BackgroundInterstitial lung disease (ILD) is one of the most frequent extra-articular manifestations of rheumatoid arthritis (RA) and leads to a significantly increased risk for morbidity and mortality compared with RA alone [1]. The analysis of Electronic Health Records (ERHs) using machine learning (ML) and Natural Language Processing (NLP) holds great promise to better characterize the disease in real-world settings.ObjectivesThis study aims to a) estimate the prevalence of RA in Spain, b) determine the frequency of RA-ILD among RA patients, and c) describe the demographic and clinical characteristics in RA/RA-ILD patients.MethodsObservational, retrospective, and multicenter study based on the secondary use of unstructured clinical data in EHRs from 6 Spanish hospitals between January 1, 2014 and December 31, 2019. The free-text information from patients’ records was captured with SAVANA’s EHRead, a validated NLP technology which extracts clinical information from EHRs and standardizes it into a SNOMED-CT-based clinical terminology [2]. The study population comprised all adult patients ≥18 years with RA in the selected period and sites. Descriptive statistics were presented in summary tables. Prevalence was calculated dividing the total number of patients with RA over the total number of attended patients. This analysis was performed by age and sex.ResultsAmong all attended patients in the participating hospitals within the study period, 11,163 patients with RA were identified; of these, 8.6% (n = 959) had RA-associated ILD (RA-ILD). The age-adjusted prevalence of RA is shown in Figure 1. The estimated prevalence (95% CI) in the overall population was 0.49 (0.37-0.60), being 0.26 (0.19-0.32) in males and 0.71 (0.54-0.87) in females. Most patients in the RA (73.9%; n = 8,250) and RA-ILD populations (63.3%, n = 607) were female (Table 1). The median age (Q1, Q3) was 60.8 (49, 74) and 67 (56, 77) years in the RA and RA-ILD groups, respectively. Regarding disease course, the time from RA to ILD diagnosis was 27.6 (3.7, 73.2) months. Most comorbidities presented higher rates in the RA-ILD population, as shown in Table 1. Among patients with available ILD subtype information (n = 618), the most common was usual interstitial pneumonia (29.8%; n = 184).Table 1.Demographics and comorbidities in the RA and RA-ILD patient populationsRA* N=11,163RA-ILD N=959Gender, n (%) Female8,250 (73.9)607 (63.3) Male2,913 (26.1)352 (36.7)Age at first mention of disease (years)1  Median (Q1, Q3)61 (49, 74)67 (56, 77)Comorbidities, n (%)Dyslipidaemia4369 (39.1)316 (33)Hypertension3851 (34.5)320 (33.4)Diabetes mellitus2970 (26.6)248 (25.9)Infections2129 (19.1)328 (34.2)Bone fracture1875 (16.8)210 (21.9)Osteoporosis1275 (11.4)150 (15.6)Malignancies1004 (9)169 (17.6)Kidney failure1006 (9)156 (16.3)Heart failure993 (8.9)184 (19.2)Depression825 (7.4)99 (10.3)Psoriasis773 (6.9)39 (4.1)Obesity732 (6.6)90 (9.4)Asthma740 (6.6)82 (8.6)Atrial Fibrillation729 (6.5)102 (10.6)*RA includes patients in the RA-ILD population. 1Patients’ age when either RA or ILD was first detected in the EHRs. RA = rheumatoid arthritis; ILD = interstitial lung diseaseConclusionThis pioneering study is the first to characterize RA-ILD using NLP methodology in a multicenter setting. By analyzing readily available real-world data in patients EHRs, we were able to estimate the prevalence of RA in the Spanish population and describe the demographic and clinical characteristics of patients with RA/RA-ILD.References[1]Bongartz T, Nannini C, Medina-Velasquez YF et al. Incidence and mortality of interstitial lung disease in rheumatoid arthritis: a population-based study. Arthritis and rheumatism 2010; 62: 1583-1591.[2]Canales L, Menke S, Marchesseau S et al. Assessing the Performance of Clinical Natural Language Processing Systems: Development of an Evaluation Methodology. JMIR Med Inform 2021; 9: e20492.AcknowledgementsRA-W-ILD Study GroupDisclosure of InterestsJose Andrés Román Ivorra Speakers bureau: AbbVie, Bristol Myers Squibb, FER, Galápagos, GlaxoSmithKline, Janssen, Lilly, Novartis, Pfizer, Consultant of: AbbVie, Bristol Myers Squibb, FER, Galápagos, GlaxoSmithKline, Janssen, Lilly, Novartis, Pfizer, Grant/research support from: AbbVie, Bristol Myers Squibb, FER, GlaxoSmithKline, Janssen, Lilly, MSD, Novartis, Pfizer, UCB, Isabel de la Morena Speakers bureau: Pfizer, Novartis, Janssen, AbbVie, MSD, UCB, Sanofi, Roche, Nordic, Lilly, NEREA COSTAS TORRIJO Speakers bureau: UCB, Novartis, Pfizer, Belen Safont Speakers bureau: AstraZeneca, Roche, Boehringer Ingelheim, Grant/research support from: Boehringer Ingelheim, J. Fernández-Melón Speakers bureau: Bristol Myers Squibb, UCB, Galapagos, Belen Nuñez Speakers bureau: Boehringer Ingelheim, Roche, Bristol Myers Squibb, Grant/research support from: Boehringer Ingelheim, Roche, Lucía Silva Fernández Speakers bureau: Bristol Myers Squibb, Consultant of: Novartis, MSD, Laura Cebrián Méndez Speakers bureau: