Moderate-High Disease Activity in Patients with Recent-Onset Psoriatic Arthritis-Multivariable Prediction Model Based on Machine Learning.

The aim was to identify patient- and disease-related characteristics predicting moderate-to-high disease activity in recent-onset psoriatic arthritis (PsA). We performed a multicenter observational prospective study (2-year follow-up, regular annual visits) in patients aged ≥18 years who fulfilled the CASPAR criteria and had less than 2 years since the onset of symptoms. The moderate-to-high activity of PsA was defined as DAPSA > 14. We trained a logistic regression model and random forest-type and XGBoost machine learning algorithms to analyze the association between the outcome measure and the variables selected in the bivariate analysis. The sample comprised 158 patients. At the first follow-up visit, 20.8% of the patients who attended the clinic had a moderate-to-severe disease. This percentage rose to 21.2% on the second visit. The variables predicting moderate-high activity were the PsAID score, tender joint count, level of physical activity, and sex. The mean values of the measures of validity of the machine learning algorithms were all high, especially sensitivity (98%; 95% CI: 86.89-100.00). PsAID was the most important variable in the prediction algorithms, reinforcing the convenience of its inclusion in daily clinical practice. Strategies that focus on the needs of women with PsA should be considered.

Confounders contributing to explain the association between sex and disease impact in patients with recent-onset psoriatic arthritis.

OBJECTIVES: To evaluate the effect of potential confounders on the association between sex and disease impact in recent-onset psoriatic arthritis. METHODS: We performed a multicentre observational prospective study (2-year follow-up, regular annual visits). The study population comprised patients aged ≥18 years who fulfilled the CASPAR criteria and less than 2 years since the onset of symptoms. The dataset was generated using data for each patient at the 3 visits (baseline, first year, and second year of follow-up) matched with the PsAID values at each of the 3 visits. Once variables associated with both PsAID ≥4 and sex were selected, those that led to a difference of >10% between the adjusted and crude estimations were identified as potential confounders in the association between sex and PsAID. Lastly, the final multivariate logistic regression model estimating the association between sex and PsAID was defined. RESULTS: The dataset contained 418 observations (158 at baseline, 135 at the first follow-up visit, and 125 at the second visit). The confounders identified in the multivariate model were HAQ, global pain, level of physical activity, and joint pattern at diagnosis. After adjustment for these variables, no statistically significant association was observed between female sex and PsAID ≥4. CONCLUSIONS: The association between female sex and greater disease impact could be explained by the influence of other variables, specifically higher HAQ score, greater intensity of pain, differences in the level of physical activity and in the joint pattern at diagnosis (lower frequency of the spondylitis pattern in women).

Characteristics associated with the perception of high-impact disease (PsAID ≥4) in patients with recent-onset psoriatic arthritis. Machine learning-based model.

OBJECTIVES: To evaluate which patient and disease characteristics are associated with the perception of high-impact disease (PsAID ≥4) in recent-onset psoriatic arthritis. METHODS: We performed a multicenter observational prospective study (2-year follow-up, regular annual visits). The study population comprised patients aged ≥18 years who fulfilled the CASPAR criteria and less than 2 years since the onset of symptoms. The dataset was generated using data for each patient at the 3 visits (baseline, first year, and second year of follow-up) matched with the PsAID values at each of the 3 visits. PsAID was categorized into two groups (<4 and ≥4). We trained a logistic regression model and random forest-type and XGBoost machine learning algorithms to analyze the association between the outcome measure and the variables selected in the bivariate analysis. A k-fold cross-validation with k = 5 was performed. RESULTS: The sample comprised 158 patients. Of the patients who attended the clinic, 45.8% scored PsAID ≥4 at baseline; 27.1%, at the first follow-up visit, and in 23.0%, at the second follow-up visit. The variables associated with PsAID ≥4 were, in decreasing order of importance: HAQ, pain, educational level, and physical activity. Higher HAQ (logistic regression coefficient 10.394; IC95% 7.777,13.011), higher pain (5.668; 4.016, 7.320), lower educational level (-2.064; -3.515, -0.613) and high level of physical activity (1.221; 0.158, 2.283) were associated with a higher frequency of PsAID ≥4. The mean values of the measures of validity of the algorithms were all ≥85%. CONCLUSIONS: Despite the higher weight given to pain when scoring PsAID, we observed a greater influence of physical function on disease impact.

Minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis: predictive model based on machine learning.

BACKGROUND: Very few data are available on predictors of minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis (PsA). Such data are crucial, since the therapeutic measures used to change the adverse course of PsA are more likely to succeed if we intervene early. In the present study, we used predictive models based on machine learning to detect variables associated with achieving MDA in patients with recent-onset PsA. METHODS: We performed a multicenter observational prospective study (2-year follow-up, regular annual visits). The study population comprised patients aged ≥18 years who fulfilled the CASPAR criteria and less than 2 years since the onset of symptoms. The dataset contained data for the independent variables from the baseline visit and from follow-up visit number 1. These were matched with the outcome measures from follow-up visits 1 and 2, respectively. We trained a random forest-type machine learning algorithm to analyze the association between the outcome measure and the variables selected in the bivariate analysis. In order to understand how the model uses the variables to make its predictions, we applied the SHAP technique. We used a confusion matrix to visualize the performance of the model. RESULTS: The sample comprised 158 patients. 55.5% and 58.3% of the patients had MDA at the first and second follow-up visit, respectively. In our model, the variables with the greatest predictive ability were global pain, impact of the disease (PsAID), patient global assessment of disease, and physical function (HAQ-Disability Index). The percentage of hits in the confusion matrix was 85.94%. CONCLUSIONS: A key objective in the management of PsA should be control of pain, which is not always associated with inflammatory burden, and the establishment of measures to better control the various domains of PsA.

Severe Disease in Patients With Recent-Onset Psoriatic Arthritis. Prediction Model Based on Machine Learning.

Objectives: To identify patient- and disease-related characteristics that make it possible to predict higher disease severity in recent-onset PsA. Methods: We performed a multicenter observational prospective study (2-year follow-up, regular annual visits). The study population comprised patients aged ≥ 18 years who fulfilled the CASPAR criteria and less than 2 years since the onset of symptoms. Severe disease was defined at each visit as fulfillment of at least 1 of the following criteria: need for systemic treatment, Health Assessment Questionnaire (HAQ) > 0.5, polyarthritis. The dataset contained data for the independent variables from the baseline visit and follow-up visit number 1. These were matched with the outcome measures from follow-up visits 1 and 2, respectively. We trained a logistic regression model and random forest-type and XGBoost machine learning algorithms to analyze the association between the outcome measure and the variables selected in the bivariate analysis. Results: The sample comprised 158 patients. At the first follow-up visit, 78.2% of the patients who attended the clinic had severe disease. This percentage decreased to 76.4% at the second visit. The variables predicting severe disease were patient global pain, treatment with synthetic DMARDs, clinical form at diagnosis, high CRP, arterial hypertension, and psoriasis affecting the gluteal cleft and/or perianal area. The mean values of the measures of validity of the machine learning algorithms were all ≥ 80%. Conclusion: Our prediction model of severe disease advocates rigorous control of pain and inflammation, also addressing cardiometabolic comorbidities, in addition to actively searching for hidden psoriasis.

Registro Español de Artritis Psoriásica de Reciente Comienzo (estudio REAPSER). Objetivos y metodología / Spanish Registry of Recent-onset Psoriatic Arthritis (REAPSER study): aims and methodology

OBJETIVOS: Describir la metodología del Registro Español de Artritis Psoriásica de reciente comienzo de la Sociedad Española de Reumatología (REAPSER), así como sus fortalezas y limitaciones. El objetivo principal del proyecto es identificar factores pronósticos de la evolución clínica y radiográfica en una cohorte de pacientes que padecen artritis psoriásica (APs) diagnosticada con menos de 2 años de evolución. MATERIAL Y MÉTODO: Estudio observacional, prospectivo (2 años de seguimiento; periodicidad anual de las visitas), multicéntrico. La intención en la visita basal fue reflejar la situación del paciente antes de que la evolución de la enfermedad se viese modificada por los tratamientos pautados en los servicios de reumatología. Los pacientes fueron invitados a participar consecutivamente en una de sus visitas habituales al reumatólogo. El tamaño muestral finalmente alcanzado fue de 211 pacientes. Se recogen datos sociodemográficos; de situación laboral; historia familiar; antecedentes personales y comorbilidad; antropométricos; estilo de vida; uso de los servicios de salud; situación clínica al diagnóstico de APs; afectación articular y dolor espinal; dolor y valoración global de la enfermedad; entesitis, dactilitis y uveítis; afectación cutánea y ungueal; situación funcional y calidad de vida; evaluación radiográfica; determinaciones analíticas; tratamiento; brotes en esqueleto axial y periférico. CONCLUSIONES: El estudio REAPSER incluye una cohorte de pacientes con APs de inicio reciente reclutados antes de que la evolución de la enfermedad se viese modificada por la prescripción de FAME en los servicios de reumatología. Se espera que la información exhaustiva recogida en las visitas suponga una amplia fuente de datos para futuros análisis

