Prediction of lung emphysema in COPD by spirometry and clinical symptoms: results from COSYCONET.
Aged
Cohort Studies
Comorbidity
Decision Trees
Female
Humans
Male
Middle Aged
Predictive Value of Tests
Prospective Studies
Pulmonary Disease, Chronic Obstructive
/ diagnostic imaging
Pulmonary Emphysema
/ diagnostic imaging
Severity of Illness Index
Spirometry
/ methods
Tomography, X-Ray Computed
/ methods
Adaboost
COPD phenotypes
CT scan
Decision trees
Emphysema
Random forest
Journal
Respiratory research
ISSN: 1465-993X
Titre abrégé: Respir Res
Pays: England
ID NLM: 101090633
Informations de publication
Date de publication:
09 Sep 2021
09 Sep 2021
Historique:
received:
02
02
2021
accepted:
01
09
2021
entrez:
10
9
2021
pubmed:
11
9
2021
medline:
29
1
2022
Statut:
epublish
Résumé
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 physicians with limited technical resources can improve the diagnosis of emphysema. 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 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. 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 FEV Selected items (cough, sleep, breathlessness, chest condition, slow walking) from comprehensive COPD questionnaires in combination with FEV
Sections du résumé
BACKGROUND
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 physicians with limited technical resources can improve the diagnosis of emphysema.
METHODS
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 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.
RESULTS
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 FEV
CONCLUSIONS
CONCLUSIONS
Selected items (cough, sleep, breathlessness, chest condition, slow walking) from comprehensive COPD questionnaires in combination with FEV
Identifiants
pubmed: 34503520
doi: 10.1186/s12931-021-01837-2
pii: 10.1186/s12931-021-01837-2
pmc: PMC8427948
doi:
Banques de données
ClinicalTrials.gov
['NCT01245933']
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
242Subventions
Organisme : Deutsche Zentrum für Lungenforschung
ID : 82DZLI05A2
Organisme : Bundesministerium für Bildung und Forschung
ID : 01GI0881
Informations de copyright
© 2021. The Author(s).
Références
Respir Med. 2016 May;114:27-37
pubmed: 27109808
Eur Radiol. 2012 Oct;22(10):2085-93
pubmed: 22699870
COPD. 2012 Apr;9(2):151-9
pubmed: 22429093
Eur Respir J. 2016 Jul;48(1):92-103
pubmed: 27230444
Respir Med. 2006 Oct;100(10):1742-52
pubmed: 16549342
Eur Respir J. 2017 Sep 11;50(3):
pubmed: 28893868
Radiology. 2015 Oct;277(1):192-205
pubmed: 25961632
Lung Cancer. 2012 Jul;77(1):58-63
pubmed: 22437042
BMC Pulm Med. 2014 Oct 24;14:164
pubmed: 25341556
Chest. 2015 Jul;148(1):176-184
pubmed: 25539080
Am J Respir Crit Care Med. 2021 May 25;:
pubmed: 34033525
Respiration. 2017;94(4):380-388
pubmed: 28817821
Respir Med. 2019 Nov;159:105810
pubmed: 31739262
Respir Med. 2020 Oct;172:106117
pubmed: 32891937
Respir Med. 2011 Dec;105(12):1872-84
pubmed: 21852081
Chron Respir Dis. 2019 Jan-Dec;16:1479972318775423
pubmed: 29742906
Eur Respir J. 2004 May;23(5):769-75
pubmed: 15176695
Eur Respir J. 2017 Aug 24;50(2):
pubmed: 28838984
Respir Med. 1991 Sep;85 Suppl B:25-31; discussion 33-7
pubmed: 1759018
NPJ Prim Care Respir Med. 2020 Jul 30;30(1):32
pubmed: 32732930
Am J Respir Crit Care Med. 2008 Oct 1;178(7):738-44
pubmed: 18565949
Am J Respir Crit Care Med. 2013 Mar 15;187(6):602-8
pubmed: 23328525
Am J Respir Crit Care Med. 2017 Mar 1;195(5):557-582
pubmed: 28128970
Eur Respir J. 2012 Dec;40(6):1324-43
pubmed: 22743675