Researchers Unveil First Imaging Biomarker for Chronic Stress

Researchers have identified a groundbreaking imaging-based biomarker for chronic stress, utilizing artificial intelligence to analyze routine chest CT scans. This development, presented at the annual meeting of the Radiological Society of North America (RSNA) in early December, has the potential to flag long-term health risks associated with stress.

The study employed a deep learning model, a type of AI specifically trained to recognize patterns in extensive datasets. This model was tasked with identifying and measuring the size of the adrenal glands, which are crucial for the body’s stress response as they produce cortisol. According to Health Canada, chronic stress is linked to numerous physical and mental health issues, including heart disease, bowel disorders, and weakened immune functions.

Elena Ghotbi, a postdoctoral research fellow at The Johns Hopkins University School of Medicine, explained that the initial hypothesis was driven by a lack of widely accessible and validated markers to measure chronic stress. In her words, “Our hypothesis was that maybe … measuring this adrenal gland in chest CT scans, and then measuring its volume, would be related to markers of chronic stress.”

Unlike a single cortisol test that captures stress at a single moment, the adrenal gland volume may provide a more comprehensive picture of prolonged physiological strain. By employing an AI model capable of automatically segmenting the adrenal glands on CT scans, the researchers created an Adrenal Volume Index (AVI), defined as the total adrenal gland volume in cubic centimeters divided by a person’s height squared in meters.

The findings revealed that individuals reporting high levels of perceived stress exhibited higher AVI compared to those indicating low stress levels. The model was validated using data from nearly 3,000 participants in the Multi-Ethnic Study of Atherosclerosis, which combines chest CT scans with cortisol measurements.

“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,” Ghotbi noted.

Senior author Shadpour Demehri, a professor of radiology at Johns Hopkins, emphasized the significance of this approach. He mentioned that it could enable clinicians to extract valuable information from scans conducted for other medical reasons. “There is no quick measure of chronic stress, (or) objective measure of chronic stress,” Demehri stated. “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 underscored that the findings are preliminary and require validation within diverse populations and age groups. They cautioned that further external validation is essential before clinical application. Nonetheless, Demehri expressed optimism about the algorithm’s potential, stating that it could leverage millions of existing CT scans to uncover biological signals previously deemed impractical to measure.

Recent data indicate that approximately 6.4 million publicly funded CT exams were conducted in Canada during the 2022–2023 fiscal year, according to the Canadian Medical Imaging Inventory. This translates to a national average of 160 exams per 1,000 people. The inventory’s data collection phase began on May 5, 2023, concluding on October 31, 2023.

“Just imagine this algorithm can run on all of (CT machines) and get the data that we want,” Demehri remarked. “Like anything in medicine, there’s nothing guaranteed, but we are very hopeful.” The identification of this biomarker represents a significant step forward in understanding the biological impacts of chronic stress and paves the way for future research in the field.