Diagnostic accuracy in axial spondyloarthritis: a systematic evaluation of the role of clinical information in the interpretation of sacroiliac joint imaging.

OBJECTIVES: Radiography and MRI of the sacroiliac joints (SIJ) are relevant for the diagnosis and classification of patients with axial spondyloarthritis (axSpA). This study aimed to evaluate the impact of clinical information (CI) on the accuracy of imaging interpretation. METHODS: Out of 109 patients referred because of suspicion of axSpA with complete imaging sets (radiographs and MRI of SIJ), 61 were diagnosed with axSpA (56%). Images were independently evaluated by three radiologists in four consecutive reading campaigns: radiographs and radiographs+MRI without and with CI including demographic data, SpA features, physical activity and pregnancy. Radiographs were scored according to the modified New York criteria, and MRIs for inflammatory and structural changes compatible with axSpA (yes/no). The clinical diagnosis was taken as reference standard. The compatibility of imaging findings with a diagnosis of axSpA (precision) before and after the provision of CI and radiologists' confidence with their findings (0-10) were evaluated. RESULTS: The precision of radiographs evaluation without versus with CI increased from 70% to 78% (p=0.008), and for radiographs+MRI from 81% to 82% (p=1.0), respectively. For CR alone, the sensitivity and specificity of radiologic findings were 51% and 94% without and 60% and 100% with CI, while, for radiographs+MRI, they were 74% and 90% vs 71% and 98%, respectively. The diagnostic confidence of radiologists increased from 5.2±1.9 to 6.0±1.7 with CI for radiographs, and from 6.7±1.6 to 7.2±1.6 for radiographs+MRI, respectively. CONCLUSION: The precision, specificity and diagnostic confidence of radiologic evaluation increased when CI was provided.

Frequency and the effects of spondyloarthritis-spectrum disorders on the clinical course and management of Takayasu arteritis: an observational retrospective study.

OBJECTIVES: Extravascular findings of Takayasu arteritis (TAK) often share features with the spondyloarthritis (SpA) spectrum of disorders. However, the characteristics of this overlap and its effect on the vascular manifestations of TAK are not fully known. Therefore, we aimed to investigate the frequency of SpA-related features in TAK patients. MATERIAL AND METHODS: In this observational retrospective study, 350 patients with TAK classified according to ACR 1990 criteria, from 12 tertiary rheumatology clinics, were included and evaluated for the presence of axSpA, IBD, or psoriasis. Demographic, clinical features, angiographic involvement patterns, disease activity, and treatments of TAK patients with or without SpA were analyzed. RESULTS: Mean age was 45.5 ± 13.6 years and mean follow-up period was 76.1 ± 65.9 months. Among 350 patients, 31 (8.8%) had at least one additional disease from the SpA spectrum, 8 had IBD, 8 had psoriasis, and 20 had features of axSpA. In the TAK-SpA group, TAK had significantly earlier disease onset, compared to TAK-without-SpA (p = 0.041). SpA-related symptoms generally preceded TAK symptoms. Biological treatments, mostly for active vasculitis, were higher in the TAK-SpA group (70.9%) compared to TAK-without-SpA (27.9%) (p < 0.001). Vascular involvements were similar in both. CONCLUSION: Our study confirmed that diseases in the SpA spectrum are not rare in TAK. Vascular symptoms appeared earlier in such patients, and more aggressive therapy with biological agents was required in the TAK-SpA group, suggesting an association between TAK and SpA spectrum. Key Points • The pathogenesis of Takayasu arteritis is mediated by an MHC class I alelle (HLA-B*52), similar to spondyloarthritis-disorders. • Extravascular findings of Takayasu arteritis are in the spectrum of spondyloarthritis disease. • This frequent coexistence between Takayasu arteritis and spondyloarthritic disorders suggests a relationship rather than a coincidence.

Learning imaging in axial spondyloarthritis: more than just a matter of experience.

