Salminen LE, et al. - In 97 combat-exposed military veterans, researchers used a novel machine learning method—evolving partitions to improve classification (EPIC)—to recognize shared and unique structural neuroimaging indicators of early life stress (ELS) and posttraumatic stress disorder (PTSD). In all analyses, surface area in the right posterior cingulate was the one variable that was repetitively selected as a crucial feature for PTSD and ELS classification. In this sample of combat-exposed military veterans, EPIC revealed unique patterns of features that distinguished PTSD and ELS, which might represent distinct biotypes of stress-related neuropathology.