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 breakthrough, presented at the annual meeting of the Radiological Society of North America (RSNA) in early December, could help flag long-term health risks associated with chronic stress.

The study employed a deep learning model—a form of AI designed to recognize patterns in extensive datasets—to automatically analyze medical images. Specifically, the model focused on the adrenal glands, small organs that play a crucial role in the body’s stress response by producing the hormone cortisol.

According to Health Canada, chronic stress is linked to various health issues, including heart disease, digestive disorders, mental health conditions, and a weakened immune system. Despite its prevalence, there has been no widely available method to objectively measure the biological effects of stress over time.

Lead author Elena Ghotbi, a postdoctoral research fellow at The Johns Hopkins University School of Medicine, explained, “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 size in chest CT scans might correlate with markers of chronic stress.

Unlike a single cortisol test, which reflects stress at a specific moment, measuring adrenal gland volume could indicate prolonged physiological strain. The researchers calculated an Adrenal Volume Index (AVI), defined as the total volume of the adrenal glands in cubic centimetres divided by a person’s height squared in metres. The findings showed that individuals reporting high levels of perceived stress had higher AVIs compared to those experiencing low stress.

The model was validated using imaging and health data from nearly 3,000 participants in the Multi-Ethnic Study of Atherosclerosis. This long-running cohort combines chest CT scans with cortisol measurements, providing a robust data set for analysis. “We were able to show that those adrenal volumes were associated with cortisol hormone levels, stress levels expressed in standardized questionnaires, and also long-term cardiovascular outcomes,” Ghotbi stated.

Senior author Shadpour Demehri, a professor of radiology at Johns Hopkins, emphasized the potential of this approach. “There is no quick measure of chronic stress or objective measure of chronic stress,” Demehri noted. “People express their stress in various ways, and we are focused on its biological impact rather than the psychological component.”

While the findings are promising, both Ghotbi and Demehri cautioned that further validation is necessary across different populations, imaging technologies, and age groups. They highlighted that external validation is crucial before this method can be implemented clinically. Nevertheless, Demehri remarked on the significance of applying the algorithm to millions of existing CT scans.

The latest data indicates that in Canada, approximately 6.4 million publicly funded CT exams were conducted in the 2022–2023 fiscal year, averaging 160 exams per 1,000 people. This extensive data pool could facilitate the application of this new algorithm.

“Just imagine this algorithm running on all of the CT machines and extracting the data we need,” Demehri said, expressing optimism about the future of this research. “While there are no guarantees in medicine, we are very hopeful.”

As the research progresses, it could pave the way for a more objective and accessible approach to measuring chronic stress, ultimately aiding in the prevention and management of stress-related health conditions.