Background: Interstitial lung disease (ILD) is the most common and serious organ manifestation in patients with connective tissue diseases (CTD). Given that ILD is a leading cause of mortality in most CTD, early diagnosis, severity assessment and consequent therapy is essential.

Objectives: The objective of this study was to evaluate the effects of clinical parameters such as pulmonary symptoms, age, gender or pulmonary functions test (PFT) on quantified ILD features (e. g. ground glass opacities [GGO], reticulations or lung volume) measured by artificial intelligence quantification of pulmonary HRCT (AIpqHRCT) and finally to specify ILD prediction.

Methods: The study included 76 CTD patients with ILD. All patients received HRCT and PFT including the following parameters (diffusing capacity of the lungs for carbon monoxide [DLCO], forced expiratory volume in 1 second [FEV1] and total lung capacity [TLC]). AIpqHRCT was used to quantify ILD features including GGO, reticulations, high attenuation lung volume (HAV), lung volumetry and emphysema. To evaluate the influence of clinical parameters to ILD features subsequent multiple linear regression analysis was performed.

Results: AIpqHRCT analysis of ILD showed 8.91±9.66% (GGO), 4.06±7.33% (reticulations), 0.68±2.41% (honey combing) and 12.70±9.37% HAV. The PFT demonstrated the following mean values: FVC 75.5±17.5%, TLC 77.4±14.8% and DLCO 51.6±16.9%. The subsequent multiple linear regression analysis demonstrated for GGO significant negative correlations regarding female gender (b=-0.79; [-1.32, -0.26]) and TLC (b=-0.57; [-0.91, -0.24]), DLCO (b=-0.32; [-0.56, -0.08]). Similar effects were obtained for reticulations. Regarding HAV, the analysis revealed significant negative correlation to female gender (b=-0.63; [-1.10, -0.16]), TLC (b=-0.44; [-0.74, -0.15]) and DLCO (b=-0.36; [-0.57, -0.15]). In all measured ILD features, FVC demonstrated no significance for predicting ILD.

Conclusion: The study revealed a significant influence of female gender, TLC and DLCO on the severity of ILD as quantified by AIpqHRCT. These parameters can be used as valuable predictors for ILD in CTD patients. Overall, the study highlights the potential of using specific clinical parameters in association with advanced imaging techniques to enhance the prediction ILD in CTD patients.

REFERENCES: NIL.

Acknowledgements: This research has been partially funded by the “Bundesministerium für Bildung und Forschung”, Germany (BMBF, FKZ: 01KX2021 and 01KX2121 as part of “Netzwerk Universitätsmedizin” [NUM] 2.0).

Disclosure of Interests: None declared.

© 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.