Machine-learning derived algorithms for prediction of radiographic progression in early axial spondyloarthritis

Un nouvel article scientifique intitulé «Machine-learning derived algorithms for prediction of radiographic progression in early axial spondyloarthritis» a été publié dans le journal Clin Exp Rheumatol.

Romain Garofoli, Matthieu Resche-Rigon, Christian Roux, Désirée van der Heijde, Maxime Dougados, Anna Moltó.

Objectives:

To compare machine learning (ML) to traditional models to predict radiographic progression in patients with early axial spondyloarthritis (axSpA).

Methods:

We carried out a prospective French multicentric DESIR cohort study with 5 years of follow-up that included patients with chronic back pain for <3 years, suggestive of axSpA. Radiographic progression was defined as progression at the spine (increase of at least 1 point of mSASSS scores/2 years) or at the sacroiliac joint (worsening of at least one grade of the mNY score between 2 visits). Statistical analyses were based on patients without any missing data regarding the outcome and variables of interest (295 patients).Traditional modelling: we performed a multivariate logistic regression model (M1); then variable selection with stepwise selection based on Akaike Information Criterion (stepAIC) method (M2), and Least Absolute Shrinkage and Selection Operator (LASSO) method (M3).ML modelling: using « SuperLearner » package on R, we modelled radiographic progression with stepAIC, LASSO, random forest, Discrete Bayesian Additive Regression Trees Samplers (DBARTS), Generalized Additive Models (GAM), multivariate adaptive polynomial spline regression (polymars), Recursive Partitioning And Regression Trees (RPART) and Super Learner. Accuracy of these models was compared based on their 10-fold cross-validated AUC (cv-AUC).

Results:

10-fold cv-AUC for traditional models were 0.79 and 0.78 for M2 and M3, respectively. The three best models in the ML algorithms were the GAM, the DBARTS and the Super Learner models, with 10-fold cv-AUC of: 0.77, 0.76 and 0.74, respectively.

Conclusions:

Two traditional models predicted radiographic progression as good as the eight ML models tested in this population.

Hip Pain Associated with Acetabular Dysplasia in Patients with Suspected Axial Spondyloarthritis: DESIR Cohort Data

Un nouvel article scientifique intitulé «Hip Pain Associated with Acetabular Dysplasia in Patients with Suspected Axial Spondyloarthritis: DESIR Cohort Data» a été publié dans le journal BMC Musculosketel Disord.

Dewi Guellec, Guillaume Prado, Corinne Miceli-Richard, Guillermo Carvajal-Alegria, Alain Saraux.

Objectives:

To determine whether acetabular dysplasia is associated with hip pain at physical examination among adults with recent-onset inflammatory back pain (IBP) suggesting axial spondyloarthritis (axSpA).

Methods:

This cross-sectional ancillary study was conducted on the prospective DESIR cohort, which enrolled patients aged 18-50 years who had recent-onset IBP. Two readers used antero-posterior pelvic radiographs to assess the Tönnis angle, acetabular angle (AA), lateral centre-edge angle (LCEA), and femoral head extrusion index (FHEI). Abnormality of one or more of these four variables defined acetabular dysplasia. Hip pain upon physical examination was assessed based on Ritchie’s articular index.

Results:

The overall prevalence of acetabular dysplasia was 22% (139/636). The proportion of females was higher in the group with acetabular dysplasia. Hip pain was found in 21% (29/139) of patients with versus 12% (59/497) without acetabular dysplasia (OR, 1.96; 95% CI, 1.20 to 3.20); the association was significant in males (OR, 3.14; 95% CI, 1.44 to 6.86) but not females (OR, 1.39; 95% CI, 0.74 to 2.62). Results were similar when acetabular dysplasia was defined on the basis of LCEA alone (OR, 2.15; 95% CI, 1.18 to 2.62).

Conclusion:

Among patients with recent-onset IBP suggesting axSpA, acetabular dysplasia was significantly associated with hip pain in males. Hip pain related to acetabular dysplasia might result in overdiagnosis of hip involvement by axSpA.

Keywords: Acetabular dysplasia; Axial Spondyloarthritis; Hip.

Bilan des projets scientifiques soumis et acceptés (juin 2022)

Un nouveau bilan du nombre de projets soumis et acceptés par le comité scientifique depuis le début de l’étude est accessible cliquer ici .

EULAR 2022

Lors du congrès de l’EULAR 2022 qui s’est déroulé du 1 au 4 juin 2022 à Copenhague , 1 abstract a été accepté pour une présentation :

▫ DETERMINANTS OF CLINICALLY IMPORTANT WORSENING IN EARLY AXIAL SpA: ANALYSIS OF THE DESIR COHORT OVER 5 YEARS. F. Hamitouche, S. Kumaradev, D. Van der Heijde, S. Ramiro, A. Sepriano, A. Molto.

