Unmet Needs in Axial Spondyloarthritis

Elevating the Standard of Care for Patients with Axial Spondyloarthritis: 'Calls to Action' from Rheumacensus, a Multistakeholder Pan-European Initiative

INTRODUCTION

Several barriers to optimal care in axial spondyloarthritis (axSpA) exist, which is detrimental to patient outcomes. The Rheumacensus programme aimed to identify how the standard of care (SoC) and treatment ambition for patients with axSpA could be elevated, from the unique perspective of three key stakeholders from across Europe: patients, healthcare professionals (HCPs) and payors.

METHODS

Rheumacensus followed three phases: an insights-gathering workshop to identify current unmet needs in axSpA and an area of focus, a modified Delphi process to gain consensus on improvements within the agreed area of focus, and a Consensus Council (CC) meeting to generate 'Calls to Action' (CTA) to highlight the changes needed to elevate the SoC for patients with axSpA.

RESULTS

The Rheumacensus CC consisted of four patient representatives, four HCPs and four payors. All 12 members completed all three Delphi e-consultations. The shared area of focus that informed the Delphi process was patient empowerment through education on the disease and treatment options available, to enable patient involvement in management and ultimately increase treatment adherence. Four key themes emerged from the Delphi process: patient empowerment, patient knowledge, patient-HCP consultations and optimal initial treatment. These themes informed 11 overarching CTA, which demonstrate the need for a multistakeholder approach to implement a paradigm shift towards patient-centred care to elevate health outcomes in patients with axSpA.

CONCLUSION

Rheumacensus identified CTA to help bridge the disparities observed in axSpA care. It is now imperative for all stakeholders to take practical steps towards addressing these CTA to elevate the SoC and treatment ambition in patients with axSpA.

How good is the agreement between clinical diagnoses and classification criteria fulfilment in axial spondyloarthritis? Results from the SPARTAKUS cohort

OBJECTIVES

To study the agreement between clinical axial spondyloarthritis (axSpA) diagnoses and fulfilment of the Assessment of SpondyloArthritis international Society (ASAS) axSpA and modified New York (mNY) classification criteria, and to compare disease/health status between axSpA subtypes.

METHOD

Patients with prevalent, clinical axSpA attending a rheumatology clinic were enrolled in a cross-sectional study. Assessments included physical evaluation, laboratory testing, questionnaires, and appropriate imaging, allowing classification. Standard axSpA outcome measures were compared between patients fulfilling mNY/radiographic versus non-radiographic axSpA (r-axSpA/nr-axSpA) criteria.

RESULTS

Of 239 consecutively included patients, 141 fulfilled ASAS r-axSpA and/or mNY criteria, while 57 fulfilled nr-axSpA criteria. The agreement between r-axSpA and mNY criteria fulfilment was 94%. The positive predictive value (PPV) of a clinical ankylosing spondylitis (AS) diagnosis for mNY criteria fulfilment was 71%; the PPV of an undifferentiated axSpA (u-axSpA) diagnosis for fulfilment of nr-axSpA criteria was 30% and 40% for mNY criteria. Patients with r-axSpA/AS were older, more often men, and had longer disease duration, more uveitis, and worse spinal mobility than nr-axSpA patients, who had more enthesitis and dactylitis.

CONCLUSION

We found an overall good concordance between clinical axSpA diagnoses and classification criteria fulfilment, with 83% fulfilling ASAS axSpA and/or mNY criteria. Regarding axSpA subtypes, the concordance was weaker, and although the ICD-10 code for AS correctly identified patients meeting mNY criteria in 71% of cases, one-third of mNY-positive patients lacked an AS diagnosis. Moreover, clinical u-axSpA diagnoses could not serve as a proxy to identify nr-axSpA, highlighting the importance of thorough classification in research on axSpA subtypes.

Therapeutic Targets for Ankylosing Spondylitis - Recent Insights and Future Prospects

Ankylosing spondylitis (AS) is a chronic inflammatory rheumatic disease belonging to the axial spondyloarthritis (axSpA), a group of diseases that affects the axial skeleton and causes severe pain and disability. An early diagnosis and appropriate treatment can reduce the severity of the disease and the risk of progression. TNF-α inhibitors demonstrated efficacy and effectiveness in axSpA patients by reducing disease activity, minimizing inflammation and improving the quality of life. More recently, new insights in pathogenesis of axSpA, including the discovery of the role of IL-23/IL-17 axis and intracellular pathways, led to the development of new biologics and small molecules that improve our therapeutic armamentarium. New alternatives are also being soon available. The aim of this paper is to narratively review the recent insights and future prospects in the treatment of AS and, more in general, axSpA.

