients With Psoriatic Arthritis on Treatment With Secukinumab
Ontology highlight
ABSTRACT: Background
Psoriatic Arthritis (PsA) is a multifactorial disease, and predicting remission is challenging. Machine learning (ML) is a promising tool for building multi-parametric models to predict clinical outcomes. We aimed at developing a ML algorithm to predict the probability of remission in PsA patients on treatment with Secukinumab (SEC). Methods
PsA patients undergoing SEC treatment between September 2017 and September 2020 were retrospectively analyzed. At baseline and 12-month follow-up, we retrieved demographic and clinical characteristics, including Body Mass Index (BMI), disease phenotypes, Disease Activity in PsA (DAPSA), Leeds Enthesitis Index (LEI) and presence/absence of comorbidities, including fibromyalgia and metabolic syndrome. Two random feature elimination wrappers, based on an eXtreme Gradient Boosting (XGBoost) and Logistic Regression (LR), were trained and validated with 10-fold cross-validation for predicting 12-month DAPSA remission with an attribute core set with the least number of predictors. The performance of each algorithm was assessed in terms of accuracy, precision, recall and area under receiver operating characteristic curve (AUROC). Results
One-hundred-nineteen patients were selected. At 12 months, 20 out of 119 patients (25.21%) achieved DAPSA remission. Accuracy and AUROC of XGBoost was of 0.97 ± 0.06 and 0.97 ± 0.07, overtaking LR (accuracy 0.73 ± 0.09, AUROC 0.78 ± 0.14). Baseline DAPSA, fibromyalgia and axial disease were the most important attributes for the algorithm and were negatively associated with 12-month DAPSA remission. Conclusions
A ML approach may identify SEC good responders. Patients with a high disease burden and axial disease with comorbid fibromyalgia seem challenging to treat.
SUBMITTER: Venerito V
PROVIDER: S-EPMC9271870 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundUsing a machine learning approach, the study investigated if specific baseline characteristics could predict which psoriatic arthritis (PsA) patients may gain additional benefit from a starting dose of secukinumab 300 mg over 150 mg. We also report results from individual patient efficacy meta-analysis (IPEM) in 2049 PsA patients from the FUTURE 2 to 5 studies to evaluate the efficacy of secukinumab 300 mg, 150 mg with and without loading regimen versus placebo at week 16 on achievement of several clinically relevant difficult-to-achieve (higher hurdle) endpoints.MethodsMachine learning employed Bayesian elastic net to analyze baseline data of 2148 PsA patients investigating 275 predictors. For IPEM, results were presented as difference in response rates versus placebo at week 16.ResultsMachine learning showed secukinumab 300 mg has additional benefits in patients who are anti-tumor necrosis factor-naive, treated with 1 prior anti-tumor necrosis factor agent, not receiving methotrexate, with enthesitis at baseline, and with shorter PsA disease duration. For IPEM, at week 16, all secukinumab doses had greater treatment effect (%) versus placebo for higher hurdle endpoints in the overall population and in all subgroups; 300-mg dose had greater treatment effect than 150 mg for all endpoints in overall population and most subgroups.ConclusionsMachine learning identified predictors for additional benefit of secukinumab 300 mg compared with 150 mg dose. Individual patient efficacy meta-analysis showed that secukinumab 300 mg provided greater improvements compared with 150 mg in higher hurdle efficacy endpoints in patients with active PsA in the overall population and most subgroups with various levels of baseline disease activity and psoriasis.
| S-EPMC8389345 | biostudies-literature
Project description:IntroductionPsoriatic arthritis (PsA) is an immune-mediated chronic inflammatory arthropathy associated with impaired physical function and reduced quality of life. Biologic therapies that target tumor necrosis factor (anti-TNF) have significantly improved clinical outcomes. Partial, non- and transient responses remain common comprising significant unmet clinical need. New therapies with novel modes of action are urgently required.ObjectivesThe interleukin (IL)-17 pathway has recently been attributed a critical role in the pathogenesis of spondyloarthritides. Herein, we review data from clinical studies with secukinumab, a novel fully human IgG1κ anti-IL-17A monoclonal antibody (mAb), in patients with active PsA.ResultsAcross two pivotal phase 3 studies, secukinumab provided significant and sustained reductions in the signs and symptoms of PsA, inhibition of radiographic progression, and improved patient-reported outcomes and measures of quality of life. The primary efficacy endpoint, a ≥20% improvement from baseline according to the American College of Rheumatology 20 (ACR20) response at Week 24, was significantly higher in patients treated with secukinumab compared with placebo, with improvements sustained through at least 52 weeks. Clinical benefits were seen with secukinumab regardless of concomitant methotrexate treatment and in patients who were either anti-TNF-naïve or who were inadequate responders to anti-TNF therapy. Secukinumab was well-tolerated, with a safety profile consistent with that previously reported in psoriasis trials. The most common adverse events were nasopharyngitis, upper respiratory tract infections, and headache.ConclusionSecukinumab offers an effective new addition to the available treatment options for PsA. Regulatory submissions have been filed worldwide, with the first approvals recently obtained in Japan and Europe. Future studies are required to define the optimal timing and strategic use of this novel treatment modality.FundingNovartis Pharma.