DETERMINANTS OF CLINICALLY IMPORTANT WORSENING IN EARLY AXIAL SpA: ANALYSIS OF THE DESIR COHORT OVER 5 YEARS,
F. Hamitouche, S. Kumaradev, D. Van der Heijde, S. Ramiro, A. Sepriano, A. Moltó

Socio-demographic determinants in the evolution of pain in inflammatory rheumatic diseases: results from ESPOIR and DESIR cohorts

Un nouvel article scientifique intitulé «Socio-demographic determinants in the evolution of pain in inflammatory rheumatic diseases: results from ESPOIR and DESIR cohorts» a été publié dans le journal Observational Study Rheumatology (Oxford).

Kumaradev S, Roux C, Sellam J, Perrot S, Pham T, Dugravot A, Molto A.

Objective:

To determine whether socio-demographic factors are associated with heterogeneity in pain evolution in inflammatory rheumatic diseases (IRDs) after accounting for disease-specific characteristics in a system with universal health care.

Methods:

This analysis included the data from two prospective observational cohorts of early IRDs (ESPOIR for early RA and DESIR for early SpA). Data on pain was measured, respectively, on 13 and 9 occasions spanning 10 and 6 years of follow-up using the Short-Form 36 bodily pain score for 810 participants of ESPOIR, and 679 participants of DESIR. Linear mixed models were used to characterize differences in pain evolution as a function of age (tertiles), sex, ethnicity, education, marital, and professional status, after accounting for disease-related, treatment, lifestyle, and health factors.

Results:

While transitioning from early (disease duration ≤6 months for RA and ≤3 years for SpA) to long-standing disease, differences in pain evolution emerged as a function of age (P < 0.001), sex (P = 0.050), and ethnicity (P = 0.001) in RA, and as a function of age (P = 0.048) in SpA; younger age, males, and Caucasians exhibited lower pain in the latter phases of both diseases. Highly educated participants (RA, β = -3.8, P = 0.007; SpA, β = -6.0, P < 0.001) for both diseases, and Caucasians (β = -5.6, P = 0.021) for SpA presented with low pain early in the disease, with no changes throughout disease course.

Conclusion:

Being older, female, non-Caucasian and having lower education was found to be associated with worse pain in early and/or long-standing IRDs, despite universally accessible health-care. Early identification of at-risk populations and implementation of multidisciplinary strategies may reduce patient-reported health outcome disparities.

Trial registration registrations: ESPOIR: ClinicalTrials.gov, www.clinicaltrials.gov, NCT03666091. DESIR: ClinicalTrials.gov, www.clinicaltrials.gov, NCT01648907.

Keywords: pain evolution; pain outcome; rheumatoid arthritis; socio-demographic factors; spondyloarthritis.

Factors associated with drug-free remission at 5-year in early onset axial spondyloarthritis patients: Data from the DESIR cohort

Un nouvel article scientifique intitulé «Factors associated with drug-free remission at 5-year in early onset axial spondyloarthritis patients: Data from the DESIR cohort» a été publié dans le journal Joint Bone Spine.

Adeline Ruyssen-Witrand, Vanessa Rousseau, Agnès Sommet, Philippe Goupille, Yannick Degboe, Arnaud Constantin.

Objectives:

To assess the frequency of patients in drug-free remission at 5 years in a cohort of early axial SpA, and the factors associated with this remission.

Methods:

Patients: patients included in the DESIR (DEvenir des Spondyloarthropathies Indifférenciées Récentes) cohort undergoing the 5-year visit were selected for this analysis. Definition of 5-year drug-free remission: (1) all patients in ASAS partial remission and/or ASDAS<1.3 at 5 year visit and (2) taking no disease modifying anti-rheumatic drugs at the 5-year visit and (3) with an ASAS-NSAID score≤25 at the 5-year visit.

Data analysis:

the proportion of patients in drug-free remission was described. The association between demographic, clinical, biological and imaging characteristics and drug-free remission at 5 years was assessed by logistic regression.

Results:

Of the 412 patients included in this analysis, 73 (18%) were in drug-free remission at the 5-year visit. The baseline clinical factors associated with the chances to be in drug-free remission at the 5-year visit were symptom duration (OR=0.66 [95%CI%: 0.44-0.97]), lower HAQ-AS score (OR=0.32 [0.12-0.78]), lower ASDAS score (OR=0.55 [95%CI: 0.34-0.86]), ASAS-NSAID score (OR=0.91 [95%CI: 0.82-0.99]). Furthermore, anti-TNF use (OR=0.20 [95%CI: 0.08-0.42]) during the follow-up decreased the chances of being in 5-year drug-free remission.