AIMS: To describe the methodology of REAPSER (Spanish Registry of Recent-onset Psoriatic Arthritis), its strengths and limitations. The aim of this study is to identify prognostic factors for the clinical and radiographic course in a cohort of patients with psoriatic arthritis (PsA) diagnosed within 2 years of symptom evolution. METHODS: Multicenter, observational and prospective study (with 2-year follow-up including annual visits). Baseline visit intended to reflect patient situation before the disease course was modified by treatments prescribed in rheumatology departments. Patients were invited to participate consecutively in one of their routine visits to the rheumatologist. 211 patients were included. Following data were collected: sociodemographic variables; employment situation; family history; personal history and comorbidities; anthropometric data; lifestyle; use of healthcare services; clinical situation at the time of PsA diagnosis; joint involvement and spinal pain; pain and overall assessment; enthesitis, dactylitis and uveitis; skin and nail involvement; functional situation and quality of life; radiographic evaluation; analytical determinations; treatment; axial and peripheral flare-ups. CONCLUSIONS: The REAPSER study includes a cohort of patients with recent-onset PsA, before the disease course was modified by disease-modifying antirheumatic drugs prescribed in rheumatology departments. Exhaustive information collected in each visit is expected to be an important data source for future analysis

Association of Platelet Binding to Lymphocytes with B Cell Abnormalities and Clinical Manifestations in Systemic Lupus Erythematosus.

Systemic lupus erythematosus (SLE) is an autoimmune disease associated with the polyclonal activation of B lymphocytes and the production of autoantibodies that cause immune complex-related inflammation. Immunological factors derived from platelets modulate B cell function in SLE disease. However, platelets do not only modify the immune system by soluble factors. The binding of platelets to lymphocytes can modulate immune response. Thus, we speculate that the binding of platelets to lymphocytes in SLE patients may play a role in abnormal B lymphocyte response and the pathogenesis of SLE. We observed that levels of lymphocytes with bound platelets were higher in SLE patients than in healthy donors (HD). In SLE patients, the percentage of B lymphocytes with bound platelets positively correlated with plasmatic levels of IgG, IgA, IL-10, and soluble CD40L and negatively correlated with IgM levels, though not in HD. Preswitched memory B lymphocytes were the subpopulation with more bound platelets. Lymphocytes with bound platelets from both HD and SLE patients had major levels of CD86 and BAFFR and a greater production of IL-10 than lymphocytes without bound platelets. However, only B lymphocytes with bound platelets from SLE patients had increased levels of IgG and IgA on their surface. SLE patients with a suggestive renal manifestation had the highest levels of B and T lymphocytes with bound platelets. These results suggest that the binding of platelets to lymphocytes plays a role in SLE disease and that controlling this binding may be a promising therapeutic approach.

Spanish Registry of Recent-onset Psoriatic Arthritis (REAPSER study): Aims and methodology. / Registro Español de Artritis Psoriásica de Reciente Comienzo (estudio REAPSER). Objetivos y metodología.

