Assessing clusters of comorbidities in rheumatoid arthritis: a machine learning approach.

BACKGROUND: Comorbid conditions are very common in rheumatoid arthritis (RA) and several prior studies have clustered them using machine learning (ML). We applied various ML algorithms to compare the clusters of comorbidities derived and to assess the value of the clusters for predicting future clinical outcomes. METHODS: A large US-based RA registry, CorEvitas, was used to identify patients for the analysis. We assessed the presence of 24 comorbidities, and ML was used to derive clusters of patients with given comorbidities. K-mode, K-mean, regression-based, and hierarchical clustering were used. To assess the value of these clusters, we compared clusters across different ML algorithms in clinical outcome models predicting clinical disease activity index (CDAI) and health assessment questionnaire (HAQ-DI). We used data from the first 3 years of the 6-year study period to derive clusters and assess time-averaged values for CDAI and HAQ-DI during the latter 3 years. Model fit was assessed via adjusted R2 and root mean square error for a series of models that included clusters from ML clustering and each of the 24 comorbidities separately. RESULTS: 11,883 patients with RA were included who had longitudinal data over 6 years. At baseline, patients were on average 59 (SD 12) years of age, 77% were women, CDAI was 11.3 (SD 11.9, moderate disease activity), HAQ-DI was 0.32 (SD 0.42), and disease duration was 10.8 (SD 9.9) years. During the 6 years of follow-up, the percentage of patients with various comorbidities increased. Using five clusters produced by each of the ML algorithms, multivariable regression models with time-averaged CDAI as an outcome found that the ML-derived comorbidity clusters produced similarly strong models as models with each of the 24 separate comorbidities entered individually. The same patterns were observed for HAQ-DI. CONCLUSIONS: Clustering comorbidities using ML algorithms is not computationally complex but often results in clusters that are difficult to interpret from a clinical standpoint. While ML clustering is useful for modeling multi-omics, using clusters to predict clinical outcomes produces models with a similar fit as those with individual comorbidities.

Clinical Characteristics of Registry Participants with Psoriatic Arthritis Initiating Guselkumab: An Analysis from the CorEvitas Psoriatic Arthritis/Spondyloarthritis Registry.

BACKGROUND: The monoclonal antibody guselkumab is the first selective inhibitor of the interleukin-23 p19 subunit approved to treat adults with moderate-to-severe plaque psoriasis and active psoriatic arthritis (PsA). Given its recent approval for active PsA, data describing patients with PsA initiating guselkumab outside of clinical trials are limited. OBJECTIVE: This analysis describes characteristics of patients with rheumatologist-diagnosed PsA initiating guselkumab in the US-based, prospective, observational CorEvitas Psoriatic Arthritis/Spondyloarthritis Registry. METHODS: Demographics, lifestyle/disease characteristics, comorbidities, prior treatment, and disease activity were summarized for patients with PsA initiating guselkumab from registry inception through 30 September, 2021. RESULTS: Of 113 patients initiating guselkumab, the majority were female (63%), obese (67%), had psoriasis (89%), and initiated guselkumab as monotherapy (81%). Common comorbidities were hypertension (32%), depression (30%), and diabetes mellitus (26%). Mean tender (6.8) and swollen (2.0) joint counts, clinical Disease Activity Index for PsA score (19.1), and 57% of participants with ≥ 3% body surface area affected by psoriasis indicated moderate disease activity. Axial involvement was identified in 49% of patients. Median patient-reported pain and fatigue visual analog scale scores (0-100) were 60 and 59, respectively. Prior to guselkumab, 76% of patients had received two or more biologic disease-modifying antirheumatic drugs; the last therapy prior to guselkumab was a biologic disease-modifying antirheumatic drug in 81% of patients. CONCLUSIONS: Registry participants with PsA initiating guselkumab had active peripheral joint and skin disease, with substantial pain and fatigue; a considerable proportion had axial involvement. Future studies will evaluate the effectiveness of guselkumab in this population.

