Chest x-ray-based biologic aging and aging velocity estimated by deep learning are linked to all-cause and disease-specific mortality.
Key Details
- 1Study analyzed 421,894 healthy Korean adults who underwent chest x-rays between 2006–2020.
- 2Deep-learning model 'AgeNet' estimated radiographic age and aging velocity from x-ray images.
- 3Baseline accelerated aging (radiographic age > chronological by 5+ years) raised mortality risk (HR 1.26 for men, 1.52 for women).
- 4Aging velocity was tracked among 179,667 with ≥3 scans; accelerated aging velocity (≥1.5 years/year) increased mortality risk (rate ratios: 1.51 for men, 1.71 for women).
- 5Decelerated aging velocity (<0.5 years/year) reduced mortality risk, especially in women (rate ratio: 0.50).
- 6Associations held for all-cause, cardiovascular, cancer, and respiratory deaths over median 8.5-year follow-up.
Why It Matters
These findings validate chest x-ray-based AI as a practical tool for estimating biological aging and predicting mortality, supporting its potential for guiding interventions aimed at improving population health and longevity. This highlights the expanding role of imaging beyond diagnosis to ongoing health monitoring.
Source
AuntMinnie
Related News
•Radiology Business
Radiologists Prefer Domain-Specific AI for CT Report Generation
Radiologists show a clear preference for domain-specific AI models in generating accurate and timely CT report impressions.
•AuntMinnie
German Researchers Release Large ICU Chest X-ray Dataset for AI
A German team has released TAIX-Ray, a massive bedside chest x-ray dataset supporting AI development for pathology detection in ICU settings.
•HealthExec
UT Austin to Launch $1B+ AI-Driven Medical Center With Major Gift
UT Austin receives $750 million from Michael and Susan Dell toward a $1 billion+ AI-native medical center opening in 2030.