OBJECTIVE: Reliable interpretation of imaging findings is essential for the diagnosis of axial spondyloarthritis (axSpA) and requires a high level of experience. We investigated experience-dependent differences in diagnostic accuracies using X-ray (XR), MRI and CT. METHODS: This post hoc analysis included 163 subjects with low back pain. Eighty-nine patients had axSpA, and 74 patients had other conditions (mechanical, degenerative or non-specific low back pain). Final diagnoses were established by an experienced rheumatologist before the reading sessions. Nine blinded readers (divided into three groups with different levels of experience) scored the XR, CT and MRI of the sacroiliac joints for the presence versus absence of axSpA. Parameters for diagnostic performance were calculated using contingency tables. Differences in diagnostic performance between the reader groups were assessed using the McNemar test. Inter-rater reliability was assessed using Fleiss kappa. RESULTS: Diagnostic performance was highest for the most experienced reader group, except for XR. In the inexperienced and semi-experienced group, diagnostic performance was highest for CT&MRI (78.5% and 85.3%, respectively). In the experienced group, MRI showed the highest performance (85.9%). The greatest difference in diagnostic performance was found for MRI between the inexperienced and experienced group (76.1% vs 85.9%, p=0.001). Inter-rater agreement was best for CT in the experienced group with κ=0.87. CONCLUSION: Differences exist in the learnability of the imaging modalities for axSpA diagnosis. MRI requires more experience, while CT is more suitable for inexperienced radiologists. However, diagnosis relies on both clinical and imaging information.

Increased carotid intima-media thickness in patients with radiographic axial spondyloarthritis compared to controls and associations with markers of inflammation.

OBJECTIVE: There is an increased risk for cardiovascular disease (CVD) in patients with radiographic axial spondyloarthritis (r-axSpA). In this cross-sectional study, we aimed to, overall and stratified by sex, (i) compare ultrasound derived carotid intima media thickness (cIMT), between patients and controls, and (ii) investigate associations between cIMT, clinical disease activity and inflammation-related laboratory markers in patients with r-axSpA. METHOD: In total, 155 patients diagnosed with r-axSpA using the modified New York criteria and 400 controls were included. Bilateral carotid ultrasound, laboratory testing, and questionaries were acquired. Disease-specific assessments were carried out for patients. Linear regression analysis was used to assess associations. RESULTS: Linear regression analyses showed that patients with r-axSpA had increased mean cIMT compared to controls (mean ± SD, 0.8 ± 0.1 mm vs 0.7± 0.1 mm, respectively, unstandardized ß (95% CI) -0.076 (-0.10, -0.052), P < 0.001) adjusted for smoking status and age. Linear regression analyses for patients with r-axSpA showed that only males presented significant associations between cIMT and inflammation-related laboratory markers, white blood cell (WBC) count (mean ± SD, 6.8 ± 1.6 109/L) and monocytes (0.6 ± 0.2 109/L); WBC count (unstandardized ß (95% CI) 0.019 (0.0065, 0.031), P = 0.003, R2 = 0.57) and monocytes (0.13 (0.0047, 0.26), P = 0.041, R2 = 0.55), adjusted for age, smoking status, body mass index, hypertension, dyslipidemia, diabetes mellitus, ASDAS-CRP, and treatment with DMARDs and glucocorticoids. No significant association was found between cIMT and clinical disease activity assessed by ASDAS-CRP. CONCLUSION: Patients with r-axSpA had significantly increased cIMT compared to controls. In male patients, higher WBC and monocyte count were associated with an increase in cIMT suggesting the role of inflammation in the development of atherosclerosis. Key Points •Carotid intima-media thickness was increased in patients with radiographic axial spondyloarthritis compared to controls. •White blood cell and monocyte counts were associated with carotid intima-media thickness in male patients with radiographic axial spondyloarthritis.

Molecular Profiling of Axial Spondyloarthritis Patients Reveals an Association between Innate and Adaptive Cell Populations and Therapeutic Response to Tumor Necrosis Factor Inhibitors.