| S-EPMC4999581 | biostudies-literature
Project description:Secukinumab (Cosentyx®) is a fully human monoclonal antibody that selectively targets interleukin (IL)-17A, a proinflammatory cytokine involved in the pathogenesis of psoriatic arthritis (PsA). Administered subcutaneously, the first-in-class anti-IL-17 agent is approved in numerous countries worldwide for the treatment of adults with active PsA. In the phase III FUTURE trials, secukinumab 150 or 300 mg improved the clinical signs and symptoms of PsA versus placebo in patients with active disease despite previous treatment with NSAIDs, biological disease-modifying anti-rheumatic drugs (bDMARDs) and/or tumour necrosis factor inhibitors (TNFi). The benefits of secukinumab were seen regardless of whether or not patients had received previous TNFi therapy, and were maintained during longer term (up to 5 years) treatment. In FUTURE 1 and 5, secukinumab inhibited structural joint damage and was associated with sustained low rates of radiographic progression through 1-3 years of treatment. Treatment with secukinumab improved physical function and health-related quality of life (HR-QOL) and was generally well tolerated, both in the short- and longer-term. In the head-to-head EXCEED trial, secukinumab did not quite attain statistical significance for superiority versus adalimumab in the joint domain. In conclusion, secukinumab is effective across all key PsA domains and is generally well tolerated, and thus represents a useful treatment alternative to TNFi and other bDMARDs in adult patients with active PsA.
| S-EPMC8049904 | biostudies-literature
Project description:The treatment of ankylosing spondylitis (AS) and psoriatic arthritis (PsA) positively changed since the introduction of anti-TNF? drugs. These treatments were shown to reduce the symptoms and signs of the diseases and improve the quality of life. However, a variable percentage of patients do not respond to anti-TNF? or can exhibit a loss of response and, furthermore, despite anti-TNF? drugs' proven efficacy in reducing peripheral radiographic progression in PsA, the impact in reducing radiographic damage in AS is still debated. Recently, the discovery of new pathogenic mechanisms paved the way to the development of new drugs that target other pro-inflammatory cytokines. In particular, the inhibition of interleukin (IL)-17, which is the principal cytokine produced by Th17 lymphocytes, a pro-inflammatory subset involved in both inflammation and new bone formation in AS and PsA, demonstrated promising results. The new molecule secukinumab, an IL-17A inhibitor, showed its efficacy and safety in phase III randomized clinical trials in AS and PsA and is the first non-anti-TNF? biologic approved for the treatment of AS, providing a useful alternative treatment strategy in both diseases. The aim of this article was to review the pathophysiological basis, the efficacy and the safety of secukinumab treatment in AS and PsA patients.
| S-EPMC5085310 | biostudies-literature
Project description:ImportanceApproximately one-quarter of the global population have latent tuberculosis infection (LTBI), and tuberculosis (TB) is accountable for more than 1.5 million deaths annually. Methotrexate, cyclosporine, and tumor necrosis factor inhibitors may be associated with increased risk of TB and LTBI reactivation, although data are limited on the risks of TB with use of newer biologics.ObjectiveTo assess the association of secukinumab with reporting of active TB development, TB reactivation, and LTBI activation as an adverse event (AE) in patients with psoriasis, psoriatic arthritis, or ankylosing spondylitis.Design, setting, and participantsThis pooled cohort study pooled data from 28 clinical trials of secukinumab used in psoriasis (17 phase 3 or 3b and 2 phase 4 trials), psoriatic arthritis (5 phase 3 trials), and ankylosing spondylitis (4 phase 3 trials). A search of the Novartis Secukinumab Compound Pool Database was conducted for the 28 trials. All trial participants who had received at least 1 approved subcutaneous dose of secukinumab (150 mg or 300 mg) were included. Before randomization in these trials, patients underwent screening for TB. Patients with active TB were excluded, and patients with LTBI were treated according to local guidelines. Data were analyzed from the start of treatment in the individual studies through December 25, 2018.Main outcomes and measuresReporting of active TB or LTBI as an AE over a 5-year period using exposure-adjusted incidence rates (EAIR; incidence rates per 100 patient-years).ResultsA total of 12 319 patients were included, of whom 8819 patients had psoriasis (71.6%; 5930 men [67.2%]; mean [SD] age, of 44.9 [13.5] years), 2523 had psoriatic arthritis (20.5%; 1323 women [52.4%]; mean [SD] age, 48.8 [12.1] years), and 977 had ankylosing spondylitis (7.3%; 658 men [67.3%]; mean [SD] age, 42.3 [11.9] years). In the total population, 684 patients (5.6%) had tested positive for LTBI at screening. Over 5 years, LTBI as an AE during secukinumab treatment was reported in 13 patients (0.1% of 12 319). Of these 13 patients, 6 had a prior positive LTBI test result, and 7 were newly diagnosed as having LTBI. Four of the 7 patients had psoriasis (EAIR, 0.03; 95% CI, 0.01-0.07), 1 had psoriatic arthritis (EAIR, 0.02; 95% CI, 0.00-0.11), and 2 had ankylosing spondylitis (EAIR, 0.08; 95% CI, 0.01-0.28). No cases of active TB were reported.Conclusions and relevanceThis study found that LTBI reported as an AE after secukinumab treatment was uncommon and appeared to support the use of secukinumab in chronic systemic inflammatory conditions.
