Background: Interstitial Lung Disease (ILD) is increasingly recognized as a common extra-glandular manifestation of Sjögren’s Disease (SjD), potentially associated with a high mortality burden. However, current literature offers limited data about the prevalence of progressive ILD in SjD and novel biomarkers to predict a progressive behavior warranting specific treatments are needed. Computer-Aided Lung Informatics for Pathology Evaluation and Rating (CALIPER) is an automated CT quantitative analysis software trained and validated against histopathology to identify and quantify ILD patterns including ground-glass, reticular, honeycombing, and low attenuation areas. CALIPER-derived ILD parameters have been recently shown to correlate with pulmonary function tests (PFT) and outcome both in Idiopathic Pulmonary Fibrosis (IPF) and other autoimmune-associated ILDs. However, no longitudinal studies have investigated the role of computer-aided imaging analysis in SjD-ILD.

Objectives: To evaluate the utility of CALIPER in assessing and predicting the outcome in SjD-ILD patients.

Methods: Consecutive SjD patients (2016 ACR/EULAR classification criteria) with HRCT-confirmed ILD under follow-up from January 2018 to September 2023 were retrospectively enrolled if one or more HRCT scans were available and suitable for lung parenchymal extraction, segmentation and processing with CALIPER. Clinical and laboratory data, respiratory symptoms and PFT results were collected at the time of baseline HRCT and at follow-up. Progressive fibrosing (PF)-ILD was defined according to ATS criteria [1] as the presence of at least 2/3 of the following: worsening respiratory symptoms, significant functional decline (FVC ≥5% or DLCO ≥10%), or radiological progression, within 1 year from the baseline HRCT. CALIPER-derived parameters, including ILD extent (sum of ground glass, reticular, and honeycombing areas) expressed as percentage of total lung (ILD%) and the volume of Vascular-Related-Structures expressed as a percentage of total lung (VRS%), were assessed. Visual ILD quantification using the Warrick score and ILD pattern classification were performed by an expert thoracic radiologist.

Results: Twenty-three SjD-ILD patients (F:M=18:5) were enrolled, with a mean age at diagnosis of 66.2 (±9.5) years and a mean follow-up of 6.1 (±5) years. Anti-SSA antibodies were present in 17/23 patients. ILD patterns were classified as NSIP (n=14), UIP (n=6), and NSIP+OP (n=3). Dyspnea and cough were reported in 21 and 19 patients, respectively. Median baseline FVC and DLCO were 83 (IQR 65.8–99) and 64 (IQR 49.5–77), respectively. Seventeen patients received steroids and/or immunosuppressive therapy, but none were treated with antifibrotics. Seven patients required long-term oxygen therapy (LTO2), and 7/23 developed PF-ILD as defined by ATS criteria. Both baseline ILD% and VRS% demonstrated a moderate to strong correlation with baseline FCV% and DLCO%, visual ILD quantification with Warrick score and between them (see Table 1). VRS%, Reticulation%, and Honeycombing% were significantly higher in UIP patients compared to other ILD patterns (p=.021, p=.038, and p=.047, respectively). On univariate regression analysis, VRS% (OR 3.2, 95%CI 1.1-9.1, p=.03) and ILD% (OR 1.13, 95%CI 1.01-1.3, p=.05) were associated with LTO2 necessity. According to ROC analysis, VRS% had an AUC of 0.813 (p=.019) with an optimal cut-off of 3.8%, yielding a sensitivity of 71.4% and a specificity of 87.5% in predicting LTO2 necessity. ILD% had an AUC of 0.777 (p=.038) with a cut-off of 11.6% resulting in a sensitivity of 71.4% and a specificity of 75% in predicting LTO2 necessity. Moreover, on univariate regression analysis VRS% (OR 2.8, 95%CI 1-8, p=.05) was associated with a PF-ILD behavior in the next year, with an AUC of 0.85 (p=.023) and an optimal cut-off of 3.8% resulting in a sensitivity of 83.3% and specificity of 80%.

Conclusion: CALIPER-derived parameters exhibited a strong correlation with functional indices in SjD-ILD patients, with higher values associated with an adverse respiratory outcome and a PF-ILD phenotype. Computer-aided HRCT analysis may provide novel valuable digital imaging biomarkers for assessing and stratifying SjD-ILD patients. Integrating CALIPER-derived parameters with clinical and functional data may assist rheumatologists in identifying patients at risk for progressive ILD who could benefit from early combination therapy with immunosuppressive and antifibrotic agents. Future studies with larger SjD-ILD cohorts are needed to validate these findings.

REFERENCES: [1] Raghu G, Remy-Jardin M, Richeldi L, Thomson CC, Inoue Y, Johkoh T, et al. Idiopathic Pulmonary Fibrosis (an Update) and Progressive Pulmonary Fibrosis in Adults: An Official ATS/ERS/JRS/ALAT Clinical Practice Guideline. Am J Respir Crit Care Med. 2022;205(9):e18-e47.

Acknowledgements: NIL.

Disclosure of Interests: Gaetano La Rocca: None declared , Francesco Ferro: None declared , Vincenzo Uggenti: None declared , Beatrice Dei: None declared , Giovanni Fulvio: None declared , Inmaculada Concepción Navarro García: None declared , Marta Mosca: None declared , Chiara Romei: None declared , Chiara Baldini Training for GSK and Sanofi, Amgen, Amgen, GSK, Sanofi, Aurina, Novartis, johnson & johnson.

© The Authors 2025. This abstract is an open access article published in Annals of Rheumatic Diseases under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ ). Neither EULAR nor the publisher make any representation as to the accuracy of the content. The authors are solely responsible for the content in their abstract including accuracy of the facts, statements, results, conclusion, citing resources etc.