Conclusion:

The probability of being in drug free remission at 5 year when beginning an axial SpA is low and is associated with lower baseline disease activity and functional scores, while starting an anti-TNF is associated with poor chances of later being in drug-free remission. NCT01648907.

Keywords: Anti-TNF; Remission; Spondyloarthritis; Therapy.

Imaging Outcomes for Axial Spondyloarthritis and Sensitivity to Change: A Five-Year Analysis of the DESIR Cohort

Un nouvel article scientifique intitulé «Imaging Outcomes for Axial Spondyloarthritis and Sensitivity to Change: A Five-Year Analysis of the DESIR Cohort» a été publié dans le journal Arthritis Care Res (Hoboken).

Alexandre Sepriano, Sofia Ramiro, Désirée van der Heijde, Maxime Dougados, Pascal Claudepierre, Antoine Feydy, Monique Reijnierse, Damien Loeuille, Robert Landewé.

Objective:

To compare the sensitivity to change of different imaging scoring methods in patients with early axial spondyloarthritis (SpA).

Methods:

Patients from the Devenir des Spondylarthropathies Indifferérenciées Récentes (DESIR) cohort fulfilling the Assessment of SpondyloArthritis international Society criteria for axial SpA were included. Radiographs and magnetic resonance imaging (MRI) of the sacroiliac (SI) joints and spine were obtained at baseline, 1, 2, and 5 years. Each image was scored by 2 or 3 readers in 3 separate reading waves. The rate of change of outcomes measuring inflammation of the spine and SI joints (e.g., Spondyloarthritis Research Consortium of Canada [SPARCC] score) and structural damage on MRI (e.g., ≥3 fatty lesions) and radiographs (e.g., modified New York grading) was assessed using multilevel generalized estimating equation models (taking all readers and waves into account). To allow comparisons across outcomes, rates were standardized (difference between the individual’s value and the population mean divided by the SD).

Results:

In total, 345 patients were included. Inflammation detected on MRI of the SI joints (MRI-SI joints) (standardized rate range -0.278, -0.441) was more sensitive to change compared to spinal inflammation (range -0.030, -0.055). Structural damage in the SI joints showed a higher standardized rate of change on MRI-SI joints (range 0.015, 0.274) compared to radiography of the SI joints (range 0.043, 0.126). MRI-SI joints damage defined by ≥3 fatty lesions showed the highest sensitivity to change (0.274). Spinal structural damage slowly progressed over time with no meaningful difference between radiographic (range 0.037, 0.043) and MRI structural outcomes (range 0.008, 0.027).

Conclusion:

Structural damage assessed in pelvic radiographs has low sensitivity to change, while fatty lesions detected on MRI-SI joints are a promising alternative. In contrast, MRI of the spine is not better than radiography of the spine in detecting structural changes in patients with early axial SpA.

Evaluation of long-term TNFi effectiveness after a first switch in early axial spondyloarthritis considering time-varying prescription bias: an inverse-probability weighting analysis of the DESIR cohort

Un nouvel article scientifique intitulé «Evaluation of long-term TNFi effectiveness after a first switch in early axial spondyloarthritis considering time-varying prescription bias: an inverse-probability weighting analysis of the DESIR cohort» a été publié dans le journal RMD Open.

Marion Pons, Sylvie Chevret, Karine Briot, Maria-Antonietta d’Agostino, Christian Roux, Maxime Dougados, Anna Molto.

Objective:

To evaluate long-term effectiveness of tumour necrosis factor inhibitor (TNFi) after a first switch, and their associated factors in an early axial spondyloarthritis (axSpA) population, considering time-varying prescription bias.

Methods:

Observational prospective cohort (DEvenir des Spondylarthropathies Indifférenciées Récentes) with 5 years of follow-up, including 708 TNFi-naïve patients with early axSpA. Long-term effectiveness of TNFi after a first switch (ASAS40 response after at least 2 visits under treatment) were estimated using marginal structural models (implementing inverse-probability weighting and iterative propensity scores). Factors associated with the outcome were explored by multivariate Cox regression models.

Results:

The hazard to present an ASAS40 response after a first TNFi switch was increased (HR=2.4 (95% CI 1.9 to 3.0)); this response ratio was slightly lower compared with the response in TNFi naïve patients after a first TNFi (HR=3.3 (95% CI 2.9 to 3.8)). HLA-B27 positive was the only factor independently associated with ASAS40 response after a first TNFi switch.