| S-EPMC7527940 | biostudies-literature
Project description:ObjectiveThe aim was to determine the cost effectiveness of secukinumab, a fully human interleukin-17A inhibitor, for adults in the UK with active psoriatic arthritis (PsA) who are tumour necrosis factor inhibitor (TNFi) naïve and without concomitant moderate-to-severe psoriasis, and who have responded inadequately to conventional systemic disease-modifying anti-rheumatic drugs (csDMARDs).Perspective and settingThe study took the perspective and setting of the UK National Health Service (NHS).MethodsThe model structure was a 3-month decision tree leading into a Markov model. Separate analyses based on the number of prior csDMARDs (one and two or more) were conducted, with secukinumab 150 mg compared to standard of care (SoC) and TNFis, respectively, for each subpopulation. Clinical parameters, including response at 3 months, were from the FUTURE 2 trial and a network meta-analysis. Outcomes included total costs and quality-adjusted life years (QALYs) over the 40-year time horizon (3.5% annual discount for both outcomes; cost year 2017), and incremental cost effectiveness ratios (ICERs).ResultsThe ICER for secukinumab 150 mg versus SoC was £28,748 per QALY gained (one prior csDMARD). Secukinumab 150 mg dominated golimumab, certolizumab pegol and etanercept, and had an ICER of £5680 per QALY gained versus adalimumab and > £1 million saved per QALY foregone versus infliximab (two or more prior csDMARDs). Valuing one QALY at between £20,000 and £30,000, the probability of secukinumab having the highest net monetary benefit was 48.9% (one prior csDMARD) and 88.9% (two or more prior csDMARDs). Parameters related to Health Assessment Questionnaire scores were most influential.ConclusionsSecukinumab 150 mg at list price appears to represent a cost-effective use of NHS resources for adults with PsA who have responded inadequately to one or two or more prior csDMARDs.
| S-EPMC5999172 | biostudies-literature
Project description:Psoriatic arthritis (PsA) is a chronic, seronegative spondyloarthropathy associated with psoriasis (PsO). Treatment options range from non-pharmacologic measures to NSAIDS, DMARDs, and biologics, depending on patient presentation. Secukinumab (Cosentyx©) is a new biologic treatment option that was approved for use in treating adult patients with PsA in October 2016. Our paper explores the clinical trial evidence available for secukinumab to examine its safety and efficacy as a therapeutic agent for the treatment of PsA. While indirect comparisons of indicate that secukinumab is as effective as other treatment options, further studies directly comparing available treatments will be necessary to establish its place in treatment guidelines. As these and other trials are conducted, the evidence produced will further elucidate the clinical potential of secukinumab as a treatment option for patients with rheumatologic disease.
| S-EPMC5696288 | biostudies-literature
Project description:Background: Real world evidence data regarding secukinumab (SEC) use in biologic-experienced patients with psoriatic arthritis (PsA) are scarce. Objectives: To assess the real life survival, safety and efficacy of SEC in biologic-experienced patients with PsA. Methods: All biologic-experienced PsA patients treated with SEC in 2 University Rheumatology Units were included (3/2016-12/2018). Patients' and disease characteristics were recorded at baseline and during SEC therapy. Results: 75 patients were included; 76% were females with a mean age of 53.9 years, median disease duration of 6.7 years and median SEC treatment duration of 11.1 months. At baseline, 97% had peripheral arthritis, 42% axial involvement, 22% enthesitis, and 12% dactylitis. Regarding previous biologic exposure, 48 (64%) had been exposed to anti-tumor necrosis factor (TNF) agents only, 5 (7%) to the interleukin (IL)-12/23 inhibitor (Ustekinumab-UST) only while 22 (29%) both to anti-TNFs and UST. Fifty-three percent received SEC in combination with non-biologics and 35% with glucocorticoids, respectively. During follow-up, statistically significant improvement in different disease activity indices were noted (DAS28-CRP, DAPSA, BASDAI). SEC survival rate at the end of follow-up was 64% (48/75), without difference between patients exposed to anti-TNFs only (67%) vs. anti-TNFs and UST (68%) as well as to 1 vs. ?2 anti-TNFs. The rate of serious adverse events and serious infections during follow-up was 4.8 and 1.2/100 patient-years, respectively. Discussion: In real life, in biologic-experienced patients with PsA, SEC displayed a high retention rate, regardless of the type, and number of previous biologics (anti-TNFs ± anti-IL12/23), without significant side effects.