Pfizer, Lilly, Gebro, Novartis, Consultant of: Pfizer, Leticia Lojo Consultant of: UCB, Belén López-Muñiz Speakers bureau: Boehringer Ingelheim, Roche, AstraZeneca, Novartis, Mundipharma, Gebro, GlaxoSmithKline, Ernesto Trallero Speakers bureau: Amgen, MSD, Maria Lopez Lasanta: None declared, Raul Maria Veiga Cabello: None declared, Maria Del Pilar Ahijado Guzman: None declared, Diego Benavent Speakers bureau: Janssen, Roche, Grant/research support from: Novartis, Employee of: Savana, David Vilanova Shareholder of: Bristol Myers Squibb, Employee of: Bristol Myers Squibb, Celgene, Raul Castellanos Moreira Speakers bureau: Lilly, Pfizer, Roche, Sanofi, UCB, Bristol Myers Squibb, Consultant of: Bristol Myers Squibb, Employee of: Bristol Myers Squibb, Sara Lujan Valdés Shareholder of: Bristol Myers Squibb, Employee of: Bristol Myers Squibb

BackgroundGuselkumab is a monoclonal antibody against interleukin-23, biological agent approved for the treatment of plaque psoriasis and psoriatic arthritis. There are two randomised, double-blind, placebo-controlled phase III studies (DISCOVER 1 and DISCOVER 2) that evaluated the efficacy and safety of guselkumab versus placebo. Treatment with guselkumab resulted in significant improvements in the measures of disease activity compared to placebo at Week 24. 1ObjectivesTo evaluate the response to Guselkumab in patients with Psoriatic Arthritis, according to CASPAR criteria, undergoing treatment by dermatology indication.MethodsThis is an observational descriptive retrospective study that includes patients with Psoriatic Arthritis (acording to CASPAR criteria) who are being treated with Guselkumab under dermatology indication due to skin involvement. In this study, the epidemiological and clinical characteristics of the patients are assessed: IMC, affected domains, previous treatments, concomitant treatments, PASI before begining the treatment, at 12 week and 24 week, and joint activity mesured by DAPSA at the beggining, after 12 and 24 week.ResultsThere are 7 patients included, 5 women and 2 men, the mean age were 50 ± 7.9 years old, with a BMI (body mass index) average of 33.13 ± 6.26. All the patients presented skin involvement: 4 of 7 with plaque psoriasis (2 of them with scalp psoriasis, and one of those two with inverse psoriasis), 3 of 7 with psoriasis in palms and soles (one with scalp psoriasis and inverse psoriasis), and 2 of 7 pacients with nail involvement. Regarding joint damage, all the patients presented peripheral joint involvement, 2 of 7 with axial too. For the other domains: 2 of 7 have had recurring uveitis, 1 of 7 one episode of dactylitis, and none of them any episode of enthensitis nor inflammatory bowel disease. All the patients had received at least 1 bDMARD (average of 2.8 ± 2.23, but one of them have used 7 before). All the patients received the standard dose of Guselkumab 100mg sc (week 0 and 4) and later each 2 months, with a duration of treatment in months with an average of 6.3 ± 2.88. At the same time, 1 of 7 patient used Methotrexate concomitantly, 2 of 7 with leflunomide, and 1 of 7 with NSAIDs. The PASI average at the beggining of the treatment with Guselkumab was 9.25 ± 4.99, at 12 week all the patients had obtain a PASI 0, and remained in remission. Regarding joint damage measured with DAPSA, at the beggining of Guselkumab treatment the average was 24.15 ± 22.02, at 12 week 12.19 ± 5.56, at the 24 week 8.86 ± 1.6, all of the patients improved, without any inflammatory flares. Any of them presented uveitis, enthensitis nor dactylitis. Drug retention rate of 100%, all the patients are still in treatment with Guselkumab, any side effect was detected.ConclusionGuselkumab is a very effective drug for the treatment of psoriasis, but also for the joint involvement in patients with failure to bDMARD. We need more real life studies to determinate the effectiveness in daily clinical practise.References[1]Guselkumab in patients with active psoriatic arthritis who were biologic-naive or had previously received TNFα inhibitor treatment (DISCOVER-1): a double-blind, randomised, placebo-controlled phase 3 trial Atul Deodhar 1, Philip S Helliwell 2, Wolf-Henning Boehncke 3, Alexa P Kollmeier 4, Elizabeth C Hsia 5, Ramanand A Subramanian 6, Xie L Xu 4, Shihong Sheng 7, Prasheen Agarwal 7, Bei Zhou 7, Yanli Zhuang 8, Christopher T Ritchlin 9, DISCOVER-1 Study Group Lancet 2020 Apr 4;395(10230):1115-1125. doi: 10.1016/S0140-6736(20)30265-8. Epub 2020 Mar 13.[2]Guselkumab in biologic-naive patients with active psoriatic arthritis (DISCOVER-2): a double-blind, randomised, placebo-controlled phase 3 trial. Philip J Mease 1, Proton Rahman 2, Alice B Gottlieb 3, Alexa P Kollmeier 4, Elizabeth C Hsia 5, Xie L Xu 4, Shihong Sheng 6, Prasheen Agarwal 6, Bei Zhou 6, Yanli Zhuang 7, Désirée van der Heijde 8, Iain B McInnes 9, DISCOVER-2 Study Group Lancet 2020 Apr 4;395(10230):1126-1136. doi: 10.1016/S0140-6736(20)30263-4. Epub 2020 Mar 13.Disclosure of InterestsNone declared