Machine Learning and Prediction of All-Cause Mortality in Chronic Obstructive Pulmonary Disease.

May 1, 2020

Contributor: Matthew Moll,Dandi Qiao,Elizabeth A Regan,Gary M Hunninghake,Barry J Make,Ruth Tal-Singer,Michael McGeachie,Peter J Castaldi,Raul San Jose Estepar,George Washko,James M Wells,David LaFon,Matthew Strand,Russell P Bowler,Meilan K Han,Jorgen Vestbo,Bartolome Celli,Peter Calverley,James Crapo,Edwin K Silverman,Brian D Hobbs,Michael H Cho

Machine Learning and Prediction of All-Cause Mortality in Chronic Obstructive Pulmonary Disease.

Chronic obstructive pulmonary disease (COPD) is a leading cause of mortality. We hypothesized that applying machine learning to clinical and quantitative CT imaging features would improve mortality prediction in COPD.
We selected 30 clinical, spirometric, and imaging features as inputs for a random survival forest (RSF). We used top features in a Cox regression to create a machine learning mortality prediction (MLMP-COPD) model, and also assessed the performance of other statistical and machine learning models. We trained the models in moderate-to-severe COPD subjects from a subset of COPDGene, and tested prediction performance in the remainder of individuals with moderate-to-severe COPD in COPDGene and ECLIPSE. We compared our model to BODE; BODE modifications; and the age, dyspnea, obstruction (ADO) index.
We included 2,632 COPDGene and 1,268 ECLIPSE participants. The top predictors of mortality were 6-minute walk distance, FEV (% predicted) and age. The top imaging predictor was pulmonary artery-to-aorta ratio. MLMP-COPD resulted in a C-index of ≥ 0.7 in both COPDGene and ECLIPSE (6.4- and 7.2-year median follow up, respectively), significantly better than all tested mortality indices (p-value < 0.05). MLMP-COPD had fewer predictors, but similar performance to other models. The group with the highest BODE scores (7-10) had 64% mortality, while the highest mortality group defined by MLMP-COPD had 77% mortality (p = 0.012).
A MLMP-COPD model outperformed 4 existing models for predicting all-cause mortality across two COPD cohorts. Performance of machine learning was similar to traditional statistical methods. The model is available online at: https://cdnm.shinyapps.io/cgmortalityapp/.

Copyright © 2020. Published by Elsevier Inc.

Author

admin

View all posts

About The Expert

Matthew Moll

Channing Division for Network Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA; Division of Pulmonary and Critical Care Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA.

Dandi Qiao

Channing Division for Network Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA.

Elizabeth A Regan

Division of Pulmonary and Critical Care Medicine, University of Colorado, Denver, CO 80204, USA.

Gary M Hunninghake

Division of Pulmonary and Critical Care Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA.

Barry J Make

Division of Pulmonary and Critical Care Medicine, National Jewish Health, Denver, CO 80206, USA.

Ruth Tal-Singer

GlaxoSmithKline Research and Development, Collegeville, PA 19426, USA.

Michael McGeachie

Channing Division for Network Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA.

Peter J Castaldi

Channing Division for Network Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA.

Raul San Jose Estepar

Division of Pulmonary and Critical Care Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA; Applied Chest Imaging Laboratory, Brigham and Women’s Hospital, Boston, MA 02115, USA.

George Washko

Division of Pulmonary and Critical Care Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA; Applied Chest Imaging Laboratory, Brigham and Women’s Hospital, Boston, MA 02115, USA.

James M Wells

Division of Pulmonary, Allergy and Critical Care Medicine, University of Alabama at Birmingham, Birmingham, AL 35924, United States.

David LaFon

Division of Pulmonary, Allergy and Critical Care Medicine, University of Alabama at Birmingham, Birmingham, AL 35924, United States.

Matthew Strand

Division of Pulmonary and Critical Care Medicine, National Jewish Health, Denver, CO 80206, USA.

Russell P Bowler

Division of Pulmonary and Critical Care Medicine, University of Colorado, Denver, CO 80204, USA; Division of Pulmonary and Critical Care Medicine, National Jewish Health, Denver, CO 80206, USA.

Meilan K Han

Division of Pulmonary and Critical Care Medicine, University of Michigan Health System, Ann Arbor, MI 48109, USA.

Jorgen Vestbo

Division of Infection, Immunity and Respiratory Medicine, Manchester Academic Health Sciences Centre, The University of Manchester, Oxford Rd, Manchester, M13 9PL, UK; Manchester University NHS Foundation Trust, Manchester, UK.

Bartolome Celli

Division of Pulmonary and Critical Care Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA.

Peter Calverley

Department of Medicine, University of Liverpool, Liverpool, United Kingdom.

James Crapo

Division of Pulmonary and Critical Care Medicine, National Jewish Health, Denver, CO 80206, USA.

Edwin K Silverman

Channing Division for Network Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA; Division of Pulmonary and Critical Care Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA.

Brian D Hobbs

Channing Division for Network Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA; Division of Pulmonary and Critical Care Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA. Electronic address: rebdh@channing.harvard.edu.

Michael H Cho

Channing Division for Network Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA; Division of Pulmonary and Critical Care Medicine, Brigham and Women’s Hospital, Boston, MA 02115, USA. Electronic address: remhc@channing.harvard.edu.

References

PubMed