.png){kind=icon}
.png){kind=icon}
Return
Sex-specific machine learning improves prediction of incident and prevalent COPD
.png){kind=icon}
OA
AI
DOI：10.1016/j.chest.2026.07.5207.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Computed tomography imaging with machine learning can predict incident and prevalent chronic obstructive pulmonary disease (COPD), however, it is unknown if sex-specific models improve performance.
Keywords:
COPD
CT Imaging
Machine Learning
Sex Differences
AUC
Area under the ROC
Canadian Cohort Obstructive Lung Disease
(CanCOLD)
Chronic obstructive pulmonary disease
(COPD)
Computed tomography
(CT)
FEV
Forced expiratory volume in one second
FVC
Forced vital capacity
HU
Hounsfield Unit
HU15
15th percentile of the density histogram
LAA856
Low attenuation areas below -856 HU
LAA950
Low attenuation areas below -950 HU
PRAUC
Area under the precision-recall curve
PRMfSAD
Response mapping functional small airway disease
ROC
Receiver operating characteristic curve
RV/ TLC
Residual volume / total lung capacity
SHAP
Shapely additive explanations
Subpopulations and Intermediate Outcome Measures in COPD Study
(SPIROMICS)
TAC
Total airway count
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.6
Papers:
4.9W
Citations:
5.1W
View more organizations