To our knowledge, this is the first published case study of a salmon processing worker with occupational hypersensitivity pneumonitis, where the causative antigen was investigated by immunoblot analysis utilising the patient's serum. Both known and previously unidentified salmon antigens were detected.

Intravascular large B-cell lymphoma (IVLBCL) is a rare and often fatal malignancy that presents with non-specific pulmonary symptoms and abnormal imaging findings. We report a unique case of IVLBCL in a 73-year-old man who initially presented with fever and bilateral ground-glass opacities on computed tomography that mimicked hypersensitivity pneumonitis. The symptoms temporarily improved with environmental antigen avoidance, which delayed a correct diagnosis. Ultimately, transbronchial lung cryobiopsy confirmed IVLBCL, and chemotherapy was effective. This case highlights the potential for spontaneous regression of IVLBCL and the importance of considering malignancy when clinical improvement is not sustained.

In patients over 60 years of age who are male, non-smokers, and in whom no organic antigen is identified in the history, differentiating fibrotic hypersensitivity pneumonitis (HP) from idiopathic pulmonary fibrosis (IPF) may be challenging. We aimed to evaluate the contribution of deep learning-based feature extraction and machine learning classification in differentiating these two pathologies, which exhibit similar radiological patterns on high-resolution computed tomography (HRCT) images. The study retrospectively included 87 patients (52 IPF, 35 HP). To completely eliminate data leakage and class imbalance-common methodological flaws in medical AI-we implemented a rigorous 10-repeated fivefold patient-level cross-validation strategy combined with hierarchical random undersampling. A pre-trained AlexNet architecture was utilized strictly as a robust feature extractor (via the fc8 layer) without fine-tuning. The extracted 1000-dimensional semantic features were subsequently classified using Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) algorithms. Under strict patient-level isolation across 50 independent training-testing cycles, the SVM classifier achieved an average accuracy of 83.03%, sensitivity of 81.74%, specificity of 84.29%, F1-score of 82.32%, and an area under the curve (AUC) of 91.93%. The KNN classifier yielded an average accuracy of 80.56% and an AUC of 87.66%. By effectively overcoming data leakage and bias, this study demonstrates the true generalization capability of deep feature extraction in distinguishing IPF from fibrotic HP. The proposed framework provides a highly robust and reliable non-invasive decision-support tool for challenging diagnostic scenarios.

Hypersensitivity pneumonitis (HP) is characterized by an excessive pulmonary T cell response after exposure to inhaled antigens. Antigen avoidance is the best treatment, but in most cases, an antigen cannot be identified. Profiling antigen-specific T cell responses in HP may provide a strategy to identify causative antigens. We used public RNA sequencing data and reconstructed T cell receptor (TCR) repertoires from bronchoalveolar lavage samples from patients with HP and idiopathic pulmonary fibrosis and healthy controls. After excluding TCR sequences likely to be related to common microbial exposures in patients with HP, we identified TCRs shared between patients with shared human leukocyte antigen alleles, indicating patients likely to have a common causative antigen. We also found clusters of identical and similar TCR clones in individual patients that are plausibly related to the causative antigens in those patients. These results establish the feasibility of profiling TCR repertoires to identify antigens in HP.