Demographics, Disease Characteristics, and Patient-Reported Outcomes Among Patients with Psoriasis Who Initiated Guselkumab in CorEvitas' Psoriasis Registry.

INTRODUCTION: Guselkumab is approved for the treatment of both moderate-to-severe plaque psoriasis and active psoriatic arthritis (PsA) in the USA. However, little is known about patients initiating guselkumab in a real-world setting. The objective of this study was to describe baseline characteristics among patients with plaque psoriasis who initiated guselkumab at or after enrollment in CorEvitas' Psoriasis Registry. METHODS: Adult patients who initiated guselkumab in the Psoriasis Registry between July 18, 2017 and November 6, 2018 were included. Demographics, disease characteristics, and patient-reported outcome measures (PROMs) were assessed at the time of guselkumab initiation (baseline). Patients with psoriasis were stratified according to the number of previously received biologics (0 to 4+) for comparison. A subset of patients with psoriasis and concomitant dermatologist-diagnosed PsA were stratified into biologic-naïve and biologic-experienced groups. RESULTS: Among 687 patients with psoriasis who initiated guselkumab, biologic-naïve patients and those with four or more prior biologics had the most severe disease and the worst PROM scores at baseline. Among 251 patients with concomitant dermatologist-diagnosed PsA, biologic-naïve patients had more severe disease and worse PROM scores than biologic-experienced patients. CONCLUSIONS: These findings highlight important differences in baseline characteristics according to biologic experience among patients with plaque psoriasis with or without concomitant PsA initiating guselkumab in a real-world setting.

Incidence of venous and arterial thromboembolic events reported in the tofacitinib rheumatoid arthritis, psoriasis and psoriatic arthritis development programmes and from real-world data.

OBJECTIVES: Tofacitinib is a Janus kinase inhibitor for the treatment of rheumatoid arthritis (RA), psoriatic arthritis (PsA) and ulcerative colitis, and has been investigated in psoriasis (PsO). Routine pharmacovigilance of an ongoing, open-label, blinded-endpoint, tofacitinib RA trial (Study A3921133; NCT02092467) in patients aged ≥50 years and with ≥1 cardiovascular risk factor identified a higher frequency of pulmonary embolism (PE) and all-cause mortality for patients receiving tofacitinib 10 mg twice daily versus those receiving tumour necrosis factor inhibitors and resulted in identification of a safety signal for tofacitinib. Here, we report the incidence of deep vein thrombosis (DVT), PE, venous thromboembolism (VTE; DVT or PE) and arterial thromboembolism (ATE) from the tofacitinib RA (excluding Study A3921133), PsA and PsO development programmes and observational studies. Data from an ad hoc safety analysis of Study A3921133 are reported separately within. METHODS: This post-hoc analysis used data from separate tofacitinib RA, PsO and PsA programmes. Incidence rates (IRs; patients with events per 100 patient-years' exposure) were calculated for DVT, PE, VTE and ATE, including for populations stratified by defined baseline cardiovascular or VTE risk factors. Observational data from the US Corrona registries (including cardiovascular risk factor stratification), IBM MarketScan research database and the US FDA Adverse Event Reporting System (FAERS) database were analysed. RESULTS: 12 410 tofacitinib-treated patients from the development programmes (RA: n=7964; PsO: n=3663; PsA: n=783) were included. IRs (95% CI) of thromboembolic events among the all tofacitinib cohorts' average tofacitinib 5 mg and 10 mg twice daily treated patients for RA, respectively, were: DVT (0.17 (0.09-0.27) and 0.15 (0.09-0.22)); PE (0.12 (0.06-0.22) and 0.13 (0.08-0.21)); ATE (0.32 (0.22-0.46) and 0.38 (0.28-0.49)). Among PsO patients, IRs were: DVT (0.06 (0.00-0.36) and 0.06 (0.02-0.15)); PE (0.13 (0.02-0.47) and 0.09 (0.04-0.19)); ATE (0.52 (0.22-1.02) and 0.22 (0.13-0.35)). Among PsA patients, IRs were: DVT (0.00 (0.00-0.28) and 0.13 (0.00-0.70)); PE (0.08 (0.00-0.43) and 0.00 (0.00-0.46)); ATE (0.31 (0.08-0.79) and 0.38 (0.08-1.11)). IRs were similar between tofacitinib doses and generally higher in patients with baseline cardiovascular or VTE risk factors. IRs from the overall Corrona populations and in Corrona RA patients (including tofacitinib-naïve/biologic disease-modifying antirheumatic drug-treated and tofacitinib-treated) with baseline cardiovascular risk factors were similar to IRs observed among the corresponding patients in the tofacitinib development programme. No signals of disproportionate reporting of DVT, PE or ATE with tofacitinib were identified in the FAERS database. CONCLUSIONS: DVT, PE and ATE IRs in the tofacitinib RA, PsO and PsA programmes were similar across tofacitinib doses, and generally consistent with observational data and published IRs of other treatments. As expected, IRs of thromboembolic events were elevated in patients with versus without baseline cardiovascular or VTE risk factors, and were broadly consistent with those observed in the Study A3921133 ad hoc safety analysis data, although the IR (95% CI) for PE was greater in patients treated with tofacitinib 10 mg twice daily in Study A3921133 (0.54 (0.32-0.87)), versus patients with baseline cardiovascular risk factors treated with tofacitinib 10 mg twice daily in the RA programme (0.24 (0.13-0.41)).