This study aims at identifying molecular biomarkers differentiating responders and non-responders to treatment with Tumor Necrosis Factor inhibitors (TNFi) among patients with axial spondyloarthritis (axSpA). Whole blood mRNA and plasma proteins were measured in a cohort of biologic-naïve axSpA patients (n = 35), pre and post (14 weeks) TNFi treatment with adalimumab. Differential expression analysis was used to identify the most enriched pathways and in predictive models to distinguish responses to TNFi. A treatment-associated signature suggests a reduction in inflammatory activity. We found transcripts and proteins robustly differentially expressed between baseline and week 14 in responders. C-reactive protein (CRP) and Haptoglobin (HP) proteins showed strong and early decrease in the plasma of axSpA patients, while a cluster of apolipoproteins (APOD, APOA2, APOA1) showed increased expression at week 14. Responders to TNFi treatment present higher levels of markers of innate immunity at baseline, and lower levels of adaptive immunity markers, particularly B-cells. A logistic regression model incorporating ASDAS-CRP, gender, and AFF3, the top differentially expressed gene at baseline, enabled an accurate prediction of response to adalimumab in our cohort (AUC = 0.97). In conclusion, innate and adaptive immune cell type composition at baseline may be a major contributor to response to adalimumab in axSpA patients. A model including clinical and gene expression variables should also be considered.

PIM Kinases as Potential Biomarkers and Therapeutic Targets in Inflammatory Arthritides.

The Proviral Integration site for the Moloney murine leukemia virus (PIM)-1 kinase and its family members (PIM-2 and PIM-3) regulate several cellular functions including survival, proliferation, and apoptosis. Recent studies showed their involvement in the pathogenesis of rheumatoid arthritis RA, while no studies are available on psoriatic arthritis (PsA) and axial spondyloarthritis (axSpA). The main objective of this study is to assess the expression of PIM kinases in inflammatory arthritides, their correlation with proinflammatory cytokines, and their variation after treatment with biologic disease-modifying anti-rheumatic drugs or JAK inhibitors. We evaluated PIM-1, -2, and -3 expression at the gene and protein level, respectively, in the peripheral blood mononuclear cells and serum of patients with RA, PsA, axSpA, and healthy individuals (CTR). All the samples showed expression of PIM-1, -2, and -3 kinases both at the gene and protein level. PIM-1 was the most expressed protein, PIM-3 the least. PIM kinase levels differed between controls and disease groups, with reduced PIM-1 protein and increased PIM-3 protein in all disease samples compared to controls. No difference was found in the expression of these molecules between the three different pathologies. PIM levels were not modified after 6 months of therapy. In conclusion, our preliminary data suggest a deregulation of the PIM pathway in inflammatory arthritides. In-depth studies on the role of PIM kinases in this field are warranted.

Barriers and facilitators in diagnosing axial spondyloarthritis: a qualitative study.

INTRODUCTION: Diagnosis of axial spondyloarthritis (axSpA) is frequently delayed for years after symptom onset. However, little is known about patient and healthcare professional (HCP) perspectives on barriers and facilitators in axSpA diagnosis. This study explored the experiences and perceptions of both groups regarding the factors affecting the timely diagnosis of axSpA. METHOD: Semi-structured interviews with patients with axSpA and axSpA-interested HCPs from the United Kingdom (UK) were performed by telephone or Microsoft Teams and focussed on the individuals' perspective of the diagnostic journey for axSpA. Interview transcripts were thematically analysed. RESULTS: Fourteen patients with axSpA (10 female, 4 male) and 14 UK based HCPs were recruited, the latter comprising of 5 physiotherapists, 4 General Practitioners, 3 rheumatologists, a nurse, and an occupational therapist. Barriers to diagnosis identified by patients and HCPs were: difficult to diagnose, a lack of awareness, unclear referral pathways, patient behaviour and patient/HCP communication. Patient-identified facilitators of diagnosis were patient advocacy, clear referral processes and pathways, increased awareness, and serendipity. HCPs identified promoting awareness as a facilitator of diagnosis, along with symptom recognition, improvements to healthcare practice and patient/HCP communications. CONCLUSION: Poor communication and a lack of understanding of axSpA in the professional and public spheres undermine progress towards timely diagnosis of axSpA. Improving communication and awareness for patients and HCPs, along with systemic changes in healthcare (such as improved referral pathways) could reduce diagnostic delay.

Fear of movement and competence frustration mediate the relationship between pain catastrophising and physical function in people living with axSpA: an online cross-sectional survey.