Conclusion:

After application of innovative methods to overcome time-varying prescription bias, the magnitude of the TNFi response after a first switch was found to be numerically lower but clinically relevant from the response in TNFi-naïve patients.

Keywords: ankylosing; epidemiology; spondylitis; tumour necrosis factor inhibitors.

Prevalence and consequences of psoriasis in recent axial spondyloarthritis: an analysis of the DESIR cohort over 6 years

Un nouvel article scientifique intitulé «Prevalence and consequences of psoriasis in recent axial spondyloarthritis: an analysis of the DESIR cohort over 6 years» a été publié dans le journal RMD Open.

Florian Lucasson, Pascal Richette, Krystel Aouad, Adeline Ryussen-Witrand, Daniel Wendling, Bruno Fautrel, Laure Gossec.

Objectives:

The consequences of psoriasis associated to axial spondyloarthritis (axSpA) are unclear. The objectives were to determine the prevalence and the consequences of psoriasis in recent axSpA over 6 years of follow-up.

Methods:

The multicentric prospective cohort DESIR (NCT01648907) of adult patients with recent inflammatory back pain suggestive of axSpA was analysed over 6 years. Psoriasis was recorded at each visit and cumulative prevalence and incidence were calculated. Patients with vs without psoriasis at any time point were compared. Outcomes included disease activity (Ankylosing Spondylitis Disease Activity Score-C reactive protein (ASDAS-CRP), joint and enthesitis count, CRP), patient-reported outcomes for function (Health Assessment Questionnaire for axSpA, HAQ-AS) and quality of life, and treatment use over 6 years. Outcomes were compared through univariable and multivariable analyses, as well as linear mixed effect models.

Results:

In 589 patients, mean age 40.5±8.7 years, 45.8% men and baseline mean symptom duration 1.5±0.9 years, the cumulative prevalence of psoriasis increased from 16.8% (99/589) at baseline to 26.8% (158/589) at 6 years, leading to an incidence of 2.1/100 patient-years. Over 6 years of follow-up, patients with psoriasis developed more synovitis (p=0.008), and received more methotrexate (cumulative use, 25.5% vs 11.8%, p<0.001) and biological disease-modifying drugs (55.7% vs 38.5%, p<0.001). There were no significant consequences of psoriasis on other outcomes, including disease activity (ASDAS-CRP), functional capacity (HAQ-AS) and quality of life.

Conclusion:

Psoriasis is frequent in early axSpA. AxSpA patients with psoriasis had more swollen joints over time and received more biologics; they did not have worse outcomes related to axSpA in terms of activity and severity.

Keywords: ankylosing; biological therapy; patient reported outcome measures; spondylitis.

Cluster analysis in early axial spondyloarthritis predicts poor outcome in the presence of peripheral articular manifestations

Un nouvel article scientifique intitulé «Cluster analysis in early axial spondyloarthritis predicts poor outcome in the presence of peripheral articular manifestations» a été publié dans le journal Rheumatology (Oxford).

Costantino F, Aegerter P, Schett G, De Craemer AS, Molto A, Van den Bosch F, Elewaut D, Breban M, D’Agostino MA.

Objectives:

To assess whether two cluster analysis-based axial SpA (axSpA) endotypes (A for purely axial; B for both axial and peripheral) are stable over time and are associated with different long-term disease outcomes.

Methods:

K-means cluster analysis was performed at each visit (until 5 years) on 584 patients from the DESIR cohort, who completed all planned visits, and validated in 232 consecutive axSpA patients from the BeGiant cohort. Cluster stability overtime was assessed by kappa statistics. A generalized linear mixed-effect analysis was applied to compare outcomes between clusters. Classification and regression tree (CART) analysis was performed to determine a decision rule able to assign a given patient to a definite cluster at onset.

Results:

Both endotypes remained remarkably stable over time. In the DESIR cohort, patients in cluster B showed higher disease activity, worse functional outcome and higher need for anti-rheumatic drugs than patients in cluster A. CART analysis yielded three main clinical features (arthritis, enthesitis, and dactylitis) that accurately determined cluster assignment. These results could be replicated in the Be-GIANT cohort.

Conclusion:

Cluster-based axSpA endotypes were reproducible in two different cohorts, stable over time and associated with different long-term outcome. The axSpA endotype with additional peripheral disease manifestations is associated with more severe disease and requires more intensive drug therapy.

Keywords: cluster analysis; disease endotypes; outcome; progression; spondyloarthritis.