Prognostic value of automated assessment of interstitial lung disease on CT in systemic sclerosis.

Stratifying the risk of death in systemic sclerosis (SSc)-related interstitial lung disease (SSc-ILD) is a challenging issue. The extent of lung fibrosis on high-resolution computed tomography (HRCT) is often assessed by a visual semi-quantitative method that lacks reliability. We aimed to assess the potential prognostic value of a deep-learning based algorithm allowing for automated quantification of ILD on HRCT in patients with SSc. We correlated the extent of ILD with the occurrence of death during follow-up and evaluated the additional value of ILD extent to predict death based on a prognostic model including well-known risk factors in SSc. We included 318 patients with SSc among which 196 had ILD; median follow-up was 94 months (interquartile range 73-111). Mortality rate was 1.6% at 2 years and 26.3% at 10 years. For each 1% increase in the baseline ILD extent (up to 30% of the lung), the risk of death at 10 years was increased 4% (hazard ratio 1.04, 95%CI 1.01-1.07, p = 0.004). We constructed a risk prediction model that showed good discrimination for 10-year mortality (c index 0.789). Adding the automated quantification of ILD significantly improved the model for 10-year survival (p = 0.007) but its discrimination only marginally. However, it improved the ability to predict 2-year mortality (difference in time-dependent AUC 0.043, 95%CI 0.002-0.084, p = 0.040). The deep-learning-based, computer-aided quantification of ILD extent on HRCT provides an effective tool for risk stratification in SSc. It might help identify patients at short-term risk of death.

Informations de copyright

© The Author(s) 2023. Published by Oxford University Press on behalf of the British Society for Rheumatology. All rights reserved. For permissions, please email: [e-mail].