Dataset Information

Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs.

ABSTRACT:

Background

Biological disease-modifying anti-rheumatic drugs (bDMARDs) can be tapered in some rheumatoid arthritis (RA) patients in sustained remission. The purpose of this study was to assess the feasibility of building a model to estimate the individual flare probability in RA patients tapering bDMARDs using machine learning methods.

Methods

Longitudinal clinical data of RA patients on bDMARDs from a randomized controlled trial of treatment withdrawal (RETRO) were used to build a predictive model to estimate the probability of a flare. Four basic machine learning models were trained, and their predictions were additionally combined to train an ensemble learning method, a stacking meta-classifier model to predict the individual flare probability within 14?weeks after each visit. Prediction performance was estimated using nested cross-validation as the area under the receiver operating curve (AUROC). Predictor importance was estimated using the permutation importance approach.

Results

Data of 135 visits from 41 patients were included. A model selection approach based on nested cross-validation was implemented to find the most suitable modeling formalism for the flare prediction task as well as the optimal model hyper-parameters. Moreover, an approach based on stacking different classifiers was successfully applied to create a powerful and flexible prediction model with the final measured AUROC of 0.81 (95%CI 0.73-0.89). The percent dose change of bDMARDs, clinical disease activity (DAS-28 ESR), disease duration, and inflammatory markers were the most important predictors of a flare.

Conclusion

Machine learning methods were deemed feasible to predict flares after tapering bDMARDs in RA patients in sustained remission.

SUBMITTER: Vodencarevic A

PROVIDER: S-EPMC7913400 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs.

Vodencarevic Asmir A Tascilar Koray K Hartmann Fabian F Reiser Michaela M Hueber Axel J AJ Haschka Judith J Bayat Sara S Meinderink Timo T Knitza Johannes J Mendez Larissa L Hagen Melanie M Krönke Gerhard G Rech Jürgen J Manger Bernhard B Kleyer Arnd A Zimmermann-Rittereiser Marcus M Schett Georg G Simon David D

Arthritis research & therapy 20210227 1

<h4>Background</h4>Biological disease-modifying anti-rheumatic drugs (bDMARDs) can be tapered in some rheumatoid arthritis (RA) patients in sustained remission. The purpose of this study was to assess the feasibility of building a model to estimate the individual flare probability in RA patients tapering bDMARDs using machine learning methods.<h4>Methods</h4>Longitudinal clinical data of RA patients on bDMARDs from a randomized controlled trial of treatment withdrawal (RETRO) were used to build ...[more]

PMID: 33640008

Similar Datasets

Project description:ImportanceThere are conflicting data on the association of antidrug antibodies with response to biologic disease-modifying antirheumatic drugs (bDMARDs) in rheumatoid arthritis (RA).ObjectiveTo analyze the association of antidrug antibodies with response to treatment for RA.Design, setting, and participantsThis cohort study analyzed data from the ABI-RA (Anti-Biopharmaceutical Immunization: Prediction and Analysis of Clinical Relevance to Minimize the Risk of Immunization in Rheumatoid Arthritis Patients) multicentric, open, prospective study of patients with RA from 27 recruiting centers in 4 European countries (France, Italy, the Netherlands, and the UK). Eligible patients were 18 years or older, had RA diagnosis, and were initiating a new bDMARD. Recruitment spanned from March 3, 2014, to June 21, 2016. The study was completed in June 2018, and data were analyzed in June 2022.ExposuresPatients were treated with a new bDMARD: adalimumab, infliximab (grouped as anti-tumor necrosis factor [TNF] monoclonal antibodies [mAbs]), etanercept, tocilizumab, and rituximab according to the choice of the treating physician.Main outcomes and measuresThe primary outcome was the association of antidrug antibody positivity with EULAR (European Alliance of Associations for Rheumatology; formerly, European League Against Rheumatism) response to treatment at month 12 assessed through univariate logistic regression. The secondary end points were the EULAR response at month 6 and at visits from month 6 to months 15 to 18 using generalized estimating equation models. Detection of antidrug antibody serum levels was performed at months 1, 3, 6, 12, and 15 to 18 using electrochemiluminescence (Meso Scale Discovery) and drug concentration for anti-TNF mAbs, and etanercept in the serum was measured using enzyme-linked immunosorbent assay.ResultsOf the 254 patients recruited, 230 (mean [SD] age, 54.3 [13.7] years; 177 females [77.0%]) were analyzed. At month 12, antidrug antibody positivity was 38.2% in patients who were treated with anti-TNF mAbs, 6.1% with etanercept, 50.0% with rituximab, and 20.0% with tocilizumab. There was an inverse association between antidrug antibody positivity (odds ratio [OR], 0.19; 95% CI, 0.09-0.38; P < .001) directed against all biologic drugs and EULAR response at month 12. Analyzing all the visits starting at month 6 using generalized estimating equation models confirmed the inverse association between antidrug antibody positivity and EULAR response (OR, 0.35; 95% CI, 0.18-0.65; P < .001). A similar association was found for tocilizumab alone (OR, 0.18; 95% CI, 0.04-0.83; P = .03). In the multivariable analysis, antidrug antibodies, body mass index, and rheumatoid factor were independently inversely associated with response to treatment. There was a significantly higher drug concentration of anti-TNF mAbs in patients with antidrug antibody-negative vs antidrug antibody-positive status (mean difference, -9.6 [95% CI, -12.4 to -6.9] mg/L; P < 001). Drug concentrations of etanercept (mean difference, 0.70 [95% CI, 0.2-1.2] mg/L; P = .005) and adalimumab (mean difference, 1.8 [95% CI, 0.4-3.2] mg/L; P = .01) were lower in nonresponders vs responders. Methotrexate comedication at baseline was inversely associated with antidrug antibodies (OR, 0.50; 95% CI, 0.25-1.00; P = .05).Conclusions and relevanceResults of this prospective cohort study suggest an association between antidrug antibodies and nonresponse to bDMARDs in patients with RA. Monitoring antidrug antibodies could be considered in the treatment of these patients, particularly nonresponders to biologic RA drugs.

