biostudies-literatureAngelini EDNCATS NIH HHSCOPD FoundationNHLBINIDDK NIH HHSNIEHS NIH HHSNIH/NHLBINational Heart, Lung, and Blood InstituteNHLBI NIH HHSFoundation for the NIHNIH1067-1079https://www.ebi.ac.uk/biostudies/studies/S-EPMC10592007biostudies-literatureUnknown78(11)<h4>Background</h4>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.<h4>Methods</h4>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 ThoraxPulmonary emphysema subtypes defined by unsupervised machine learning on CT scans.PMC10592007N02-HL-64278Not applicableRC1 HL100543R01 HL121270UL1-TR-000040UL1 TR001881HHSN268200900015CR01 HL130506HHSN268200900019CK24 HL140108R01-HL077612U01 HL089856R01-HL121270P01 HL105339R01 HL131565UL1 TR000040UL1-TR-001420R01-HL130506P01HL105339N02 HL064278HHSN268200900018CU01HL089856HHSN268200900014CR01-HL103676DK063491P30 DK063491T32-144442R01 HL103676UL1-TR-001079P30 ES005605UL1 TR001420K12 HL120004HHSN268200900017CHHSN268200900013C-20CP30 DK054759R01-HL131565R01 HL113264HHSN268200900013CP30 ES007033K12HL120004R01HL113264UL1-TR-001881R01 HL077612HHSN268201500003CUL1 TR001873R01 HL093081UL1 TR001079R01 HL155816HHSN268200900016CN01-HC-95159-69N01 HC095159R01-HL093081U24 HL141762T32 HL144442HHSN268200900020CP30 DK026687R01-HL142028R01 HL142028HHSN268201500003IWatson KEKasela SLaine AFPottinger TDHansel NNRich SSSilverman EKBarr RGOelsner ECHan MKPrince MRGarcia CKPaine RHoffman EALappalainen THughes EShen WMartinez FJSmith BMYang JPost WBalte PPBleecker ERMalinsky DKaufman JDOrtega VEWoodruff PGSun YKim JSAllen NBCho MHSwift AJLima JBowler RAngelini EDCooper CSAustin JHMDransfield MTManichaikul AWCouper DJacobs DRfalsePulmonary emphysema subtypes defined by unsupervised machine learning on CT scans.<h4>Background</h4>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.<h4>Methods</h4>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 2023-01-01T00:00:00Z2023 Nov2026-05-29T10:17:56.949Z2025-06-01T00:33:17.017ZS-EPMC105920073726841410.1136/thorax-2022-219158