Patient perspectives on health care provider practices leading to an axial spondyloarthritis diagnosis: an exploratory qualitative research study

BACKGROUND

The average time to a diagnosis for people with axial spondyloarthritis (axSpA) is 7-10 years. Delayed diagnosis may result in increased structural damage, worse physical function, and worse quality of life relative to patients with a timely axSpA diagnosis. Understanding patient experiences may provide insights for how to reduce diagnostic delays.

OBJECTIVE

To provide foundational knowledge about patient experiences with healthcare providers leading to an axSpA diagnosis.

METHODS

We conducted an exploratory qualitative research study with six focus groups interviews with participants recruited from three rheumatology clinics within the United States (MA (n = 3); CO (n = 2); PA (n = 1)) that included a total of 26 adults (10 females, 16 males) with rheumatologist confirmed diagnosis of axSpA in 2019. Focus groups were ~ 2 h, audio recorded, transcribed, and subject to dual coding. The codes reviewed were in relation to the patients' diagnostic experiences.

RESULTS

Patients described frustrating and lengthy diagnostic journeys. They recognized that the causes of diagnostic delays in axSpA are multifactorial (e.g., no definitive diagnostic test, disease characteristics, lack of primary care provider's awareness about axSpA, trust). Patients described how doctors minimized or dismissed complaints about symptoms or told them that their issues were psychosomatic. Patients believed the healthcare system contributed to diagnostic delays (e.g., lack of time in clinical visits, difficulty accessing rheumatologists, health insurance challenges). Advice to physicians to reduce the diagnostic delay included allowing time for patients to give a complete picture of their illness experience, listening to, and believing patients, earlier referral to rheumatology, provision of HLA-B27 gene testing, and that physicians need to partner with their patients.

CONCLUSIONS

Patients desire a definitive test that could be administered earlier in the course of axSpA. Until such a test is available, patients want clinicians who listen to, believe, and partner with them, and who will follow them until a diagnosis is reached. Educating primary care clinicians about guidelines and referral for diagnosis of axSpA could reduce diagnostic delay.

Sex-associated and gender-associated differences in the diagnosis and management of axial spondyloarthritis: addressing the unmet needs of female patients

Emerging evidence suggests that axial spondyloarthritis (axSpA) should not be seen as a predominantly male disease, as the non-radiographic form occurs with roughly equal frequency in women and men. However, men and women experience this disease differently. The purpose of this review is to highlight sex-associated and gender-associated differences in the patient's journey through the diagnosis and management of axSpA, in order to increase the awareness about the unmet needs of female axSpA patients.Female patients experience a longer diagnostic delay compared with men, possibly due to the different pattern of clinical presentations across genders. Therefore, it is crucial to sensitise physicians to pay attention and identify the red flags of axSpA in women and promote early referral to a rheumatologist. Women with a diagnosis of axSpA experience greater limitations in physical function, although they have less structural spinal damage compared with men. Women tend to have less adherence and a lower response to treatment, so more gender-oriented data are needed about drugs used for axSpA, especially biological disease-modifying antirheumatic drugs.Lifestyle factors have a strong impact on the disease course. Interventions regarding physical activity, smoking cessation and diet should be communicated to the patients, with particular attention to the gender-related cultural background.Patients of childbearing age living with axSpA should be engaged in a discussion about reproductive health, in terms of preservation of fertility, management of pregnancy and delivery and use of biologic drugs during pregnancy and breastfeeding.

A review of JAK-STAT signalling in the pathogenesis of spondyloarthritis and the role of JAK inhibition

Spondyloarthritis (SpA) comprises a group of chronic inflammatory diseases with overlapping clinical, genetic and pathophysiological features including back pain, peripheral arthritis, psoriasis, enthesitis and dactylitis. Several cytokines are involved in the pathogenesis of SpA, variously contributing to each clinical manifestation. Many SpA-associated cytokines, including IL-23, IL-17, IL-6, type I/II interferon and tumour necrosis factor signal directly or indirectly via the Janus kinase (JAK)–signal transducer and activator of transcription pathway. JAK signalling also regulates development and maturation of cells of the innate and adaptive immune systems. Accordingly, disruption of this signalling pathway by small molecule oral JAK inhibitors can inhibit signalling implicated in SpA pathogenesis. Herein we discuss the role of JAK signalling in the pathogenesis of SpA and summarize the safety and efficacy of JAK inhibition by reference to relevant SpA clinical trials.