Project description:BackgroundBiological disease-modifying antirheumatic drugs (bDMARDs) are effective in the treatment of rheumatoid arthritis. However, as bDMARDs may also lead to adverse events and are expensive, tapering them is of great clinical interest. Tapering according to disease activity-guided dose optimization (DGDO) does not seem to affect long term remission rates, but flares are frequent during this process. Our objective was to develop a model for the prediction of flares during bDMARD tapering using data from routine care and to evaluate its potential clinical impact.MethodsWe used a joint latent class model to repeatedly predict the probability of a flare occurring within the next 3 months. The model was developed using longitudinal data on disease activity (DAS28) and other routine care data from two clinics. Predictive accuracy was assessed in cross-validation and external validation was performed with data from the DRESS (Dose REduction Strategy of Subcutaneous tumor necrosis factor inhibitors) trial. Additionally, we simulated the reduction in number of flares and bDMARD dose when implementing the model as a decision aid during bDMARD tapering in the DRESS trial.ResultsData from 279 bDMARD courses were used for model development. The final model included two latent DAS28-trajectories, bDMARD type and dose, disease duration, and seropositivity. The area under the curve of the final model was 0.76 (0.69-0.83) in cross-validation and 0.68 (0.62-0.73) in external validation. In simulation of prediction-aided decisions, the mean number of flares over 18 months decreased from 1.21 (0.99-1.43) to 0.75 (0.54-0.96). The reduction in he bDMARD dose was mostly maintained, increasing from 54 to 64% of full dose.ConclusionsWe developed a dynamic flare prediction model, exclusively based on data typically available in routine care. Our results show that using this model to aid decisions during bDMARD tapering may significantly reduce the number of flares while maintaining most of the bDMARD dose reduction.Trial registrationThe clinical impact of the prediction model is currently under investigation in the PATIO randomized controlled trial (Dutch Trial Register number NL9798).

Project description:OBJECTIVE:To investigate whether calprotectin (S100A8/A9 or MRP8/14), an inflammatory complex released by monocytes, could indicate residual subclinical inflammation in rheumatoid arthritis (RA) patients who are in stable remission on disease-modifying anti-rheumatic drugs (DMARDs) and serve as a marker for disease flare after DMARD tapering. METHODS:We used data from two trials. Patients from the IMPROVED study had early (< 2 years) RA, and when they achieved disease activity score remission (DAS44 < 1.6), they stopped methotrexate to attempt drug-free remission. Patients from the RETRO study had established RA in stable remission (DAS28 < 2.6) and either tapered by 50% or stopped (biological or conventional) DMARDs. Circulating calprotectin at the tapering time point was determined by ELISA, and its predictive value for flare (loss of remission) within 12 months of DMARD tapering/stopping was determined. RESULTS:In both IMPROVED (n = 104) and RETRO (n = 57), patients that flared within 12 months had higher calprotectin at the moment of DMARD tapering/stopping. Twofold higher calprotectin at the moment of DMARD tapering/stopping was associated with an increased risk (odds ratio) of flare of 1.07 (95% CI 0.98-1.18, p = 0.14) in the IMPROVED and 3.62 (95% CI 1.76-7.46, p < 0.001) in the RETRO. Correcting for clinical predictors of flare (DAS at study inclusion, anti-CCP2 positivity, gender) did not change these estimates. The area under the receiver operating curve of calprotectin levels for predicting flare within 12 months was 0.63 (95% CIs 0.51-0.76) in the IMPROVED study and 0.80 (95% CIs 0.69 to 0.92) in the RETRO study. CONCLUSION:Circulating calprotectin levels in RA patients in remission on DMARDs are higher in patients that will flare upon DMARD tapering/stopping. Since the differences between the cohorts precluded definitive conclusions, more research is needed to determine whether calprotectin has prognostic value in predicting flare after attempting drug tapering in RA. TRIAL REGISTRATION:IMPROVED, ISRCTN11916566. RETRO, 2009-015740-42.

