Bayesian Integration of Bronchoalveolar Lavage miRNAs and KL-6 in Progressive Pulmonary Fibrosis Diagnosis

Background/Objectives: Progressive pulmonary fibrosis (PPF) represents one of the most severe and complex challenges in respiratory medicine, characterized by a rapid decline in lung function and often poor prognosis, making it a priority in research on interstitial lung diseases (ILDs). The aim of this study is to correlate classical clinical features and three genetic biomarkers with the diagnosis and prognosis of progressive pulmonary fibrosis in ILDs. Methods: This study involved 19 patients with progressive pulmonary fibrosis (PPF) and 20 patients with non-progressive pulmonary fibrosis (nPPF) from the S.C. of Respiratory System Diseases at the Policlinico of Foggia (Italy) between 2015 and 2022. All participants underwent pulmonary function tests (PFTs), a 6 min walk test (6MWT), and bronchoalveolar lavage (BAL) sampling, following the acquisition of written consent for these procedures. Bayesian analysis with generalized linear models has been applied for both diagnostic and prognostic classification. Results: The proposed Bayesian model enables the estimation of the contribution of each considered feature, and the quantification of the uncertainty that is consequential to the small size of the dataset. The analysis of miRNAs such as miR-21 and miR-92a, alongside the protein biomarker KL-6, was identified as a significant indicator for PPF diagnosis, enhancing both the sensitivity and specificity of predictions. Conclusions: The identification of specific genetic markers such as microRNAs and their integration with traditional clinical characteristics can significantly enhance the management of patients with the disease. This multidimensional approach, which integrates clinical data with omics data, could enable more precise identification and monitoring of the disease and potentially optimize future treatments through larger studies and extended follow-ups.