The objective of this study is to examine the contribution of pain catastrophising to Axial Spondyloarthritis (axSpA) patient's physical function and to test the mediating role of fear of movement, and uniquely, the contribution of competence frustration to the fear-avoidance model. Participants (N = 98, 70% female, M age = 45.62, SD 12.16) completed an online survey (December 2020-May 2021) distributed in the United Kingdom via the National Axial Spondyloarthritis Society (n ≈ 3500; NASS, 2019). The PROCESS SPSS macro was used to test three mediation models using percentile bootstrap 95% confidence intervals (PBCI). A significant indirect effect on the relationship between pain and physical function via fear of movement (ß = 0.10, 95% PBCI = 0.030-0.183) was observed (Model 1). Model 2 showed the relationship between pain catastrophising and physical function to be significantly mediated by fear of movement (ß = 0.16, 95% PBCI = 0.005-0.322). Finally, Model 3 showed a significant indirect effect on the relationship between pain catastrophising and physical function via competence frustration (ß = 0.15, 95% PBCI = 0.014-0.309) but not through fear of movement (ß = 0.062, 95% PBCI = - 0.134 to 0.248). To our knowledge, this is the first study to examine and demonstrate the unique contribution of competence need frustration to the Fear-avoidance model in people that live with axSpA. Identifying modifiable factors that contribute to disease outcomes such as physical function can improve the care and quality of life for people living with a disease currently without a cure.

Pain in axial spondyloarthritis: role of the JAK/STAT pathway.

Axial spondyloarthritis (axSpA) is a chronic inflammatory disease that is characterized by new bone formation in the axial musculoskeletal system, with X-ray discriminating between radiographic and non-radiographic forms. Current therapeutic options include non-steroidal anti-inflammatory drugs in addition to biological disease-modifying anti-rheumatic drugs that specifically target tumor necrosis factor-alpha (TNFα) or interleukin (IL)-17. Pain is the most critical symptom for axSpA patients, significantly contributing to the burden of disease and impacting daily life. While the inflammatory process exerts a major role in determining pain in the early phases of the disease, the symptom may also result from mechanical and neuromuscular causes that require complex, multi-faceted pharmacologic and non-pharmacologic treatment, especially in the later phases. In clinical practice, pain often persists and does not respond further despite the absence of inflammatory disease activity. Cytokines involved in axSpA pathogenesis interact directly/indirectly with the Janus kinase (JAK)/signal transducer and activator of transcription (STAT) signaling cascade, a fundamental component in the origin and development of spondyloarthropathies. The JAK/STAT pathway also plays an important role in nociception, and new-generation JAK inhibitors have demonstrated rapid pain relief. We provide a comprehensive review of the different pain types observed in axSpA and the potential role of JAK/STAT signaling in this context, with specific focus on data from preclinical studies and data from clinical trials with JAK inhibitors.

Factors associated with acute anterior uveitis history in patients with axial spondyloarthritis: Results of a longitudinal study.

BACKGROUNDS: Acute anterior uveitis (AAU) is the most common extra-musculoskeletal manifestation in axial spondyloarthritis (axSpA). OBJECTIVES: The aim of the study is to evaluate the factors associated with AAU attacks in patients with axSpA during a 36-month follow-up period. METHODS: In total, 469 patients with axSpA were included in this observational study. Demographic data, clinical characteristics, disease activity measurements, and treatment patterns were compared between patients with and without a history of AAU. The development of AAU and its related factors were investigated using generalized estimating equations, which is a technique for longitudinal data analysis. RESULTS: Overall, 99 (21%) out of 469 patients experienced at least one AAU attack, with 77 patients (78%) having a history of AAU and 53 patients (58% of whom had a history of AAU) experiencing AAU attacks during the follow-up period. At baseline, patients with a history of AAU were found to be older (p = .001), be more likely to have peripheral arthritis (p < .001), have higher serum CRP levels (p = .016), have a higher frequency of sulfasalazine (SLZ) and tumor necrosis factor inhibitors (TNFi) use (p < .001 and p < .001, respectively). In the longitudinal analysis, having a history of AAU was identified as the only independent determinant of the development of AAU. CONCLUSIONS: AAU history might be a risk factor for the development of AAU attacks in patients with axSpA. Although TNFi and SLZ were prescribed more frequently to patients with a history of AAU, the effectiveness of these agents in preventing further AAU attacks was not demonstrated.

