AI Tool Detects Biomarker of Chronic Stress Using Routine CT Scans

A research team led by Johns Hopkins University has developed a new artificial intelligence (AI) tool that can detect chronic stress through standard chest CT scans, offering the first imaging-based biomarker of long-term stress. The innovation will be presented at the upcoming Radiological Society of North America (RSNA) annual meeting.

Chronic stress, known to contribute to conditions such as heart disease, depression, and obesity, has traditionally been difficult to quantify with medical imaging. The new AI model addresses this gap by measuring the size of the adrenal glands—organs that respond to stress hormones—on already available chest CT images.

“Our approach leverages widely available imaging data and opens the door to large-scale evaluations of the biological impact of chronic stress across a range of conditions,” said lead researcher Dr. Elena Ghotbi, a postdoctoral fellow at Johns Hopkins. “This AI-driven biomarker has the potential to enhance cardiovascular risk stratification and guide preventive care without additional testing or radiation.”

The deep learning model calculates the Adrenal Volume Index (AVI), which adjusts gland size for body height, using CT images from over 2,800 participants in the Multi-Ethnic Study of Atherosclerosis. This cohort also included detailed psychological assessments, salivary cortisol levels, and markers of physiological stress—creating a rare opportunity to validate the imaging biomarker against multiple independent indicators.

Senior author Dr. Shadpour Demehri noted the breakthrough allows clinicians to assess the biological toll of stress in a tangible way. “For the first time, we can ‘see’ the long-term burden of stress inside the body, using a scan that patients already get every day in hospitals across the country.”

The findings revealed strong correlations between increased adrenal volume and higher levels of perceived stress, elevated cortisol, and greater allostatic load—a composite index of physiological wear and tear from chronic stress. Notably, a higher AVI was linked to increased left ventricular mass and a greater risk of developing heart failure or dying within a 10-year follow-up period.

“This is the very first imaging marker of chronic stress that has been validated and shown to have an independent impact on a cardiovascular outcome, namely, heart failure,” said Dr. Ghotbi.

Dr. Teresa Seeman of UCLA, a co-author and long-time researcher on stress and health, emphasized the significance of these findings. “This work links a routinely obtained imaging feature with validated biological and psychological measures of stress and shows that it independently predicts a major clinical outcome. It’s a true step forward in operationalizing the cumulative impact of stress on health.”

The researchers say this imaging biomarker could eventually be used to assess stress-related risks in a wide range of patients, especially middle-aged and older adults with chronic disease. By integrating AI with routine imaging, the tool represents a promising advance in preventive medicine and stress-related diagnostics.