Early identification of axial spondyloarthritis in a multi-ethnic Asian population

INTRODUCTION/OBJECTIVES

To address the diagnostic delay in axial spondyloarthritis (axSpA), we have cross-culturally adapted the Hamilton axSpA questionnaire, a self-administered screening questionnaire, in the Singapore population. In this study, we compared the performance of various scoring methods for this questionnaire in detecting axSpA.

METHOD

The questionnaire was self-administered by eligible subjects. Scoring methods included method A, the original questionnaire scoring, and methods B-E, scoring developed based on the Assessment of SpondyloArthritis International Society (ASAS) criteria for inflammatory back pain (IBP) and the referral, classification and both referral and classification of axSpA, respectively. The reference standard was diagnosis by a rheumatologist. Since the ASAS criteria-based scoring methods were mainly based on clinical axSpA features, self-report and rheumatologist-assessment of clinical axSpA features were also compared in subjects with axSpA.

RESULTS

Of 1418 subjects (age: 54 ± 14 years, female: 73%) recruited, 46 were diagnosed with axSpA by a rheumatologist. Sensitivities of methods A-E were 35%, 61%, 63%, 48% and 83%, respectively. Self-report of clinical axSpA features exceeded rheumatologist-assessment for arthritis (83 vs 26%), good response to NSAIDs (37 vs 30%), enthesitis (35 vs 30%), dactylitis (20 vs 2%) and family history for axSpA (13 vs 4%). The reverse was true for IBP (41 vs 63%) and uveitis (4 vs 15%).

CONCLUSIONS

A self-administered questionnaire using the ASAS referral and classification criteria-based scoring yielded relatively high sensitivity in detecting axSpA in subjects newly referred to rheumatology clinics. This supports its evaluation as a screening and referral tool in the general population in future studies. Key Points • A self-administered questionnaire could be used as a screening and referral tool. • ASAS referral and classification criteria-based scoring yielded relatively high sensitivity. • Inaccurate perception of clinical axSpA features was observed in axSpA patients.

Complement C3d is not associated with axial spondyloarthritis and magnetic resonance imaging changes at the sacroiliac joint

Objective: To investigate the associations between complement C3d and inflammatory and structural changes by magnetic resonance imaging (MRI) at the sacroiliac joints (SIJ) suggestive of axial spondyloarthritis, according to the Assessment of SpondyloArthritis international Society (ASAS) criteria, in patients with low back pain.Method: This was a cross-sectional study of patients referred to the Spine Centre of Southern Denmark owing to unspecified low back pain (Spines of Southern Denmark cohort). The patients were divided into three groups: group 1: patients fulfilling the ASAS criteria for axial spondyloarthritis (axSpA, n = 96); group 2: patients with either a positive MRI of the SIJ and no spondyloarthritis features, or a negative MRI of the SIJ but positive human leucocyte antigen-B27 and one spondyloarthritis feature (non-axSpA, n = 38); group 3: patients with unspecified low back pain for > 3 months (control group, n = 82). Complement C3d was measured with double-decker rocket immunoelectrophoresis and evaluated in relation to the group division and baseline findings by SIJ MRI.Results: In total, 184 C3d analyses were performed. The mean ± sd level of C3d was 33.8 ± 8.1 AU/mL. There were no differences in C3d levels between the three patient groups, mean values being: axSpA = 34.3 ± 7.9 AU/mL, non-axSpA = 33.5 ± 6.9 AU/mL, and controls = 33.4 ± 9.2 AU/mL. The level of C3d was not related to MRI findings.Conclusions: In these patients, complement C3d was not associated with active or structural SIJ changes on MRI suggestive of axial spondyloarthritis.

Interval between symptom onset and diagnosis among patients with autoimmune rheumatic diseases in a multi-ethnic Asian population

AIM

The interval between symptom onset and diagnosis (pre-diagnosis interval) can at times be longer than is ideal in patients with autoimmune rheumatic diseases (ARDs). In this study, we aimed to characterize this interval and to identify its associated factors.

METHOD

We characterized pre-diagnosis interval into 4 intervals: Interval #1 between symptom onset and first visit to healthcare professionals; Interval #2 between first visit to healthcare professionals and rheumatology referral; Interval #3 between rheumatology referral and first rheumatology assessment; and Interval #4 between first rheumatology assessment and diagnosis. Median regression models were used to identify factors associated with longer pre-diagnosis interval and Interval #1.

