Related Experiment Video
Updated: Mar 14, 2026
07:53
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
2.2K
Deep Learning-Based Estimated Pulmonary Biological Age From Chest Computed Tomography Images in Healthy Adults: Model
Liping Zuo1, Na Zhu2, Bowen Wang1
1Department of Radiology, Qilu Hospital of Shandong University, 107 Wenhua Xilu, Lixia District, Jinan 250012, Shandong, China, 86 18560081629.
JMIR Aging
|March 12, 2026
Summary
This study developed an estimated pulmonary biological age (ePBA) using chest CT scans. The age gap (ePBA minus chronological age) in patients with chronic obstructive pulmonary disease (COPD) is linked to reduced lung function and increased mortality risk.
Area of Science:
- Radiology and Medical Imaging
- Artificial Intelligence in Medicine
- Pulmonology and Respiratory Medicine
Background:
- Estimated pulmonary biological age (ePBA) from chest CT shows promise for predicting disease progression and mortality.
- Current CT-based ePBA models lack generalizability due to limited training and validation on diverse healthy adult populations.
Purpose of the Study:
- To develop a robust ePBA biomarker using deep learning on multicenter chest CT data from healthy adults.
- To investigate the association of the ePBA-derived age gap with pulmonary function and all-cause mortality in patients with chronic obstructive pulmonary disease (COPD).
Main Methods:
- Utilized a large dataset of 11,187 chest CT scans from healthy adults across three institutions for model development and external validation.
- Employed multiple deep learning models to calculate ePBA.
- Analyzed the correlation between age gap and lung function (FEV1% predicted) and all-cause mortality in 138 COPD patients.
Main Results:
- Deep learning models demonstrated strong correlation between ePBA and chronological age.
- A significant association was found between age gap and reduced forced expiratory volume in 1 second (FEV1% predicted) in COPD patients (rs=-0.18; P=.03).
- The age gap was significantly associated with an increased risk of all-cause mortality in COPD patients (HR: 1.16; 95% CI: 1.08-1.25).
Conclusions:
- A novel, validated ePBA biomarker was developed using deep learning on chest CT scans.
- The age gap, derived from ePBA, shows potential as a novel clinical biomarker for assessing risk in COPD patients.
