PT  - JOURNAL ARTICLE
AU  - J. A. Román Ivorra
AU  - I. De la Morena
AU  - N. Costas Torrijo
AU  - B. Safont
AU  - J. Fernández-Melón
AU  - B. Nuñez
AU  - L. Silva Fernández
AU  - L. Cebrián Méndez
AU  - L. Lojo
AU  - B. López-Muñiz
AU  - E. Trallero
AU  - M. Lopez Lasanta
AU  - R. M. Veiga Cabello
AU  - M. D. P. Ahijado Guzman
AU  - D. Benavent
AU  - D. Vilanova
AU  - R. Castellanos Moreira
AU  - S. Lujan Valdés
ED  - ,
TI  - OP0132 PREVALENCE AND COMORBIDITIES OF RHEUMATOID ARTHRITIS-ASSOCIATED INTERSTITIAL LUNG DISEASE IN SPAIN: A RETROSPECTIVE ANALYSIS OF ELECTRONIC HEALTH RECORDS USING NATURAL LANGUAGE PROCESSING
AID  - 10.1136/annrheumdis-2022-eular.5042
DP  - 2022 Jun 01
TA  - Annals of the Rheumatic Diseases
PG  - 85--85
VI  - 81
IP  - Suppl 1
4099  - http://ard.bmj.com/content/81/Suppl_1/85.1.short
4100  - http://ard.bmj.com/content/81/Suppl_1/85.1.full
SO  - Ann Rheum Dis2022 Jun 01; 81
AB  - Background Interstitial 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.Objectives This 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.Methods Observational, 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.Results Among 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).View this table:Table 1. Demographics and comorbidities in the RA and RA-ILD patient populationsConclusion This 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.Acknowledgements RA-W-ILD Study GroupDisclosure of Interests Jose 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