Project description:ImportanceBiosimilar drugs are potentially lower-cost versions of biologics that may improve access to therapy. However, there is a lack of adequate systematic reviews demonstrating equivalence between these drugs for the treatment of rheumatoid arthritis (RA).ObjectivesTo assess the efficacy, safety, and immunogenicity associated with biosimilars of adalimumab, etanercept, and infliximab compared with their reference biologics in patients with RA.Data sourcesMEDLINE via PubMed, Embase, Cochrane Central Register of Controlled Trials, and LILACS databases were searched from inception to September 2021.Study selectionHead-to-head randomized clinical trials (RCTs) of biosimilars of adalimumab, etanercept, and infliximab and their biologic reference drugs for RA were assessed.Data extraction and synthesisTwo authors independently abstracted all data. Meta-analysis was conducted with bayesian random effects using relative risks (RRs) for binary outcomes and standardized mean differences (SMDs) for continuous outcomes, with 95% credible intervals (CrIs) and trial sequential analysis. Specific domains were assessed for the risk of bias in equivalence and noninferiority trials. This study was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guideline.Main outcomes and measuresEquivalence was tested using prespecified margins for the American College of Rheumatology criteria, with at least 20% improvement in the core set measures (ACR20) (ie, RR, 0.94 to 1.06), and for the Health Assessment Questionnaire-Disability Index (HAQ-DI) (ie, SMD, -0.22 to 0.22). Secondary outcomes included 14 items measuring safety and immunogenicity.ResultsA total of 25 head-to-head trials provided data on 10 642 randomized patients with moderate to severe RA. Biosimilars met equivalence with reference biologics in terms of ACR20 response (24 RCTs with 10 259 patients; RR, 1.01; 95% CrI, 0.98 to 1.04; τ2 = 0.000) and change of HAQ-DI scores (14 RCTs with 5579 patients; SMD, -0.04; 95% CrI, -0.11 to 0.02; τ2 = 0.002) considering prespecified margins of equivalence. Trial sequential analysis found evidence for equivalence for ACR20 since 2017 and HAQ-DI since 2016. Overall, biosimilars were associated with similar safety and immunogenicity profiles compared with reference biologics.Conclusion and relevanceIn this systematic review and meta-analysis, biosimilars of adalimumab, infliximab, and etanercept were associated with clinically equivalent treatment effects compared with their reference biologics for the treatment of RA.

Project description:BackgroundRA flares are common and disabling. They are described in terms of worsening inflammation but pain and inflammation are often discordant. To inform treatment decisions, we investigated whether inflammatory and pain flares are discrete entities.MethodsPeople from the Early RA Network (ERAN) cohort were assessed annually up to 11 years after presentation (n = 719, 3703 person-years of follow up). Flare events were defined in 2 different ways that were analysed in parallel; DAS28 or Pain Flares. DAS28 Flares satisfied OMERACT flare criteria of increases in DAS28 since the previous assessment (≥1.2 points if active RA or ≥ 0.6 points if inactive RA). A ≥ 4.8-point worsening of SF36-Bodily Pain score defined Pain Flares. The first documented episode of each of DAS28 and Pain Flare in each person was analysed. Subgroups within DAS28 and Pain Flares were determined using Latent Class Analysis. Clinical course was compared between flare subgroups.ResultsDAS28 (45%) and Pain Flares (52%) were each common but usually discordant, with 60% of participants in DAS28 Flare not concurrently in Pain Flare, and 64% of those in Pain Flare not concurrently in DAS28 Flare. Three discrete DAS28 Flare subgroups were identified. One was characterised by increases in tender/swollen joint counts (14.4%), a second by increases in symptoms (13.1%), and a third displayed lower flare severity (72.5%). Two discrete Pain Flare subgroups were identified. One occurred following low disease activity and symptoms (88.6%), and the other occurred on the background of ongoing active disease and pain (11.4%). Despite the observed differences between DAS28 and Pain Flares, each was associated with increased disability which persisted beyond the flare episode.ConclusionFlares are both common and heterogeneous in people with RA. Furthermore our findings indicate that for some patients there is a discordance between inflammation and pain in flare events. This discrete flare subgroups might reflect different underlying inflammation and pain mechanisms. Treatments addressing different mechanisms might be required to reduce persistent disability after DAS28 and Pain Flares.

Dataset Information

Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs.

Background

Methods

Results

Conclusion

Publications

Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets