Researchers at Johns Hopkins University have identified a groundbreaking biomarker for chronic stress using a deep learning AI model, which can be detected through routine imaging techniques. This significant finding will be presented at the annual meeting of the Radiological Society of North America (RSNA) next week.
Chronic stress has well-documented effects on both physical and psychological health. It can contribute to severe conditions such as anxiety, insomnia, and heart disease, according to the American Psychological Association. The potential implications of chronic stress extend to a range of illnesses, including obesity and depression, making this research particularly vital.
Dr. Elena Ghotbi, a postdoctoral research fellow at Johns Hopkins, led the study, which involved developing and training a deep learning model to measure adrenal gland volume on existing chest CT scans. The model’s application is especially relevant given that tens of millions of chest CT scans are conducted annually in the United States.
“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. This AI-driven biomarker has the potential to enhance cardiovascular risk stratification and guide preventive care without additional testing or radiation,” said Dr. Ghotbi.
Senior author Dr. Shadpour Demehri, a professor of radiology at Johns Hopkins, emphasized the prevalence of chronic stress among adults. “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,” he stated. Dr. Demehri noted that previous methods of assessing chronic stress were limited, relying primarily on subjective questionnaires or cumbersome serum markers.
The study encompassed a cohort of 2,842 participants, with a mean age of 69.3 and a balanced gender representation. This data was drawn from the Multi-Ethnic Study of Atherosclerosis, which integrates chest CT scans with validated stress questionnaires and cortisol measurements. The study’s unique combination of imaging and biochemical data provided an ideal foundation for developing an imaging biomarker for chronic stress.
The researchers utilized the deep learning model to compute the volume of the adrenal glands, defining the Adrenal Volume Index (AVI) as the volume in cubic centimeters divided by height squared in square meters. They also gathered data on salivary cortisol levels, measuring them multiple times a day over two days. Allostatic load—a measure reflecting the cumulative physiological effects of chronic stress—was assessed alongside various health indicators.
Analysis revealed significant correlations: AI-derived AVI was associated with validated stress questionnaires, cortisol levels, and future adverse cardiovascular outcomes. Higher AVI correlated with increased cortisol, peak cortisol, and allostatic load. Notably, participants reporting high levels of perceived stress exhibited elevated AVI compared to those with lower stress levels. This biomarker also correlated with a higher left ventricular mass index, with each 1 cm³/m² increase in AVI linked to an increased risk of heart failure and mortality.
“With up to 10-year follow-up data on our participants, we were able to correlate AI-derived AVI with clinically meaningful and relevant outcomes,” Dr. Ghotbi remarked. “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.”
Dr. Teresa E. Seeman, a professor of epidemiology at UCLA and co-author of the study, noted the importance of linking a routinely obtained imaging feature, like adrenal volume, to validated biological and psychological measures of stress. “It’s a true step forward in operationalizing the cumulative impact of stress on health,” she said.
The implications of this research extend to various diseases associated with chronic stress in middle-aged and older adults. Dr. Demehri highlighted the significance of linking a measurable imaging feature to multiple validated indicators of stress and downstream disease, representing a new method to quantify chronic stress.
“The key significance of this work is that this biomarker is obtainable from CTs that are performed widely in the United States for various reasons,” he added. “Secondly, it is a physiologically sound measure of adrenal volume, which is part of the chronic stress physiological cascade.”
As researchers explore further applications of this imaging biomarker, it may offer a practical tool for assessing chronic stress and its health impacts, paving the way for improved clinical outcomes and preventive care strategies.
U of T Study Reveals AI Generates Narrow Body Ideals, Missing Diversity and Inclusion
Yushau Shuaib Reveals 75% AI Adoption in Nigeria’s Crisis Communication at CCC Symposium
CxOs Project IT Budget Increases, Focus on AI with 52% Aiming for Strategic Differentiation
Generative AI Agents Automate Key Cash Management Tasks, Boosting Liquidity Efficiency
Machine Learning Reveals Phase Transition in Zinc Oxide Nanoparticles During Growth