Rebound in Measures of Disease Activity and Symptoms in Corrona Registry Patients with Psoriatic Arthritis Who Discontinue Tumor Necrosis Factor Inhibitor Therapy after Achieving Low Disease Activity.

OBJECTIVE: Rebound may occur in patients with psoriatic arthritis (PsA) who discontinue TNF inhibitor (TNFi) therapy in low disease activity (LDA). METHODS: Using physician and patient reports, we quantified rebound following TNFi discontinuation [defined as Clinical Disease Activity Index (CDAI) score > 10 or TNFi restart] and time to rebound in adults with PsA in LDA (CDAI score ≤ 10) at TNFi discontinuation. RESULTS: Rebound occurred in 73% (69/94) of patients soon after discontinuation (median time to rebound 8.0 mos, 95% CI 6.0-12.0). CONCLUSION: Rebound occurred frequently in patients with PsA after TNFi discontinuation. TNFi discontinuation after achieving LDA should be carefully considered.

Clinical and Patient-reported Outcomes in Patients with Psoriatic Arthritis (PsA) by Body Surface Area Affected by Psoriasis: Results from the Corrona PsA/Spondyloarthritis Registry.

OBJECTIVE: Psoriatic arthritis (PsA) is commonly comorbid with psoriasis; the extent of skin lesions is a major contributor to psoriatic disease severity/burden. We evaluated whether extent of skin involvement with psoriasis [body surface area (BSA) > 3% vs ≤ 3%] affects overall clinical and patient-reported outcomes (PRO) in patients with PsA. METHODS: Using the Corrona PsA/Spondyloarthritis Registry, patient characteristics, disease activity, and PRO at registry enrollment were assessed for patients with PsA aged ≥ 18 years with BSA > 3% versus ≤ 3%. Regression models were used to evaluate associations of BSA level with outcome [modified minimal disease activity (MDA), Health Assessment Questionnaire (HAQ) score, patient-reported pain and fatigue, and the Work Productivity and Activity Impairment questionnaire score]. Adjustments were made for age, sex, race, body mass index, disease duration, and history of biologics, disease-modifying antirheumatic drug, and prednisone use. RESULTS: This analysis included 1240 patients with PsA with known BSA level (n = 451, BSA > 3%; n = 789, BSA ≤ 3%). After adjusting for potential confounding variables, patients with BSA > 3% versus ≤ 3% had greater patient-reported pain and fatigue and higher HAQ scores (p = 2.33 × 10-8, p = 0.002, and p = 1.21 × 10-7, respectively), were 1.7× more likely not to be in modified MDA (95% CI 1.21-2.41, p = 0.002), and were 2.1× more likely to have overall work impairment (1.37-3.21, p = 0.0001). CONCLUSION: These Corrona Registry data show that substantial skin involvement (BSA > 3%) is associated with greater PsA disease burden, underscoring the importance of assessing and effectively managing psoriasis in patients with PsA because this may be a contributing factor in PsA severity.

