Pulmonary emphysema subtypes defined by unsupervised machine learning on CT scans

Elsa D Angelini; Jie Yang; Pallavi P Balte; Eric A Hoffman; Ani W Manichaikul; Yifei Sun; Wei Shen; John H M Austin; Norrina B Allen; Eugene R Bleecker; Russell Bowler; Michael H Cho; Christopher S Cooper; David Couper; Mark T Dransfield; Christine Kim Garcia; MeiLan K Han; Nadia N Hansel; Emlyn Hughes; David R Jacobs; Silva Kasela; Joel Daniel Kaufman; John Shinn Kim; Tuuli Lappalainen; Joao Lima; Daniel Malinsky; Fernando J Martinez; Elizabeth C Oelsner; Victor E Ortega; Robert Paine; Wendy Post; Tess D Pottinger; Martin R Prince; Stephen S Rich; Edwin K Silverman; Benjamin M Smith; Andrew J Swift; Karol E Watson; Prescott G Woodruff; Andrew F Laine; R Graham Barr

doi:10.1136/thorax-2022-219158

Pulmonary emphysema subtypes defined by unsupervised machine learning on CT scans

Thorax. 2023 Nov;78(11):1067-1079. doi: 10.1136/thorax-2022-219158. Epub 2023 Jun 2.

Authors

Elsa D Angelini^#^{1

2

3}, Jie Yang^#¹, Pallavi P Balte⁴, Eric A Hoffman⁵, Ani W Manichaikul⁶, Yifei Sun⁷, Wei Shen^{8

9}, John H M Austin¹⁰, Norrina B Allen¹¹, Eugene R Bleecker¹², Russell Bowler¹³, Michael H Cho^{14

15}, Christopher S Cooper¹⁶, David Couper¹⁷, Mark T Dransfield¹⁸, Christine Kim Garcia⁴, MeiLan K Han¹⁹, Nadia N Hansel²⁰, Emlyn Hughes²¹, David R Jacobs²², Silva Kasela^{23

24}, Joel Daniel Kaufman²⁵, John Shinn Kim^{4

26}, Tuuli Lappalainen²³, Joao Lima²⁰, Daniel Malinsky⁷, Fernando J Martinez²⁷, Elizabeth C Oelsner⁴, Victor E Ortega²⁸, Robert Paine²⁹, Wendy Post²⁰, Tess D Pottinger⁴, Martin R Prince³⁰, Stephen S Rich⁶, Edwin K Silverman¹⁴, Benjamin M Smith^{4

