Pathway‑based detection of idiopathic pulmonary fibrosis at an early stage.

Abstract

Idiopathic pulmonary fibrosis (IPF) is the most common interstitial pneumonia and the most aggressive interstitial lung disease. Usually, IPF is confirmed by the histopathological pattern of typical interstitial pneumonia and requires an integrated multidisciplinary approach from pulmonologists, radiologists and pathologists. However, these diagnoses are performed at an advanced stage of IPF. At present, pathway-based detection requires investigation, as it can be performed at an early stage of the disease. The aim of the present study was to find an effective method of diagnosing IPF at an early stage. Microarray data for E-GEOD-33566 were downloaded from the ArrayExpress database. Human pathways were downloaded from Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway database. An individual pathway-based method to diagnose IPF at an early stage was introduced. Pathway statistics were analyzed with an individualized pathway aberrance score. P-values were obtained with different methods, including the Wilcoxon test, linear models for microarray data (Limma) test and attract methods, generating three pathway groups. Support vector machines (SVM) were used to identify the best group for diagnosing IPF at an early stage. There were 106 differential pathways in Wilcoxon-based KEGG Pathway (n>5) group, 100 in the Limma-based KEGG Pathway (n>5) group, and seven in the attract-based KEGG Pathway (n>5) group. The pathway statistics of these differential pathways in three groups were analyzed with linear SVM. The results demonstrated that the Wilcoxon-based KEGG Pathway (n>5) group performed best in diagnosing IPF.