Clinical Characteristics, Disease Activity, and Patient-Reported Outcomes in Psoriatic Arthritis Patients With Dactylitis or Enthesitis: Results From the Corrona Psoriatic Arthritis/Spondyloarthritis Registry.

OBJECTIVE: To characterize psoriatic arthritis (PsA) patients with dactylitis or enthesitis and evaluate the associations of these manifestations with disease activity and patient-reported outcomes. METHODS: Using the Corrona PsA/Spondyloarthritis Registry, patient characteristics, disease activity, and patient-reported outcomes at registry enrollment were assessed for PsA patients ages ≥18 years with or without dactylitis or enthesitis. Regression models were used to evaluate associations of dactylitis and enthesitis with outcomes, including minimal disease activity, Health Assessment Questionnaire scores, patient-reported pain and fatigue, and work productivity (Work Productivity and Activity Impairment questionnaire). Adjustments were made for age, sex, race, body mass index, disease duration, and history of biologic agent, disease-modifying antirheumatic drug, and prednisone use. RESULTS: This analysis included 1,567 PsA patients (420 with enthesitis; 228 with dactylitis). Patients with versus without dactylitis or enthesitis had greater disease activity and were less likely to be in minimal disease activity (P < 0.05). Patients with versus without enthesitis had poorer functional status as assessed by the Health Assessment Questionnaire (adjusted P = 4.15 x 10-5 ), greater patient-reported pain and fatigue (adjusted P < 0.0001), and greater likelihood of any impairment while working (adjusted odds ratio [OR] 1.57, P = 0.027), overall work impairment (OR 1.85, P = 0.006), and activity impairment (OR 1.77, P = 0.008). Dactylitis was associated with similar numerical trends, but differences versus patients without dactylitis did not reach statistical significance. CONCLUSION: Enthesitis and dactylitis are associated with greater overall disease burden of PsA, underscoring the importance of identifying, assessing, and effectively managing these periarticular manifestations.

Impact of prior biologic use on persistence of treatment in patients with psoriatic arthritis enrolled in the US Corrona registry.

Psoriatic arthritis (PsA) is a chronic condition characterized by a diverse set of symptoms, from swollen joints to nail disease to skin disease. A variety of treatment options are available, including tumor necrosis factor inhibitors (TNFis). Little is known about treatment persistence in patients with PsA who initiate TNFi therapy, with and without prior biologic use. This study assessed persistence in these subgroups of patients with PsA and identified factors associated with persistence. This retrospective study utilized data from the Corrona registry of patients with PsA-with or without prior biologic experience-who initiated TNFi therapy between October 1, 2002, and March 21, 2013. Kaplan-Meier curves estimated median time to nonpersistence (discontinuation or switch to another biologic). Cox proportional hazards models identified factors associated with TNFi nonpersistence. A total of 1241 TNFi initiations were identified: 549 by biologic-naïve and 692 by biologic-experienced patients. Through 4 years of follow-up, more biologic-naïve than biologic-experienced patients remained persistent. Biologic-naïve patients had a greater mean time to nonpersistence compared with biologic-experienced patients: 32 vs 23 months (p = 0.0002). Moderate and high disease activities based on clinical disease activity index and disease duration were associated with persistence in both biologic-naïve and biologic-experienced patients. Additionally, in the biologic-experienced patients, the number of prior medications and skin disease were associated with persistence. The majority of patients with PsA in this study were persistent with their TNFi therapy; biologic-naïve patients had greater persistence compared with biologic-experienced patients. Predictors of persistence differed slightly between biologic-naïve and biologic-experienced patients.