Stress is a part of everyday life. Chronic stress that persists over an extended period of time can lead to a higher risk of developing physical and mental health issues. Having a method to quantify stress levels can be a useful diagnostic tool for clinicians. Researchers at Johns Hopkins University School of Medicine have developed a new, noninvasive, artificial intelligence (AI) deep learning digital biomarker for chronic stress, which was unveiled at the recent annual meeting of the Radiological Society of North America (RSNA).

What sets this study apart is that it not only considers biological factors but also considers psychosocial stress indicators, such as perceived stress questionnaires and depression, which have been clinically validated. The team evaluated AVI vis-à-vis psychosocial factors, cortisol, and the cumulative physiological effects, called allostatic load, which were calculated from blood pressure, heart rate, glucose, BMI, hemoglobin, albumin, WBC, and creatinine.

“We used a deep learning model to automatically segment adrenals in a three-dimensional manner, and after that, we measured adrenal volumes and........

© Psychology Today