A deep learning model has identified and validated the first imaging biomarker for chronic stress using adrenal gland measurements from routine chest CT scans.
Key Details
- 1Researchers at Johns Hopkins developed an AI model to measure adrenal gland volume on chest CT scans.
- 2The study used data from 2,842 participants in the Multi-Ethnic Study of Atherosclerosis, integrating imaging, cortisol, and psychosocial stress measures.
- 3AI-derived Adrenal Volume Index (AVI) correlated with stress questionnaires, cortisol levels, and allostatic load.
- 4Higher AVI was associated with greater stress indicators and increased risk of heart failure and mortality over 10 years of follow-up.
- 5This method leverages routinely performed CT scans without additional testing or radiation.
Why It Matters
This is the first validated AI-driven imaging biomarker for chronic stress, offering radiologists a new quantitative tool for assessing the physiological impact of stress using existing CT data. The approach could improve risk stratification and guide preventive care for stress-related diseases.
Source
EurekAlert
Related News
•EurekAlert
NYU AI Model Improves 5-Year Breast Cancer Risk Prediction via 3D Mammograms
NYU researchers developed an AI model using longitudinal 3D mammograms that outperforms single-scan and 2D-based tools in predicting 5-year breast cancer risk.
•EurekAlert
Explainable AI Predicts High-Risk Heart Attack Patients for Imaging and Treatment
Researchers developed an explainable AI scoring system to predict intramyocardial hemorrhage risk after severe heart attacks, potentially guiding imaging decisions.
•EurekAlert
AI Framework Accelerates Aortic Aneurysm Risk Prediction from Imaging
Researchers developed BioPINN-LM, combining physics-informed neural networks and multimodal large language models to deliver fast, interpretable risk assessments for ascending thoracic aortic aneurysms.