RESULTS

Among 259 patients (median age = 52.0 [41.6-61.9] years, 71% female, rheumatoid arthritis [n = 75], axial spondyloarthritis [axSpA] [n = 40] and psoriatic arthritis [n = 35]), median pre-diagnosis interval was 11.5 (4.7-36.0) months. Interval #1 (median = 4.9 months) was significantly longer than Intervals #2-#4 (median = 0.3, 1.5, and 0.0 months, respectively). Patients with axSpA had significantly longer pre-diagnosis interval (median = 38.7 months) and Interval #1 (median = 26.6 months) than patients with the other ARDs. Median regression suggested that patients referred from specialty care had significantly longer pre-diagnosis interval (median difference = 7.7 months) and Interval #1 (median difference = 6.4 months) compared to those referred from primary care.

CONCLUSION

A long pre-diagnosis interval was observed among patients with ARDs (especially axSpA), due largely to a long interval between symptom onset and the first visit to healthcare professionals. This highlights the importance of interventions targeting patients prior to their first visit to healthcare professionals in reducing pre-diagnosis interval.

Gut microbiota-microRNA interactions in ankylosing spondylitis

Ankylosing spondylitis (AS) is a chronic autoimmune inflammatory disability that is part of the rheumatic disease group of spondyloarthropathies. AS commonly influences the joints of the axial skeleton. The contributions to AS pathogenesis of genetic susceptibility (particularly HLA-B27 and ERAP-1) and epigenetic modifications, like non-coding RNAs, as well as environmental factors, have been investigated over the last few years. But the fundamental etiology of AS remains elusive to date. The evidence summarized here indicates that in the immunopathogenesis of AS, microRNAs and the gut microbiome perform critical functions. We discuss significant advances in the immunological mechanisms underlying AS and address potential cross-talk between the gut microbiome and host microRNAs. This critical interaction implicates a co-evolutionary symbiotic link between host immunity and the gut microbiome.

Identifying Patients With Axial Spondyloarthritis in Large Datasets: Expanding Possibilities for Observational Research

OBJECTIVE

Observational research of axial spondyloarthritis (axSpA) is limited by a lack of methods for identifying diverse axSpA phenotypes in large datasets. Algorithms were previously designed to identify a broad spectrum of patients with axSpA, including patients not identifiable with diagnosis codes. The study objective was to estimate the performance of axSpA identification methods in the general Veterans Affairs (VA) population.

METHODS

A patient sample with known axSpA status (n = 300) was established with chart review. For feasibility, this sample was enriched with veterans with axSpA risk factors. Algorithm performance outcomes included sensitivities, positive predictive values (PPV), and F1 scores (an overall performance metric combining sensitivity and PPV). Performance was estimated with unweighted outcomes for the axSpA-enriched sample and inverse probability weighted (IPW) outcomes for the general VA population. These outcomes were also assessed for traditional identification methods using diagnosis codes for the ankylosing spondylitis (AS) subtype of axSpA.

RESULTS

The mean age was 54.7 and 92% were male. Unweighted F1 scores (0.59-0.74) were higher than IPW F1 scores (0.48-0.65). The full algorithm had the best overall performance (F1_IPW 0.65). The Early Algorithm was the most inclusive (sensitivity_IPW 0.90, PPV_IPW 0.38). The traditional method using ≥ 2 AS diagnosis codes from rheumatology had the highest PPV (PPV_IPW 0.84, sensitivity_IPW 0.34).

CONCLUSION

The axSpA identification methods demonstrated a range of performance attributes in the general VA population that may be appropriate for various types of studies. The novel identification algorithms may expand the scope of research by enabling identification of more diverse axSpA populations.

Primary care physician perspectives on barriers to diagnosing axial Spondyloarthritis: a qualitative study

BACKGROUND

The average delay in diagnosis for patients with axial spondyloarthritis (axSpA) is 7 to 10 years. Factors that contribute to this delay are multifactorial and include the lack of diagnostic criteria (although classification criteria exist) for axSpA and the difficulty in distinguishing inflammatory back pain, a key symptom of axSpA, from other highly prevalent forms of low back pain. We sought to describe reasons for diagnostic delay for axSpA provided by primary care physicians.

