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

Respiratory Research

Henrik Watz¹  Helgo Magnussen¹  Johanna Lutter²  Hans-Ulrich Kauczor³  Bertram Jobst³  Jürgen Biederer⁴  Robert Bals⁵  Kathrin Kahnert⁶  Diego Kauffmann-Guerrero⁶  Jürgen Behr⁶  Claus F. Vogelmeier⁷  Peter Alter⁷  Tobias Welte⁸  Rudolf A. Jörres⁹  Alexander Hapfelmeier^1,10  Antonius Schneider^1,10  Christina Kellerer^1,11  Franziska C. Trudzinski^1,12 

[1] Airway Research Center North (ARCN), German Center for Lung Research (DZL), Pulmonary Research Institute at LungenClinic Grosshansdorf, Woehrendamm 80, 22927, Grosshansdorf, Germany;Comprehensive Pneumology Center Munich (CPC-M), German Center for Lung Research (DZL), Institute of Epidemiology, Helmholtz Zentrum München (GmbH) – German Research Center for Environmental Health, 85764, Neuherberg, Germany;Department of Diagnostic and Interventional Radiology, University Hospital of Heidelberg, Heidelberg, Germany;Translational Lung Research Centre Heidelberg (TLRC), Member of the German Center for Lung Research, Heidelberg, Germany;Department of Diagnostic and Interventional Radiology, University Hospital of Heidelberg, Heidelberg, Germany;Translational Lung Research Centre Heidelberg (TLRC), Member of the German Center for Lung Research, Heidelberg, Germany;Faculty of Medicine, University of Latvia, Raina bulvaris 19, 1586, Riga, Latvia;Faculty of Medicine, Christian-Albrechts-Universität Zu Kiel, 24098, Kiel, Germany;Department of Internal Medicine V – Pulmonology, Allergology, Respiratory Intensive Care Medicine, Saarland University Hospital, Kirrberger Straße 1, 66424, Homburg, Germany;Department of Internal Medicine V, University of Munich (LMU), Comprehensive Pneumology Center, German Center for Lung Research, Ziemssenstr. 1, 80336, Munich, Germany;Department of Medicine, Pulmonary and Critical Care Medicine, University Medical Center Giessen and Marburg, Philipps-University Marburg, German Center for Lung Research (DZL), Baldingerstrasse, 35043, Marburg, Germany;Department of Pneumology, Hannover Medical School, Carl-Neuberg-Str. 1, 30625, Hannover, Germany;Institute and Outpatient Clinic for Occupational, Social and Environmental Medicine, Comprehensive Pneumology Center Munich (CPC-M), Ludwig-Maximilians-Universität München, Ziemssenstr. 1, 80336, Munich, Germany;School of Medicine, Institute of General Practice and Health Services Research, Technische Universität München/Klinikum Rechts der Isar, Orleansstr. 47, 81667, Munich, Germany;School of Medicine, Institute of General Practice and Health Services Research, Technische Universität München/Klinikum Rechts der Isar, Orleansstr. 47, 81667, Munich, Germany;Institute and Outpatient Clinic for Occupational, Social and Environmental Medicine, Comprehensive Pneumology Center Munich (CPC-M), Ludwig-Maximilians-Universität München, Ziemssenstr. 1, 80336, Munich, Germany;Translational Lung Research Centre Heidelberg (TLRC), Member of the German Center for Lung Research, Thoraxklinik-Heidelberg gGmbH, Röntgenstraße 1, 69126, Heidelberg, Germany;

关键词: Emphysema;    CT scan;    Decision trees;    Random forest;    Adaboost;    COPD phenotypes;   

DOI  :  10.1186/s12931-021-01837-2

来源: Springer

【 摘 要 】

BackgroundLung 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 physicians with limited technical resources can improve the diagnosis of emphysema.MethodsWe 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 modified Medical Research Council (mMRC) scale, as well as data from spirometry and CO diffusing capacity, were used to construct binary decision trees. The importance of parameters was checked by the Random Forest and AdaBoost machine learning algorithms.ResultsWhen 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 combination 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 identified in the trees. Inclusion of CO diffusing capacity revealed the transfer coefficient as dominant measure. The results of machine learning were consistent with those of the single trees.ConclusionsSelected 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.Trial registration ClinicalTrials.gov, Identifier: NCT01245933, registered 18 November 2010, https://clinicaltrials.gov/ct2/show/record/NCT01245933.

【 授权许可】

CC BY