Imaging-Based Mortality Prediction in Patients with Systemic Sclerosis

2025-09-27

AI Summary

Systemic sclerosis–associated interstitial lung disease (SSc-ILD) is a leading cause of mortality, yet conventional CT-based assessments exhibit limited prognostic accuracy for mortality risk. To address this, we developed the first large-scale longitudinal chest CT analysis framework specifically for SSc-ILD, integrating radiomics with deep learning to enable dynamic mortality risk prediction. We fine-tuned pre-trained models—including ResNet-18, DenseNet-121, and Swin Transformer—on 2,125 patient CT scans. The model achieved AUCs of 0.769, 0.801, and 0.709 for 1-, 3-, and 5-year mortality prediction, respectively, significantly outperforming traditional clinical metrics. Our key contributions are: (1) establishing the first SSc-specific longitudinal CT modeling paradigm, overcoming the limitations of single-timepoint static analysis; and (2) demonstrating the strong discriminative power of multi-scale deep features for progression-associated mortality risk, yielding interpretable imaging biomarkers to guide early therapeutic intervention.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements

Abstract

Interstitial lung disease (ILD) is a leading cause of morbidity and mortality in systemic sclerosis (SSc). Chest computed tomography (CT) is the primary imaging modality for diagnosing and monitoring lung complications in SSc patients. However, its role in disease progression and mortality prediction has not yet been fully clarified. This study introduces a novel, large-scale longitudinal chest CT analysis framework that utilizes radiomics and deep learning to predict mortality associated with lung complications of SSc. We collected and analyzed 2,125 CT scans from SSc patients enrolled in the Northwestern Scleroderma Registry, conducting mortality analyses at one, three, and five years using advanced imaging analysis techniques. Death labels were assigned based on recorded deaths over the one-, three-, and five-year intervals, confirmed by expert physicians. In our dataset, 181, 326, and 428 of the 2,125 CT scans were from patients who died within one, three, and five years, respectively. Using ResNet-18, DenseNet-121, and Swin Transformer we use pre-trained models, and fine-tuned on 2,125 images of SSc patients. Models achieved an AUC of 0.769, 0.801, 0.709 for predicting mortality within one-, three-, and five-years, respectively. Our findings highlight the potential of both radiomics and deep learning computational methods to improve early detection and risk assessment of SSc-related interstitial lung disease, marking a significant advancement in the literature.

Problem

• Predicting mortality in systemic sclerosis patients using CT scans
• Developing AI framework for SSc-ILD progression and risk assessment
• Improving early detection of lung complications through computational analysis

Innovation

• Large-scale longitudinal chest CT analysis framework
• Radiomics and deep learning predict SSc mortality
• Pre-trained models fine-tuned on 2,125 patient scans