summary: Researchers have developed an AI tool to detect chronic stress by measuring adrenal gland volume during regular chest CT scans. This biomarker matches cortisol levels, stress questionnaires, and future cardiovascular disease outcomes, providing the first image-based method to quantify stress load in the body.
The results of this study show that larger adrenal volume is associated with greater stress, greater allostatic load, and increased risk of heart failure and death. With millions of CT scans already performed each year, this approach could transform early detection and prevention of stress without the need for new tests or radiation.
important facts
- AI Stress Biomarkers: Adrenal gland volumes measured with CT scans more reliably reflect long-term chronic stress than transient cortisol tests.
- Risk prediction: Increased adrenal volume is associated with elevated cortisol, increased allostatic load, and increased risk of future heart failure.
- Clinical potential: This biomarker can be extracted from routine image processing and provides a scalable tool for early prevention of stress-related diseases.
sauce: RSNA
Researchers used a deep learning AI model to identify a first-of-its-kind chronic stress biomarker that can be detected with routine image processing, according to research to be presented next week at the Radiological Society of North America (RSNA) annual meeting.
According to the American Psychological Association, chronic stress can affect both physical and psychological health and cause a variety of problems, including anxiety, insomnia, muscle pain, high blood pressure, and a weakened immune system. Research shows that chronic stress can contribute to the development of major diseases such as heart disease, depression, and obesity.
The study’s lead author, Dr. Elena Ghotbi, a postdoctoral fellow at Johns Hopkins University School of Medicine in Baltimore, Maryland, developed and trained a deep learning model to measure adrenal gland volume on existing CT scans.
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 assessment of the biological effects of chronic stress across a variety of conditions using existing chest CT scans,” said Dr. Ghotbi.
“This AI-driven biomarker has the potential to enhance cardiovascular risk stratification and guide preventive care without additional testing or radiation.”
Lead author Shadpur Demery, MD, professor of radiology at Johns Hopkins University, said chronic stress is a common symptom and complaint that many adults deal with on a daily basis.
“For the first time, we can ‘see’ long-term stress loads in the body using the scans that patients are already undergoing daily in hospitals across the country. Until now, there has been no way to measure and quantify the cumulative effects of chronic stress other than questionnaires, surrogate serum markers such as chronic inflammation, and cortisol measurements, which are very cumbersome to obtain,” Dr. Demery said.
Unlike a single cortisol measurement, which provides an instantaneous snapshot of stress levels, adrenal volume acts more like a biological barometer of chronic stress.
In this study, researchers obtained data on 2,842 participants (mean age 69.3 years, 51% female) from the Multi-Ethnic Study of Atherosclerosis. The study is a comprehensive study that combines chest CT scans, validated stress questionnaires, cortisol measurements, and markers of allostatic load (the cumulative physiological and psychological effects of chronic stress on the body). This rare integration of imaging, biochemical, and psychosocial data makes it the optimal and perhaps the only cohort for developing imaging biomarkers of chronic stress.
The researchers applied a deep learning model retrospectively to CT scans to segment and calculate the volume of the adrenal glands. Adrenal volume index (AVI) was defined as volume (cm3) divided by height 2 (m2). Salivary cortisol was collected eight times per day over 2 days. Allostatic load was based on BMI, creatinine, hemoglobin, albumin, glucose, white blood cell count, heart rate, and blood pressure.
Statistical associations between AVI and psychosocial stress measures such as cortisol, allostatic load, and depression and perceived stress questionnaires were assessed. Researchers found that AI-derived AVI was correlated with validated stress questionnaires, circulating cortisol levels, and future adverse cardiovascular outcomes.
Higher AVI was associated with higher cortisol, peak cortisol, and allostatic load. Participants with high perceived stress had higher AVI compared to participants with lower stress. AVI was also associated with higher left ventricular mass index. Each 1 cm3/m2 increase in AVI was associated with an increased risk of heart failure and death.
“With up to 10 years of participant follow-up data, we were able to correlate AI-derived AVI with relevant and clinically meaningful outcomes,” said Dr. Ghotbi.
“This is the first imaging marker of chronic stress that has been validated and shown to have an independent impact on cardiovascular disease, or heart failure.”
“For more than 30 years, we’ve known that chronic stress can deplete the body across a variety of systems,” said study co-author Teresa E. Seaman, Ph.D., professor of epidemiology at UCLA and a pioneering researcher in stress and health.
“What’s so exciting about this study is that it combines adrenal volume, a routinely acquired imaging feature, with validated biological and psychological measures of stress and shows that it can independently predict key clinical outcomes. This is a real step forward in operationalizing the cumulative effects of stress on health.”
Dr. Demehri said that by linking easily measurable image features with multiple validated indicators of stress and downstream disease, this study introduces an entirely new practical way to quantify chronic stress.
“The important significance of this study is that this biomarker is obtained from CT, which is widely performed in the United States for a variety of reasons,” said Dr. DeMeffri. “Second, it is a physiologically relevant measure of adrenal volume and is part of the physiological cascade of chronic stress.”
The researchers said this imaging biomarker could be used for a variety of diseases associated with chronic stress in middle-aged and older adults.
Other co-authors are Roham Hadidchi, Seyedhouman Seyedekrami, Quincy A. Hathaway, MD, Ph.D., Michael Banks, Nikhil Subhas, Matthew J. Budoff, MD, David A. Bluemke, MD, Ph.D., R. Graham Barr, and Joao AC Lima, MD.
Answers to key questions:
A: They used adrenal gland volume measured by AI to identify the first image-based biomarker of chronic stress.
A: It reflects long-term physiological stress and correlates with cortisol, allostatic load, and future cardiovascular risk.
A: Cortisol fluctuates throughout the day. Adrenal volume provides a stable and cumulative indicator of long-term stress load.
Editorial note:
- This article was edited by Neuroscience News editors.
- Journal articles were reviewed in full text.
- Additional context added by staff.
About this AI and stress research news
author: Linda Brooks
sauce: RSNA
contact: Linda Brooks – RSNA
image: Image credited to Neuroscience News
Original research: The results of this study will be presented at the 111th Scientific Meeting and Annual Meeting of the Radiological Society of North America (RSNA).
