Prediction of lung emphysema in COPD by spirometry and clinical symptoms : results from COSYCONET

Abstract

Background: Lung emphysema is an important phenotype of chronic obstructive pulmonary disease (COPD), and CT scanning is strongly recommended to establish the diagnosis. This study aimed to identify criteria by which physi‑ cians with limited technical resources can improve the diagnosis of emphysema. Methods: We studied 436 COPD patients with prospective CT scans from the COSYCONET cohort. All items of the COPD Assessment Test (CAT) and the St George’s Respiratory Questionnaire (SGRQ), the modifed Medical Research Council (mMRC) scale, as well as data from spirometry and CO difusing capacity, were used to construct binary decision trees. The importance of parameters was checked by the Random Forest and AdaBoost machine learning algorithms. Results: When relying on questionnaires only, items CAT 1 & 7 and SGRQ 8 & 12 sub-item 3 were most important for the emphysema- versus airway-dominated phenotype, and among the spirometric measures FEV1/FVC. The combina‑ tion of CAT item 1 (≤2) with mMRC (>1) and FEV1/FVC, could raise the odds for emphysema by factor 7.7. About 50% of patients showed combinations of values that did not markedly alter the likelihood for the phenotypes, and these could be easily identifed in the trees. Inclusion of CO difusing capacity revealed the transfer coefcient as dominant measure. The results of machine learning were consistent with those of the single trees. Conclusions: Selected items (cough, sleep, breathlessness, chest condition, slow walking) from comprehensive COPD questionnaires in combination with FEV1/FVC could raise or lower the likelihood for lung emphysema in patients with COPD. The simple, parsimonious approach proposed by us might help if diagnostic resources regarding respiratory diseases are limited.