METHODS

We conducted a qualitative research study which included 18 US primary care physicians, balanced by gender. Physicians provided informed consent to participate in an in-depth interview (< 60 min), conducted in person (n = 3) or over the phone (n = 15), in 2019. The analysis focuses on thoughts about factors contributing to diagnostic delay in axSpA.

RESULTS

Physicians noted that the disease characteristics contributing to diagnostic delay include: back pain is common and axSpA is less prevalent, slow progression of axSpA, intermittent nature of axSpA pain, and in the absence of abnormal radiographs of the spine or sacroiliac joints, there is no definitive test for axSpA. Patient characteristics believed to contribute to diagnostic delay included having multiple conditions in need of attention, infrequent interactions with the health care system, and "doctor shopping." Doctors noted that patients wait until the last moments of the clinical encounter to discuss back pain. Problematic physician characteristics included lack of rapport with patients, lack of setting appropriate expectations, and attribution of back pain to other factors. Structural/system issues included short appointments, lack of continuity of care, insufficient insurance coverage for tests, lack of back pain clinics, and a shortage of rheumatologists.

CONCLUSION

Primary care physicians agreed that lengthy axSpA diagnosis delays are challenging to address owing to the multifactorial causes (e.g., disease characteristics, patient characteristics, lack of definitive tests, system factors).

MicroRNAs in ankylosing spondylitis: Function, potential and challenges

Epigenetic mechanisms such as DNA methylation, histone modifications and non-coding RNA, are considered the essential connection between a disorder's onset and the environment, on a permissive genetic background. Among autoimmune and inflammatory-mediated disorders, Ankylosing Spondylitis (AS), a chronic arthritis of the spine, is a very good example for the weight of epigenetics' contribution. MicroRNAs (miRNAs) are single-stranded nucleotides which regulate gene expression and are involved in pathological and physiological processes. In this manuscript we provide a clarification on the role of microRNAs in AS, with a focus on the mechanisms of pathogenesis. In specific, we have examined the contribution of miRNAs in the processes of inflammation, new bone formation and T-cell function, and the pathways (i.e. Wnt, BMP, TGFβ signalling etc.) they regulate. The utility of miRNAs in better understanding AS pathogenesis is undisputed and their utility as therapeutic opportunity is strongly increasing.

Improvement of Function and Its Determinants in a Group of Axial Spondyloarthritis Patients Treated with TNF Inhibitors: A Real-Life Study

INTRODUCTION

The aim of this work is to investigate the improvement of physical function and its determinants in axial spondyloarthritis (SpA) patients treated with tumor necrosis factor (TNF) inhibitors in a real clinical practice setting.

METHODS

An observational study was conducted in patients with axial SpA treated with anti-TNF from 2010 to 2018 with a minimum 6 months of follow-up. All patients fulfilled ASAS or the modified New York criteria. The Bath Ankylosing Spondylitis Metrology Index (BASMI) and the Bath Ankylosing Spondylitis Functional Index (BASFI) were used as objective and self-reported functional indices. The improvement of function and factors associated were evaluated for the present study, as well as disease activity and patient-reported outcome measures.

RESULTS

A total of 183 patients with axial SpA were examined. Among them, 27 were non-radiographic axial SpA, while the remaining 156 were ankylosing spondylitis patients. BASFI and BASMI significantly improved during follow-up. Improvement of metrology index BASMI inverse correlated with disease duration (rho - 0.2, p = 0.009) and directly correlated with the improvement of BASDAI (rho 0.26, p = 0.003) and CRP (rho 0.26, p = 0.0003). Improvement of BASFI significantly inversely correlated with disease duration and directly correlated with the improvement of BASDAI, CRP, and baseline ESR. Male sex, lower disease duration, high ESR, and the improvement of BASDAI were found to be associated with the improvement of BASFI.

CONCLUSIONS

Our results showed that in real-life settings, patients improve in BASMI and BASFI. Furthermore, factors associated with this improvement were identified.

New Insights in Physical Therapy and Rehabilitation in Axial Spondyloarthritis: A Review

Axial spondyloarthritis (axSpA) is a chronic and inflammatory rheumatic disease characterized by pain, structural and functional impairments, and reduced mobility and potential deformity of the axial skeleton. Treatment of axSpA includes pharmacological and non-pharmacological therapy. However, in the biologic era, unmet needs still remain for patients intolerant to or non-responders to biologic drugs and despite the development of new treatments, physical therapy and rehabilitation are of crucial importance in the management of axSpA patients. The aim of this manuscript is to review the current evidence on the assessment, physical therapy, and rehabilitation in axSpA patients.