Impact of the time of initiation and line of biologic therapy on the retention rate of secukinumab in axial spondyloarthritis (axSpA): data from the French multicentre retrospective FORSYA study.

OBJECTIVE: To compare the 1-year retention rate of secukinumab in axial spondyloarthritis (axSpA) and its predisposing factors with regard to its time of initiation (eg, right after or remotely from its launch). METHODS: Study design: Retrospective multicentre French study of patients with axSpA. Study periods: Two cohorts were evaluated regarding the time of initiation of secukinumab: cohort 1 (C1)-between 16 August 2016 and 31 August 2018-and cohort 2 (C2)-between 1 September 2018 and 13 November 2020. STATISTICAL ANALYSIS: The 1-year retention rate of secukinumab was estimated using the Kaplan-Meier method, and the log-rank test was used to compare the retention curves of the two cohorts. Preselected factors (eg, disease characterristics, line and time of secukinumab initiation) of secukinumab retention at 1 year were analysed by univariate and multivariate Cox model regression. RESULTS: In total, 906 patients in C1 and 758 in C2 from 50 centres were included in the analysis. The 1-year retention rate was better in C2 (64% (61%-68%)) vs C1 (59% (55%-62%)) (HR=1.19 (1.02-1.39); p=0.0297). In the multivariate analysis, the line of biologic therapy was the single predictive factor of the 1-year retention rate of secukinumab picked up in both cohorts, with a better retention rate when prescribed as first-line biologic therapy. CONCLUSION: The better secukinumab retention rate remotely from its launch is explained by its use at an earlier stage of the disease, suggesting a change in the behaviour of prescribing physicians. Our results emphasise the relevance of iterative evaluations of routine care treatments.

The bright Easter bunny sign: a useful aide-memoire on MRI for costotransverse joint inflammation in axial spondyloarthritis.

AIM: To assess the significance of the "bright Easter bunny" sign on magnetic resonance imaging (MRI) to indicate inflammatory costotransverse joint (CtJ) lesions to diagnose axial spondyloarthritis (ax-SpA). MATERIALS AND METHODS: Consecutive cases of patients with ax-SpA from a specialist rheumatology clinic were analysed retrospectively over two cohorts, between 2012-2014 and 2018-2020, to determine newly diagnosed patients under the Assessment of SpondyloArthritis international Society (ASAS) criteria. Biological naive adult patients who underwent spine MRI and sacroiliac imaging with full immunological work-up and a C-reactive protein reading within 3 months of the scan were included. Blinded images were reviewed by experienced musculoskeletal radiologists. RESULT: From the 1,284 cases that were identified, 40 cases met the inclusion criteria for this study. Seven out of the 40 cases (17.5%) identified inflammatory lesions at the CtJ with five (70%) showing concordance with the bright Easter bunny sign. CONCLUSION: The bright Easter bunny sign is concordant with inflammatory costotransverse enthesitis. This aide-memoire radiological sign is often on overlooked edge-of-field sections and this emphasises the need to ensure adequate coverage of the CtJ on spine MRI protocols as an important anatomical site of inflammatory change in ax-SpA assessment.

Change of perspective: impact of COVID-19 pandemic on axial spondyloarthritis-related web searches in Germany.

Several conventional cross-sectional studies have investigated the impact of the coronavirus disease (COVID-19) pandemic on patients with axial spondyloarthritis (axSpA) and reached contrary results regarding health and well-being. As analysis of web search data already provided insights into public interest and unmet needs, this study aimed to examine axSpA-related web searches before and during COVID-19 pandemic to gain a different perspective on the impact of COVID-19 on this disease. The Google Ads Keyword Planner was used to generate axSpA-related keywords and their monthly number of searches between June 2018 and November 2021 in Germany. These keywords were qualitatively classified into seven categories. A total of 538 axSpA-related keywords were used for the analysis. The number of axSpA-related searches increased during COVID-19 pandemic (before: n = 1,525,010 vs. during: n = 1,848,300), particularly searches for symptoms, disease outcomes, and causes, while interest in disease management and diagnosis decreased. This study demonstrated a shift in public interest in axSpA during COVID-19 in Germany and highlights an urgent expansion of telemedicine to be prepared for exceptional situations such as a pandemic.

