AI Unveils a Hidden Stress Signal in Routine CT Scans
A groundbreaking study has harnessed the power of artificial intelligence to uncover a novel biomarker of chronic stress, offering a glimpse into the body's hidden stress burden. The research, presented at the Radiological Society of North America's annual conference, introduces a deep learning model that can identify adrenal gland size on standard medical images, a significant advancement in stress assessment.
Chronic stress, a pervasive issue affecting both physical and mental health, has long been associated with mood disorders, anxiety, sleep disturbances, muscle pain, high blood pressure, and a weakened immune system, according to the American Psychological Association. This study takes a significant step forward by providing a direct and measurable indicator of chronic stress on medical images.
AI's Role in Measuring Adrenal Glands
The study's lead researcher, Dr. Elena Ghotbi, developed a deep learning tool to calculate adrenal gland size from existing CT scans. This approach is particularly valuable given the widespread use of chest CT scans, with tens of millions performed annually in the United States alone.
Dr. Ghotbi emphasizes the potential of this method: "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."
Visualizing the Body's Stress Burden
Senior author Dr. Shadpour Demehri highlights the significance of this discovery: "For the first time, we can 'see' the long-term burden of stress inside the body using a scan that patients already undergo daily in hospitals. Until now, measuring and quantifying chronic stress's cumulative effects has been challenging, relying on questionnaires and surrogate markers like cortisol, which are cumbersome to obtain."
The adrenal glands, unlike a single cortisol test, serve as a long-term gauge of chronic stress. This study's unique contribution lies in its integration of imaging, biochemical data, and psychosocial assessments, enabling the creation of an imaging-based marker of chronic stress.
Large Cohort Study Links Imaging, Hormones, and Stress
The research team analyzed data from 2,842 participants in the Multi-Ethnic Study of Atherosclerosis, a comprehensive study combining chest CT imaging, validated stress questionnaires, cortisol measurements, and indicators of allostatic load. This multi-ethnic cohort, with its diverse population, was instrumental in establishing a connection between imaging, hormones, and stress.
The investigators applied their deep learning model to automatically outline and measure adrenal gland volume, defining the Adrenal Volume Index (AVI) as adrenal volume divided by height squared. Participants provided salivary cortisol samples multiple times a day over two days to capture hormonal patterns.
AVI Tracks Stress, Hormones, and Heart Risk
The study revealed a strong correlation between AVI, cortisol levels, allostatic load, and psychosocial stress indicators. Higher AVI values were associated with increased cortisol exposure, peak cortisol levels, and allostatic load. Individuals reporting high perceived stress had elevated AVI compared to those with low stress.
AVI was also linked to a higher left ventricular mass index, a heart structure measure. The risk of heart failure and death increased with every 1 cm3/m2 increase in AVI.
Dr. Ghotbi highlights the clinical significance: "With up to 10-year follow-up data, we correlated AI-derived AVI with clinically meaningful outcomes, making it the first imaging marker of chronic stress validated to impact cardiovascular health."
A New Approach to Stress Measurement
Co-author Dr. Teresa E. Seeman, a pioneer in stress and health research, emphasizes the excitement of this discovery: "For over three decades, we've understood chronic stress's cumulative impact on the body. This study links adrenal volume, a routine imaging feature, with validated stress measures, independently predicting major clinical outcomes. It's a significant step in operationalizing stress's impact on health."
Dr. Demehri explains the practical implications: "Connecting imaging with established stress markers creates a new approach to measuring chronic stress in clinical practice. This biomarker, derived from widely performed CT scans, is a physiologically sound measure of adrenal volume, reflecting the chronic stress cascade."
The researchers suggest that this imaging biomarker could be applied to various stress-related diseases affecting middle-aged and older adults, marking a significant advancement in stress assessment and management.