| S-EPMC7317305 | biostudies-literature
Project description:BACKGROUND:Secukinumab has demonstrated sustained improvement in the signs and symptoms of psoriatic arthritis (PsA) over 2?years in the FUTURE 2 study (NCT01752634). This post hoc analysis assessed the ability of secukinumab to achieve Psoriatic Arthritis Disease Activity Score (PASDAS)-based remission or low disease activity (LDA) through 2?years among patients with PsA in the FUTURE 2 study. METHODS:PASDAS (cut-off scores: remission ??1.9; LDA >?1.9 and?<?3.2; Moderate Disease Activity ??3.2 and?<?5.4; and high disease activity [HDA]???5.4) was assessed in the overall population (tumour necrosis factor inhibitor [TNFi]-naïve and TNFi-experienced), in patients stratified by prior TNFi use and by disease duration at weeks 16, 52 and 104. The impact of secukinumab on individual PASDAS core components and on the relationship between PASDAS states and patient-reported outcomes (PROs), including physical function, health-related quality of life (HRQoL) and work productivity, were also assessed. Data for the approved doses of secukinumab (300 and 150?mg) are reported. PASDAS scores and core components were reported as observed, and PROs were analysed using mixed models for repeated measures. RESULTS:In the overall population, PASDAS remission and LDA were achieved in 15.6% and 22.9%, respectively, of patients treated with secukinumab 300?mg and in 15.2% and 19.2%, respectively, in the secukinumab 150?mg group versus 2.3% and 13.8%, respectively, with placebo at week 16. In the TNFi-naïve group, a higher proportion of patients achieved remission?+?LDA at week 16 with secukinumab 300 and 150?mg (46.2% and 42.9%, respectively) versus placebo (17.5%), with corresponding responses in TNFi-experienced patients being 22.6% and 19.4% versus 13.3%. Remission/LDA responses with secukinumab were sustained through 2?years. Patients achieving remission/LDA reported greater improvements in PROs than patients in HDA through 2?years. CONCLUSIONS:Secukinumab-treated patients achieved higher PASDAS-defined remissions or LDA compared with placebo at week 16, which were sustained through 2?years. Remission/LDA was achieved by both TNFi-naïve and TNFi-experienced patients treated with secukinumab, with higher rates in TNFi-naïve patients. Secukinumab-treated patients achieving remission/LDA reported significantly greater improvements in PROs, including physical function and different dimensions of health-related quality of life and work, than patients in HDA. TRIAL REGISTRATION:ClinicalTrials.gov, NCT01752634 . Registered on December 19, 2012. EUDRACT, 2012-004439-22 . Registered on December 12, 2012.
| S-EPMC6286532 | biostudies-literature
Project description:Machine learning (ML) is largely used to develop automatic predictors in migraine classification but automatic predictors for medication overuse (MO) in migraine are still in their infancy. Thus, to understand the benefits of ML in MO prediction, we explored an automated predictor to estimate MO risk in migraine. To achieve this objective, a study was designed to analyze the performance of a customized ML-based decision support system that combines support vector machines and Random Optimization (RO-MO). We used RO-MO to extract prognostic information from demographic, clinical and biochemical data. Using a dataset of 777 consecutive migraine patients we derived a set of predictors with discriminatory power for MO higher than that observed for baseline SVM. The best four were incorporated into the final RO-MO decision support system and risk evaluation on a five-level stratification was performed. ROC analysis resulted in a c-statistic of 0.83 with a sensitivity and specificity of 0.69 and 0.87, respectively, and an accuracy of 0.87 when MO was predicted by at least three RO-MO models. Logistic regression analysis confirmed that the derived RO-MO system could effectively predict MO with ORs of 5.7 and 21.0 for patients classified as probably (3 predictors positive), or definitely at risk of MO (4 predictors positive), respectively. In conclusion, a combination of ML and RO - taking into consideration clinical/biochemical features, drug exposure and lifestyle - might represent a valuable approach to MO prediction in migraine and holds the potential for improving model precision through weighting the relative importance of attributes.
| S-EPMC7327028 | biostudies-literature