Sequence of Events in the Pathogenesis of Axial Spondyloarthritis: A Current Review-2023 SPARTAN Meeting Proceedings.

PURPOSE OF REVIEW: Over the past two decades, significant progress has been made to untangle the etiology of inflammation and new bone formation (NBF) associated with axial spondyloarthritis (axSpA). However, exact mechanisms as to how the disease initiates and develops remain elusive. RECENT FINDINGS: Type 3 immunity, centered around the IL-23/IL-17 axis, has been recognized as a key player in the pathogenesis of axSpA. Multiple hypotheses associated with HLA-B*27 have been proposed to account for disease onset and progression of axSpA, potentially by driving downstream T cell responses. However, HLA-B*27 alone is not sufficient to fully explain the development of axSpA. Genome-wide association studies (GWAS) identified several genes that are potentially relevant to disease pathogenesis leading to a better understanding of the immune activation seen in axSpA. Furthermore, gut microbiome studies suggest an altered microbiome in axSpA, and animal studies suggest a pathogenic role for immune cells migrating from the gut to the joint. Recent studies focusing on the pathogenesis of new bone formation (NBF) have highlighted the importance of endochondral ossification, mechanical stress, pre-existing inflammation, and activated anabolic signaling pathways during the development of NBF. Despite the complex etiology of axSpA, recent studies have shed light on pivotal pieces that could lead to a better understanding of the pathogenic events in axSpA.

Patient-reported outcomes in axial spondyloarthritis and psoriatic arthritis patients treated with secukinumab for 24 months in daily clinical practice.

OBJECTIVES: In patients with axial spondyloarthritis (axSpA) or psoriatic arthritis (PsA) initiating secukinumab, we aimed to assess and compare the proportion of patients achieving 6-, 12- and 24-month patient-reported outcomes (PRO) remission and the 24-month retention rates. PATIENTS AND METHODS: Patients with axSpA or PsA from 16 European registries, who initiated secukinumab in routine care were included. PRO remission rates were defined as pain, fatigue, Patient Global Assessment (PGA) ≤2 (Numeric Rating Scale (NRS) 0-10) and Health Assessment Questionnaire (HAQ) ≤0.5, for both axSpA and PsA, and were calculated as crude values and adjusted for drug adherence (LUNDEX). Comparisons of axSpA and PsA remission rates were performed using logistic regression analyses (unadjusted and adjusted for multiple confounders). Kaplan-Meier plots with log-rank test and Cox regression analyses were conducted to assess and compare secukinumab retention rates. RESULTS: We included 3087 axSpA and 3246 PsA patients initiating secukinumab. Crude pain, fatigue, PGA and HAQ remission rates were higher in axSpA than in PsA patients, whereas LUNDEX-adjusted remission rates were similar. No differences were found between the patient groups after adjustment for confounders. The 24-month retention rates were similar in axSpA vs. PsA in fully adjusted analyses (HR [95 %CI] = 0.92 [0.84-1.02]). CONCLUSION: In this large European real-world study of axSpA and PsA patients treated with secukinumab, we demonstrate for the first time a comparable effectiveness in PRO remission and treatment retention rates between these two conditions when adjusted for confounders.

Entry point of machine learning in axial spondyloarthritis.

Axial spondyloarthritis (axSpA) is a globally prevalent and challenging autoimmune disease. Characterised by insidious onset and slow progression, the absence of specific clinical manifestations and biomarkers often leads to misdiagnosis, thereby complicating early detection and diagnosis of axSpA. Furthermore, the high heterogeneity of axSpA, its complex pathogenesis and the lack of specific drugs means that traditional classification standards and treatment guidelines struggle to meet the demands of personalised treatment. Recently, machine learning (ML) has seen rapid advancements in the medical field. By integrating large-scale data with diverse algorithms and using multidimensional data, such as patient medical records, laboratory examinations, radiological data, drug usage and molecular biology information, ML can be modelled based on real-world clinical issues. This enables the diagnosis, stratification, therapeutic efficacy prediction and prognostic evaluation of axSpA, positioning it as an emerging research topic. This study explored the application and progression of ML in the diagnosis and therapy of axSpA from five perspectives: early diagnosis, stratification, disease monitoring, drug efficacy evaluation and comorbidity prediction. This study aimed to provide a novel direction for exploring rational diagnostic and therapeutic strategies for axSpA.

