Abstract
COPD (chronic obstructive pulmonary disease) and ILD (interstitial lung disease) are two common respiratory diseases. They share similar clinical traits but require different therapeutic treatments. Identifying the biomarkers that are differentially expressed between them will not only help the diagnosis of COPD and ILD, but also provide candidate drug targets that may facilitate the development of new treatment for COPD and ILD. Due to the irreversible complex pathological changes of COPD, there are very limited therapeutic options for COPD patients. In this study, we analyzed the gene expression profiles of two datasets: one training dataset that includes 144 COPD patients and 194 ILD patients, and one test dataset that includes 75 COPD patients and 61 ILD patients. Advanced feature selection methods, mRMR (minimal Redundancy Maximal Relevance) and incremental feature selection (IFS), were applied to identify the 38-gene biomarker. An SVM (support vector machine) classifier was built based on the 38-gene biomarker. Its accuracy, sensitivity, and specificity on training dataset evaluated by leave one out cross-validation were 0.905, 0.896, and 0.912, respectively. And on independent test dataset, the accuracy, sensitivity, and specificity on were as great as and were 0.904, 0.933, and 0.869, respectively. The biological function analysis of the 38 genes indicated that many of them can be potential treatment targets that may benefit COPD and ILD patients.
Highlights
COPD and ILD are both common lung diseases (Andersen et al, 2013)
The mRMR ranked the genes based on their relevance with disease types, COPD or ILD, and their redundancy with selected genes
The Optimal Biomarkers Identified From the mRMR Gene List With incremental feature selection (IFS) Methods
Summary
COPD (chronic obstructive pulmonary disease) and ILD (interstitial lung disease) are both common lung diseases (Andersen et al, 2013). Cigarette smoking is the biggest risk factor for COPD and ILD (Caminati et al, 2012). COPD is an independent risk factor of lung cancer. Both emphysema and non-emphysema COPD phenotypes significantly increased the risk of lung cancer (Wang et al, 2018). Epidemiological studies have found that COPD increases the risk of lung cancer by two to six times, regardless of whether there is a history of smoking or not (Papi et al, 2004; Young et al, 2009). Since the complex pathological changes in COPD and most of ILD patients are not irreversible, the diseases cause extensive mortality and are great public health problems worldwide (Vogelmeier et al, 2017)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
