Proteomic profiling and machine learning for endotype prediction in chronic rhinosinusitis

Abstract

Background: Chronic rhinosinusitis (CRS) is a common, heterogeneous upper airway inflammatory disorder, affecting approximately 12% of the general population. The disease is clinically stratified into CRS without nasal polyps and CRS with nasal polyps, including the most severe subtype of nonsteroidal anti-inflammatory drug (NSAID)-exacerbated respiratory disease (N-ERD).

Objective: To identify molecular signatures and biomarkers allowing for the distinction between different disease endotypes and controls, we used targeted proteomics combined with bioinformatics and machine learning analyses.

Methods: Nasal secretions and serum from 80 patients (20 each of CRS without nasal polyps, CRS with nasal polyps, N-ERD, and disease controls) were subjected to high-throughput targeted proteomics (Olink). The expression patterns of 161 and 2677 proteins, for nasal secretions and serum, respectively, were analyzed alongside clinical evaluations of nasal polyp and smell test scores.

Results: Two distinct expression patterns were identified in nasal secretions: proteins associated with macrophage recruitment and type 2 inflammation were increased in CRS with nasal polyps and N-ERD, whereas proteins associated with innate immunity, particularly Toll-like receptor 4 signaling, were gradually downregulated from disease control to N-ERD. Furthermore, using machine learning, we confirmed 2 potential biomarkers for nasal polyposis: the glial cell line-derived neurotrophic factor in nasal secretions and Charcot-Leyden crystal protein in serum.

Conclusions: Our findings provide unique insights into CRS pathophysiology and highlight potential biomarkers for precision diagnosis and treatment, particularly in severe cases such as N-ERD.

Keywords: Nasal polyposis; biomarker; machine learning; type 2 inflammation.