Use of MRI-based deep learning radiomics to diagnose sacroiliitis related to axial spondyloarthritis.

OBJECTIVES: This study aimed to evaluate the performance of a deep learning radiomics (DLR) model, which integrates multimodal MRI features and clinical information, in diagnosing sacroiliitis related to axial spondyloarthritis (axSpA). MATERIAL & METHODS: A total of 485 patients diagnosed with sacroiliitis related to axSpA (n = 288) or non-sacroiliitis (n = 197) by sacroiliac joint (SIJ) MRI between May 2018 and October 2022 were retrospectively included in this study. The patients were randomly divided into training (n = 388) and testing (n = 97) cohorts. Data were collected using three MRI scanners. We applied a convolutional neural network (CNN) called 3D U-Net for automated SIJ segmentation. Additionally, three CNNs (ResNet50, ResNet101, and DenseNet121) were used to diagnose axSpA-related sacroiliitis using a single modality. The prediction results of all the CNN models across different modalities were integrated using a stacking method based on different algorithms to construct ensemble models, and the optimal ensemble model was used as DLR signature. A combined model incorporating DLR signature with clinical factors was developed using multivariable logistic regression. The performance of the models was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). RESULTS: Automated deep learning-based segmentation and manual delineation showed good correlation. ResNet50, as the optimal basic model, achieved an area under the curve (AUC) and accuracy of 0.839 and 0.804, respectively. The combined model yielded the highest performance in diagnosing axSpA-related sacroiliitis (AUC: 0.910; accuracy: 0.856) and outperformed the best ensemble model (AUC: 0.868; accuracy: 0.825) (all P < 0.05). Moreover, the DCA showed good clinical utility in the combined model. CONCLUSION: We developed a diagnostic model for axSpA-related sacroiliitis by combining the DLR signature with clinical factors, which resulted in excellent diagnostic performance.

Association of nociplastic and neuropathic pain components with the presence of residual symptoms in patients with axial spondyloarthritis receiving biological disease-modifying antirheumatic drugs.

OBJECTIVE: To evaluate the association of nociplastic (NoP) and neuropathic pain (NP) components with residual symptoms in patients with radiographic axial spondyloarthritis (r-axSpA) receiving biological disease-modifying antirheumatic drugs (bDMARDs). METHODS: 78 patients with r-axSpA from the GErman SPondyloarthritis Inception Cohort receiving a bDMARD for at least 3 months were included in this analysis. The Widespread Pain Index (WPI) and the PainDETECT (PD) questionnaire were used to quantify the NoP and the NP components, respectively. Axial Spondyloarthritis Disease Activity Score (ASDAS) and the Bath Ankylosing Spondylitis Disease Activity Index (BASDAI) were used as measures of residual symptoms. C reactive protein (CRP) was used as a measure of systemic inflammatory activity. Univariable and multivariable regression analyses of disease activity were performed. The regions of the WPI score and items of the PD score were used for cluster analyses. RESULTS: Linear multivariable regression analysis showed that WPI and PD were independently associated with ASDAS (b=0.1, 95% CI 0.04 to 0.17, and b=0.05, 95% CI 0.02 to 0.08, respectively) and BASDAI (b=0.24, 95% CI 0.08 to 0.39, and b=0.17, 95% CI 0.1 to 0.25, respectively) in r-axSpA patients receiving stable treatment with bDMARDs. Furthermore, WPI and PD were found to be significantly associated with the presence of relevant residual symptoms as defined by BASDAI ≥4 (OR 1.93, 95% CI 1.09 to 4.15, and OR 1.32, 95% CI 1.04 to 1.85, respectively). The effects were present also in patients with normal level of CRP. Cluster analysis revealed three distinct pain distribution profiles and four specific sensory symptom constellations allowing differentiation of different pain subtypes. CONCLUSION: Both NoP and NP components seem to be associated with residual symptoms in patients with r-axSpA receiving treatment with bDMARDs.