Related Experiment Video
Updated: Jun 19, 2025
Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography
Published on: November 8, 2024
External Testing of a Deep Learning Model to Estimate Biologic Age Using Chest Radiographs
Jong Hyuk Lee1, Dongheon Lee1, Michael T Lu1
1From the Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul 03080, Korea (J.H.L., J.M.G., H.K.); Department of Biomedical Engineering, Chungnam National University College of Medicine, Chungnam National University Hospital, Daejeon, Korea (D.L.); Massachusetts General Hospital Cardiovascular Imaging Research Center and Harvard Medical School, Boston, Mass (M.T.L., V.K.R.); Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Korea (J.M.G.); Cancer Research Institute, Seoul National University, Seoul, Korea (J.M.G.); Medical Research Collaborating Center, Seoul National University Hospital, Seoul, Korea (Y.C.); and Department of Internal Medicine, Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, Korea (S.H.C.).
Deep learning-based chest radiographic age (CXR-Age) predicts mortality risk in Asian adults. This model showed added prognostic value beyond clinical factors for various survival outcomes.
Area of Science:
- Radiology and Medical Imaging
- Artificial Intelligence in Medicine
- Prognostic Biomarkers
Background:
- Chest radiography is a common imaging modality.
- Deep learning models can extract complex patterns from medical images.
- Assessing prognostic value of AI-derived imaging biomarkers is crucial for clinical application.
Purpose of the Study:
- To evaluate the prognostic capability of a deep learning-based chest radiographic age (CXR-Age) model.
- To assess the model's performance in a large, external cohort of Asian individuals.
- To determine if CXR-Age adds prognostic value to established clinical factors.
Main Methods:
- Retrospective analysis of chest radiographs from 36,924 asymptomatic Asian individuals (aged 50-80).
- External validation of a pre-developed CXR-Age model predicting mortality risk.
- Multivariable Cox or Fine-Gray models assessed hazard ratios for all-cause, cardiovascular, lung cancer, and respiratory disease mortality.
- Likelihood ratio tests evaluated the added prognostic value of CXR-Age.
Main Results:
- CXR-Age was significantly associated with increased risk for all-cause, cardiovascular, lung cancer, and respiratory disease mortality.
- Adjusted hazard ratios indicated increased mortality risk with higher CXR-Age.
- The CXR-Age model demonstrated significant added prognostic value to clinical factors, including chronological age, for all assessed outcomes (P < .001).
Conclusions:
- Deep learning-based CXR-Age is a significant prognostic indicator for various mortality outcomes in asymptomatic Asian individuals.
- CXR-Age provides added prognostic information beyond traditional clinical factors.
- The findings suggest the generalizability of the CXR-Age model for risk stratification.
More Related Videos
07:12Semiautomated Longitudinal Microcomputed Tomography-based Quantitative Structural Analysis of a Nude Rat Osteoporosis-related Vertebral Fracture Model
Published on: September 28, 2017
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020