31}, Andrew J Swift^{4

32}, Karol E Watson¹⁶, Prescott G Woodruff³³, Andrew F Laine^#^{1

9

10}, R Graham Barr^#^{34

35}

Affiliations

¹ Department of Biomedical Engineering, Columbia University, New York, New York, USA.
² LTCI, Institut Polytechnique de Paris, Telecom Paris, Palaiseau, France.
³ NIHR Imperial Biomedical Research Centre, ITMAT Data Science Group, Imperial College, London, UK.
⁴ Department of Medicine, Columbia University Irving Medical Center, New York, New York, USA.
⁵ Departments of Radiology, Medicine and Biomedical Engineering, University of Iowa, Iowa City, Iowa, USA.
⁶ Center for Public Health Genomics, University of Virginia, Charlottesville, Virginia, USA.
⁷ Department of Biostatistics, Columbia University Irving Medical Center, New York, New York, USA.
⁸ Department of Pediatrics, Institute of Human Nutrition, Columbia University Irving Medical Center, New York, New York, USA.
⁹ Columbia Magnetic Resonance Research Center (CMRRC), Columbia University Irving Medical Center, New York, New York, USA.
¹⁰ Department of Radiology, Columbia University Irving Medical Center, New York, New York, USA.
¹¹ Institute for Public Health and Medicine (IPHAM) - Center for Epidemiology and Population Health, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA.
¹² Department of Medicine, University of Arizona Health Sciences, Tucson, Arizona, USA.
¹³ Department of Medicine, National Jewish Health, Denver, Colorado, USA.
¹⁴ Channing Division of Network Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA.
¹⁵ Harvard Medical School, Boston, Massachusetts, USA.
¹⁶ Department of Medicine, University of California, Los Angeles, California, USA.
¹⁷ Department of Biostatistics, University of North Carolina, Chapel Hill, North Carolina, USA.
¹⁸ Lung Health Center, University of Alabama, Birmingham, Alabama, USA.
¹⁹ Department of Medicine, University of Michigan, Ann Arbor, Michigan, USA.
²⁰ Department of Medicine, Johns Hopkins University, Baltimore, Maryland, USA.
²¹ Department of Physics, Columbia University, New York, New York, USA.
²² Division of Epidemiology and Community Public Health, School of Public Health, University of Minnesota, Minneapolis, Minnesota, USA.
²³ Department of Systems Biology, Columbia University Irving Medical Center, New York, New York, USA.
²⁴ New York Genome Center, New York, New York, USA.
²⁵ Departments of Environmental & Occupational Health Sciences, Medicine, and Epidemiology, University of Washington, Seattle, Washington, USA.
²⁶ Department of Medicine, University of Virginia School of Medicine, Charlottesville, Virginia, USA.
²⁷ Department of Medicine, Cornell University Joan and Sanford I Weill Medical College, New York, New York, USA.
²⁸ Department of Pulmonary Medicine, Mayo Clinic, Phoenix, Arizona, USA.
²⁹ Department of Medicine, University of Utah, Salt Lake City, Utah, USA.
³⁰ Department of Radiology, Cornell University Joan and Sanford I Weill Medical College, New York, New York, USA.
³¹ Department of Medicine, Research Institute of the McGill University Health Centre, Montreal, Quebec, Canada.
³² Department of Infection, Immunity and Cardiovascular Disease, The University of Sheffield, Sheffield, UK.
³³ Department of Medicine, University of California, San Francisco, California, USA.
³⁴ Department of Medicine, Columbia University Irving Medical Center, New York, New York, USA rgb9@columbia.edu.
³⁵ Department of Epidemiology, Columbia University Irving Medical Center, New York, New York, USA.

^# Contributed equally.

Abstract

Background: Treatment and preventative advances for chronic obstructive pulmonary disease (COPD) have been slow due, in part, to limited subphenotypes. We tested if unsupervised machine learning on CT images would discover CT emphysema subtypes with distinct characteristics, prognoses and genetic associations.

Methods: New CT emphysema subtypes were identified by unsupervised machine learning on only the texture and location of emphysematous regions on CT scans from 2853 participants in the Subpopulations and Intermediate Outcome Measures in COPD Study (SPIROMICS), a COPD case-control study, followed by data reduction. Subtypes were compared with symptoms and physiology among 2949 participants in the population-based Multi-Ethnic Study of Atherosclerosis (MESA) Lung Study and with prognosis among 6658 MESA participants. Associations with genome-wide single-nucleotide-polymorphisms were examined.

Results: The algorithm discovered six reproducible (interlearner intraclass correlation coefficient, 0.91-1.00) CT emphysema subtypes. The most common subtype in SPIROMICS, the combined bronchitis-apical subtype, was associated with chronic bronchitis, accelerated lung function decline, hospitalisations, deaths, incident airflow limitation and a gene variant near DRD1, which is implicated in mucin hypersecretion (p=1.1 ×10^-8). The second, the diffuse subtype was associated with lower weight, respiratory hospitalisations and deaths, and incident airflow limitation. The third was associated with age only. The fourth and fifth visually resembled combined pulmonary fibrosis emphysema and had distinct symptoms, physiology, prognosis and genetic associations. The sixth visually resembled vanishing lung syndrome.

Conclusion: Large-scale unsupervised machine learning on CT scans defined six reproducible, familiar CT emphysema subtypes that suggest paths to specific diagnosis and personalised therapies in COPD and pre-COPD.

Keywords: COPD epidemiology; Emphysema; Imaging/CT MRI etc.

Publication types

Research Support, Non-U.S. Gov't
Research Support, N.I.H., Extramural

MeSH terms

Case-Control Studies
Emphysema*
Humans
Lung
Pulmonary Disease, Chronic Obstructive*
Pulmonary Emphysema* / diagnostic imaging
Pulmonary Emphysema* / genetics
Tomography, X-Ray Computed
Unsupervised Machine Learning

Abstract

Publication types

MeSH terms

Grants and funding