Multimodal Fusion of Chest X-Rays and Blood Biomarkers for Automated Silicosis Staging

Background/Objectives: Silicosis, a fibrotic lung disease, is re-emerging globally, driven by an aggressive form linked to engineered stone processing that rapidly progresses to progressive massive fibrosis (PMF). The standard diagnostic approach, chest X-ray (CXR), is subject to considerable inter-observer variability, making the distinction between simple silicosis (SS) and PMF particularly challenging. The purpose of this study was to develop and validate an automated multimodal framework for silicosis staging by integrating artificial intelligence (AI), CXR images, and routine blood biomarkers. Methods: We developed three fusion architectures, early, late, and hybrid, connecting blood biomarker analysis with CXR analysis. Deep learning and conventional (shallow) machine learning models were combined. The models were trained and validated on a cohort of 94 patients with engineered stone silicosis, providing 341 paired CXR and biomarker samples. A patient-aware 5-fold cross-validation was used to ensure the model's generalizability and prevent patient data leakage between folds. Results: The hybrid and late fusion models achieved the best performance for disease staging, yielding an area under the receiver operating characteristic (ROC) curve (AUC) of 0.85. This multimodal approach outperformed both the unimodal CXR-based model (AUC = 0.83) and the biomarker-based model (AUC = 0.70). Conclusions: This study reveals that AI-based techniques that utilize a multimodal fusion approach have the potential to outperform single-modality methods have the potential to serve as an objective decision support tool for clinicians, leading to more consistent staging and improved patient management.