AI Identifies Chronic Stress Biomarker on Routine CT Scans
For decades, clinicians and researchers have understood the profound impact of chronic stress on health, linking it to conditions ranging from heart disease to depression. Now, a new approach, leveraging the power of artificial intelligence, is offering a way to not just acknowledge that impact, but to visualize it – and potentially quantify it – using existing medical scans. Researchers have developed an AI tool capable of detecting a biomarker for chronic stress directly on routine chest CT scans, a finding that could transform how we understand and address the long-term effects of stress on the body.
Seeing the Invisible: How AI Detects Chronic Stress
The breakthrough, presented next week at the annual meeting of the Radiological Society of North America (RSNA), centers on measuring the volume of the adrenal glands. Traditionally, assessing stress levels has relied on subjective questionnaires or fleeting measurements like cortisol levels in blood or saliva. Cortisol, often called the “stress hormone,” provides a snapshot in time, but doesn’t capture the cumulative toll of ongoing stress. The adrenal glands, responsible for producing cortisol, offer a different perspective. As explained by Dr. Elena Ghotbi, a postdoctoral research fellow at Johns Hopkins University School of Medicine and lead author of the study, “Each year, tens of millions of chest CT scans are performed in the United States alone. 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 using existing chest CT scans.”
The team trained a deep learning model to automatically outline and measure adrenal gland volume on these existing scans. They then defined the Adrenal Volume Index (AVI) – adrenal volume divided by height squared – as a standardized metric. This isn’t about discovering a new physiological process, but about finding a way to reliably *measure* a process already known to be affected by chronic stress. As Dr. Shadpour Demehri, professor of radiology at Johns Hopkins, noted, “For the first time, we can ‘see’ the long-term burden of stress inside the body, using a scan that patients already secure every day in hospitals across the country.”
Beyond Questionnaires: Linking Imaging to Biological and Psychological Stress
The power of this research lies in the breadth of data used to validate the AI-derived biomarker. The study analyzed information from 2,842 participants enrolled in the Multi-Ethnic Study of Atherosclerosis, a large, ongoing study that combines chest CT imaging with validated stress questionnaires, cortisol measurements, and indicators of allostatic load. Allostatic load, a key concept in stress research, refers to the cumulative physiological and psychological effects of chronic stress on the body. This integration of imaging, biochemical data, and psychosocial assessments is what allowed the researchers to create a robust imaging-based marker of chronic stress.
The findings revealed a strong correlation between AVI and established measures of stress. Higher AVI values were associated with greater cortisol exposure, higher peak cortisol levels, and increased allostatic load. Participants who reported high levels of perceived stress on questionnaires likewise had higher AVI compared to those reporting low stress. Critically, the researchers also found a link between AVI and a higher left ventricular mass index, a measure related to heart structure, and an increased risk of heart failure and death. For every 1 cm3/m2 increase in AVI, the risk of heart failure and death increased, suggesting a clinically meaningful connection.
What Does This Indicate for Cardiovascular Risk?
The connection to cardiovascular outcomes is particularly significant. Chronic stress is a well-established risk factor for heart disease, but quantifying that risk has been challenging. This new biomarker offers a potential way to enhance cardiovascular risk stratification – identifying individuals at higher risk – and guide preventive care. Dr. Ghotbi emphasized that with up to 10 years of follow-up data on participants, the team was able to correlate the AI-derived AVI with clinically relevant outcomes, marking it as the first imaging marker of chronic stress validated to independently impact cardiovascular health. Neuroscience News provides further detail on the study’s findings.
Limitations and Future Directions
Although promising, it’s important to acknowledge the limitations of this research. The study population, drawn from the Multi-Ethnic Study of Atherosclerosis, consisted primarily of individuals aged 69.3, with 51% women. Further research is needed to determine whether the findings generalize to younger populations or different ethnic groups. The study also demonstrates correlation, not causation. While AVI is linked to stress and cardiovascular outcomes, it doesn’t prove that stress *causes* the changes in adrenal gland volume or the increased risk of heart failure. Other factors could be at play.
the AVI is a population-level measure. It doesn’t provide information about the specific sources of stress or the individual coping mechanisms that might mitigate its effects. It’s also important to note that adrenal gland volume can be affected by other conditions, such as Cushing’s syndrome, so a high AVI doesn’t automatically equate to chronic stress. The Radiological Society of North America highlights these nuances in their press release.
Operationalizing Stress: What Comes Next?
The researchers envision a future where this AI-driven biomarker is routinely extracted from chest CT scans, providing clinicians with a valuable tool for assessing and managing stress-related health risks. Dr. Teresa Seeman, a study co-author and professor of epidemiology at UCLA, described the work as a “true step forward in operationalizing the cumulative impact of stress on health.” The next steps involve further validation of the biomarker in larger and more diverse populations, as well as exploring its potential applications in other stress-related diseases. Researchers also plan to investigate whether interventions aimed at reducing stress can lead to changes in AVI over time, providing a measurable indicator of treatment effectiveness. This work is likely to spur further investigation into the complex interplay between stress, the adrenal glands, and overall health, potentially leading to new strategies for prevention and treatment.