A total of 119 subjects were enrolled from the Chinese Interstitial Lung Disease (ILD) National Cohort and the PORTRAY IPF Cohort between July 2018 and June 2022, including 32 healthy controls (HCs), 31 non-fibrotic HP (NFHP), 28 FHP, and 28 IPF cases. Plasma samples underwent quantitative proteomic profiling, weighted gene co-expression network analysis (WGCNA), and bioinformatics analysis to identify differentially expressed proteins, core pathways, and co-expression modules. Key proteins were selected to construct and validate disease differentiation models using machine learning algorithms. The proteomic dataset comprised 813 identified proteins, with 493 reliably quantified. Pathway analysis implicated nitrogen metabolism, alcohol addiction signaling, and thyroid hormone biosynthesis in disease pathogenesis. A machine learning-based proteomic model was developed for differentiating HP subtypes from IPF. The support vector machine (SVM) algorithm demonstrated the most robust and balanced performance on an independent test set, achieving an accuracy of 71.4% with equal sensitivity and specificity. This model provides a non-invasive tool for preliminary case differentiation and suggests potential biomarkers for precision medicine in fibrotic lung diseases.