Researchers Uncover First Imaging Biomarker for Chronic Stress

Researchers have identified the first imaging-based biomarker of chronic stress, utilizing artificial intelligence to analyze routine chest CT scans. This groundbreaking study, presented at the annual meeting of the Radiological Society of North America (RSNA) in early December, aims to enhance our understanding of long-term health risks associated with stress.

By employing a deep learning model trained to recognize patterns in extensive datasets, the team focused on measuring the size of the adrenal glands. These small organs are crucial in the body’s stress response, primarily through the production of cortisol. According to Health Canada, chronic stress is linked to various health issues, including heart disease, bowel diseases, mental illness, and a weakened immune system. Currently, there is no widely available and objective method to assess the biological impact of stress over time.

Lead author Elena Ghotbi, a postdoctoral research fellow at The Johns Hopkins University School of Medicine, noted, “Our initial hypothesis was based on the fact that there is no widely accessible and widely approved marker which measures chronic stress in medicine and medical imaging.” The researchers proposed that measuring adrenal gland volume in chest CT scans could correlate with chronic stress markers.

Unlike a single cortisol test, which reflects stress levels at a specific moment, the volume of the adrenal glands may provide insight into prolonged physiological strain. The researchers developed an Adrenal Volume Index (AVI), which quantifies total adrenal gland volume in cubic centimeters divided by a person’s height squared in meters. The study revealed that individuals reporting high levels of perceived stress exhibited a higher AVI compared to those with lower stress levels.

The AI model was tested on imaging and health data from nearly 3,000 participants in the Multi-Ethnic Study of Atherosclerosis, a long-term cohort study that integrates chest CT scans and cortisol measurements. Ghotbi explained, “We were able to show that those adrenal volumes … were associated with cortisol hormone levels, stress levels that patients expressed in standardized questionnaires, and also long-term cardiovascular outcomes.”

Senior author Shadpour Demehri, a professor of radiology at Johns Hopkins, highlighted the potential of this approach to extract valuable information from scans conducted for other medical reasons. He stated, “There is no quick measure of chronic stress, or objective measure of chronic stress. People are reflecting (on) and expressing their stress in different ways. We are not as much interested in the psychological component of it, but its biological impact.”

Both researchers emphasized the preliminary nature of their findings, urging the need for further validation across diverse populations, scanners, and age groups. Demehri noted that external validation will be essential before this measure can be implemented clinically. Nevertheless, he expressed optimism about the algorithm’s ability to analyze millions of existing CT scans, potentially revealing previously undetectable biological signals.

Recent data indicates that approximately 6.4 million publicly funded CT exams were performed in Canada during the 2022–2023 fiscal year, averaging 160 exams per 1,000 people. Demehri remarked, “Just imagine this algorithm can run onto all of (CT machines) and get the data that we want. Like anything in medicine, there’s nothing guaranteed, but we are very hopeful.”

This innovative research represents a significant step forward in understanding chronic stress and its effects on health, paving the way for future studies and potential clinical applications.