AIMS: To describe the methodology of REAPSER (Spanish Registry of Recent-onset Psoriatic Arthritis), its strengths and limitations. The aim of this study is to identify prognostic factors for the clinical and radiographic course in a cohort of patients with psoriatic arthritis (PsA) diagnosed within 2years of symptom evolution. METHODS: Multicenter, observational and prospective study (with 2-year follow-up including annual visits). Baseline visit intended to reflect patient situation before the disease course was modified by treatments prescribed in rheumatology departments. Patients were invited to participate consecutively in one of their routine visits to the rheumatologist. 211 patients were included. Following data were collected: sociodemographic variables; employment situation; family history; personal history and comorbidities; anthropometric data; lifestyle; use of healthcare services; clinical situation at the time of PsA diagnosis; joint involvement and spinal pain; pain and overall assessment; enthesitis, dactylitis and uveitis; skin and nail involvement; functional situation and quality of life; radiographic evaluation; analytical determinations; treatment; axial and peripheral flare-ups. CONCLUSIONS: The REAPSER study includes a cohort of patients with recent-onset PsA, before the disease course was modified by disease-modifying antirheumatic drugs prescribed in rheumatology departments. Exhaustive information collected in each visit is expected to be an important data source for future analysis.

Impact of ultrasonography on treatment decision in rheumatoid arthritis: the IMPULSAR study.

Ultrasonography (US) has shown to be more sensitive than physical examination for diagnosis and assessment of rheumatoid arthritis (RA). It is also a useful approach for accurate monitoring and intensive treatment adjustment. However, there is limited information concerning the impact of US on therapeutic decision-making in routine daily practice. A single-center cross-sectional study in routine daily practice was conducted to determine the percentage of patients with rheumatoid arthritis (RA) in which treatment decision was modified on the basis of results of musculoskeletal ultrasonography. All consecutive patients with RA visited for the control of their disease between September and November 2014 were included. Patients were visited by their attending rheumatologist, who made a therapeutic decision according to the results of physical examination and laboratory tests. Thereafter, a musculoskeletal ultrasound (US) was performed by an independent expert sonographer. According to US findings, a change in therapeutic decision was considered, and categorized as 'negative' (maintenance of the therapeutic attitude) or 'positive' (intensification or reduction of treatment). A total of 78 patients (83% women, mean age 63.3 years) were included. In 29 patients [32%, 95% confidence interval (CI) 26.5-48.9], a change in the therapeutic decision was made, which included intensification of treatment in 18 (62.1%) and reduction of treatment in 11 (37.9%). Change of treatment was more frequent in patients with intermediate disease activity (low and moderate) than in those in clinical remission or with high activity (41.4 vs. 25%), in men than in women (53.8 vs. 33.8%), and in the presence than in the absence of bone erosions (43.6 vs. 21.7%), although differences were not statistically significant. We conclude that in patients with RA, joint US is a relevant complementary tool for treatment decisions in daily practice, particularly in patients with intermediate disease activity.

Sequential nailfold videocapillaroscopy examinations have responsiveness to detect organ progression in systemic sclerosis.

OBJECTIVE: To determine the merit of nailfold videocapillaroscopy (NVC) to detect meaningful microvascular changes over time in patients with systemic sclerosis (SSc) and whether these changes are associated with overall disease progression and organ involvements. METHODS: A prospective cohort of 140 SSc patients was recruited over a 12-month period and was followed up on an annual basis for 3 years. Detailed NVC analysis was performed at inclusion and repeated annually. Disease progression and organ damage were defined according to validated definitions. RESULTS: Significant NVC changes were detected in 72 SSc patients (51%) during the follow-up period. Patients with incident or increased number of giant capillaries were less at risk to develop new digital ulcers (DU) [hazard ratio (HR) = 0.53, 95% confidence interval (CI): 0.07-0.93]. Loss of capillaries over time was confirmed as a robust and independent marker of organ progression. The reduction of the number of capillaries was associated with overall disease progression (HR = 4.35, 95% CI: 1.87-10.12), occurrence of new DU (HR = 5.33, 95% CI: 1.69-16.71), lung vascular progression (HR = 18.53, 95% CI: 1.28-78.33), progression of skin fibrosis (HR = 4.22, 95% CI: 1.24-14.36), and worsening of the Medsger severity score (HR = 5.26, 95% CI: 1.78-15.52). CONCLUSION: Significant NVC changes are observed in almost half of the patients with SSc during a follow-up of 3 years. Sequential NVC examinations have responsiveness to detect disease progression. Sequential NVC is confirmed of value to monitor SSc, as well as progressive loss of capillaries over time as a potential surrogate marker for disease progression.