Universität zu Köln

McInnis, Micheal C., Ma, Jin, Karur, Gauri Rani, Houbois, Christian, Levy, Liran, Havlin, Jan, Fuchs, Eyal, Tikkanen, Jussi, Chow, Chung-Wai ORCID: 0000-0001-9344-8522, Huszti, Ella and Martinu, Tereza (2022). Chronic lung allograft dysfunction phenotype and prognosis by machine learning CT analysis. Eur. Resp. J., 60 (1). SHEFFIELD: EUROPEAN RESPIRATORY SOC JOURNALS LTD. ISSN 1399-3003

Full text not available from this repository.

Abstract

Background Chronic lung allograft dysfunction (CLAD) is the principal cause of graft failure in lung transplant recipients and prognosis depends on CLAD phenotype. We used a machine learning computed tomography (CT) lung texture analysis tool at CLAD diagnosis for phenotyping and prognostication compared with radiologist scoring. Methods This retrospective study included all adult first double lung transplant patients (January 2010-December 2015) with CLAD (censored December 2019) and inspiratory CT near CLAD diagnosis. The machine learning tool quantified ground-glass opacity, reticulation, hyperlucent lung and pulmonary vessel volume (PVV). Two radiologists scored for ground-glass opacity, reticulation, consolidation, pleural effusion, air trapping and bronchiectasis. Receiver operating characteristic curve analysis was used to evaluate the diagnostic performance of machine learning and radiologist for CLAD phenotype. Multivariable Cox proportional hazards regression analysis for allograft survival controlled for age, sex, native lung disease, cytomegalovirus serostatus and CLAD phenotype. Results 88 patients were included (57 bronchiolitis obliterans syndrome (BOS), 20 restrictive allograft syndrome (RAS)/mixed and 11 unclassified/undefined) with CT a median 9.5 days from CLAD onset. Radiologist and machine learning parameters phenotyped RAS/mixed with PVV as the strongest indicator (area under the curve (AUC) 0.85). Machine learning hyperlucent lung phenotyped BOS using only inspiratory CT (AUC 0.76). Radiologist and machine learning parameters predicted graft failure in the multivariable analysis, best with PVV (hazard ratio 1.23, 95% CT 1.05-1.44; p=0.01). Conclusions Machine learning discriminated between CLAD phenotypes on CT. Both radiologist and machine learning scoring were associated with graft failure, independent of CLAD phenotype. PVV, unique to machine learning, was the strongest in phenotyping and prognostication.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code McInnis, Micheal C. UNSPECIFIED UNSPECIFIED UNSPECIFIED Ma, Jin UNSPECIFIED UNSPECIFIED UNSPECIFIED Karur, Gauri Rani UNSPECIFIED UNSPECIFIED UNSPECIFIED Houbois, Christian UNSPECIFIED UNSPECIFIED UNSPECIFIED Levy, Liran UNSPECIFIED UNSPECIFIED UNSPECIFIED Havlin, Jan UNSPECIFIED UNSPECIFIED UNSPECIFIED Fuchs, Eyal UNSPECIFIED UNSPECIFIED UNSPECIFIED Tikkanen, Jussi UNSPECIFIED UNSPECIFIED UNSPECIFIED Chow, Chung-Wai UNSPECIFIED orcid.org/0000-0001-9344-8522 UNSPECIFIED Huszti, Ella UNSPECIFIED UNSPECIFIED UNSPECIFIED Martinu, Tereza UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-674378
DOI:	10.1183/13993003.01652-2021
Journal or Publication Title:	Eur. Resp. J.
Volume:	60
Number:	1
Date:	2022
Publisher:	EUROPEAN RESPIRATORY SOC JOURNALS LTD
Place of Publication:	SHEFFIELD
ISSN:	1399-3003
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language BRONCHIOLITIS OBLITERANS SYNDROME; QUANTITATIVE COMPUTED-TOMOGRAPHY; TRANSPLANTATION; VALIDATION; SURVIVAL; PATTERNS; SOCIETY; ONSET; HEART Multiple languages Respiratory System Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/67437