Application of machine learning in the diagnosis of axial spondyloarthritis

PURPOSE OF REVIEW

In this review article, we describe the development and application of machine-learning models in the field of rheumatology to improve the detection and diagnosis rates of underdiagnosed rheumatologic conditions, such as ankylosing spondylitis and axial spondyloarthritis (axSpA).

RECENT FINDINGS

In an attempt to aid in the earlier diagnosis of axSpA, we developed machine-learning models to predict a diagnosis of ankylosing spondylitis and axSpA using administrative claims and electronic medical record data. Machine-learning algorithms based on medical claims data predicted the diagnosis of ankylosing spondylitis better than a model developed based on clinical characteristics of ankylosing spondylitis. With additional clinical data, machine-learning algorithms developed using electronic medical records identified patients with axSpA with 82.6-91.8% accuracy. These two algorithms have helped us understand potential opportunities and challenges associated with each data set and with different analytic approaches. Efforts to refine and validate these machine-learning models are ongoing.

SUMMARY

We discuss the challenges and benefits of machine-learning models in healthcare, along with potential opportunities for its application in the field of rheumatology, particularly in the early diagnosis of axSpA and ankylosing spondylitis.

Unmet needs in the treatment of ankylosing spondylitis: a long-term observational study from a single university center

Despite the progress in the treatment of ankylosing spondylitis (AS), a significant number of patients do not achieve low disease activity (LDA). The aim of the study is to estimate the size of unmet needs in the treatment of AS in a long-term observational study. Between January 2003 and December 2017, 220 patients with radiographic SpA were evaluated fulfilling the ASAS criteria. They were followed up at predefined times and were naive to biological treatment with anti-tumor necrosis factor agents (anti-TNFs) and the interleukin (IL)-17 inhibitor. NSAIDs, all anti-TNFs and the IL-17 inhibitor secukinumab were used according to the European, United States and Canadian guidelines for AS. During follow-up, several clinical parameters including disease activity scores were recorded. All 220 patients had an active disease and received at least two NSAIDs for 3 months. The anti-TNF of first choice was infliximab-51%, followed by adalimumab-27% and etanercept-22%. During follow-up, 22 patients were excluded from the study (18 lost, 4 never received anti-TNF due to comorbidities). From the rest (198), 12 did not receive anti-TNFs (8 due to sustained LDA on NSAIDs solely and 4 due to treatment denial). Finally, 186 (94%) were treated with anti-TNFs demonstrating sustained long-term LDA. However, 16 patients never achieved LDA despite they received two or three anti-TNFs or the IL-17 inhibitor. Thus, a total of 20 (10.1%) patients never achieved LDA. This is the first study aiming to estimate the gap and the size of unmet needs in AS patients using the international guidelines and recommendations for AS treatment, which is 10.1%.

Identification of Axial Spondyloarthritis Patients in a Large Dataset: The Development and Validation of Novel Methods

OBJECTIVE

Observational axial spondyloarthritis (axSpA) research in large datasets has been limited by a lack of adequate methods for identifying patients with axSpA, because there are no billing codes in the United States for most subtypes of axSpA. The objective of this study was to develop methods to accurately identify patients with axSpA in a large dataset.

METHODS

The study population included 600 chart-reviewed veterans, with and without axSpA, in the Veterans Health Administration between January 1, 2005, and June 30, 2015. AxSpA identification algorithms were developed with variables anticipated by clinical experts to be predictive of an axSpA diagnosis [demographics, billing codes, healthcare use, medications, laboratory results, and natural language processing (NLP) for key SpA features]. Random Forest and 5-fold cross validation were used for algorithm development and testing in the training subset (n = 451). The algorithms were additionally tested in an independent testing subset (n = 149).

RESULTS

Three algorithms were developed: Full algorithm, High Feasibility algorithm, and Spond NLP algorithm. In the testing subset, the areas under the curve with the receiver-operating characteristic analysis were 0.96, 0.94, and 0.86, for the Full algorithm, High Feasibility algorithm, and Spond NLP algorithm, respectively. Algorithm sensitivities ranged from 85.0% to 95.0%, specificities from 78.0% to 93.6%, and accuracies from 82.6% to 91.3%.

CONCLUSION

Novel axSpA identification algorithms performed well in classifying patients with axSpA. These algorithms offer a range of performance and feasibility attributes that may be appropriate for a broad array of axSpA studies. Additional research is required to validate the algorithms in other cohorts.