Lauren E Salminen1, Rajendra A Morey2,3, Brandalyn C Riedel1,4, Neda Jahanshad1, Emily L Dennis1,5,6, Paul M Thompson1. 1. Imaging Genetics Center of the Mark and Mary Stevens Institute for Neuroimaging & Informatics, Keck School of Medicine, University of Southern California, Marina del Rey, CA. 2. Durham VA Medical Center, Durham, NC. 3. Duke University Medical Center, Durham, NC. 4. Department of Radiology and Imaging Sciences, Indiana University School of Medicine, Indianapolis, IN. 5. Psychiatry Neuroimaging Laboratory, Harvard Medical School, Boston, MA. 6. Stanford Neurodevelopment, Affect, and Psychopathology Laboratory, Stanford, CA.
Abstract
BACKGROUND AND PURPOSE: Posttraumatic stress disorder (PTSD) is a heterogeneous condition associated with a range of brain imaging abnormalities. Early life stress (ELS) contributes to this heterogeneity, but we do not know how a history of ELS influences traditionally defined brain signatures of PTSD. Here, we used a novel machine learning method - evolving partitions to improve classification (EPIC) - to identify shared and unique structural neuroimaging markers of ELS and PTSD in 97 combat-exposed military veterans. METHODS: We used EPIC with repeated cross-validation (CV) to determine how combinations of cortical thickness, surface area, and subcortical brain volumes could contribute to classification of PTSD (n = 40) versus controls (n = 57), and classification of ELS within the PTSD (ELS+ n = 16; ELS- n = 24) and control groups (ELS+ n = 16; ELS- n = 41). Additional inputs included intracranial volume, age, sex, adult trauma, and depression. RESULTS: On average, EPIC classified PTSD with 69% accuracy (SD = 5%), and ELS with 64% accuracy in the PTSD group (SD = 10%), and 62% accuracy in controls (SD = 6%). EPIC selected unique sets of individual features that classified each group with 75-85% accuracy in post hoc analyses; combinations of regions marginally improved classification from the individual atlas-defined brain regions. Across analyses, surface area in the right posterior cingulate was the only variable that was repeatedly selected as an important feature for classification of PTSD and ELS. CONCLUSIONS: EPIC revealed unique patterns of features that distinguished PTSD and ELS in this sample of combat-exposed military veterans, which may represent distinct biotypes of stress-related neuropathology.
BACKGROUND AND PURPOSE:Posttraumatic stress disorder (PTSD) is a heterogeneous condition associated with a range of brain imaging abnormalities. Early life stress (ELS) contributes to this heterogeneity, but we do not know how a history of ELS influences traditionally defined brain signatures of PTSD. Here, we used a novel machine learning method - evolving partitions to improve classification (EPIC) - to identify shared and unique structural neuroimaging markers of ELS and PTSD in 97 combat-exposed military veterans. METHODS: We used EPIC with repeated cross-validation (CV) to determine how combinations of cortical thickness, surface area, and subcortical brain volumes could contribute to classification of PTSD (n = 40) versus controls (n = 57), and classification of ELS within the PTSD (ELS+ n = 16; ELS- n = 24) and control groups (ELS+ n = 16; ELS- n = 41). Additional inputs included intracranial volume, age, sex, adult trauma, and depression. RESULTS: On average, EPIC classified PTSD with 69% accuracy (SD = 5%), and ELS with 64% accuracy in the PTSD group (SD = 10%), and 62% accuracy in controls (SD = 6%). EPIC selected unique sets of individual features that classified each group with 75-85% accuracy in post hoc analyses; combinations of regions marginally improved classification from the individual atlas-defined brain regions. Across analyses, surface area in the right posterior cingulate was the only variable that was repeatedly selected as an important feature for classification of PTSD and ELS. CONCLUSIONS: EPIC revealed unique patterns of features that distinguished PTSD and ELS in this sample of combat-exposed military veterans, which may represent distinct biotypes of stress-related neuropathology.
Authors: Carolina P Clancy; Anna Graybeal; Whitney P Tompson; Kourtni S Badgett; Michelle E Feldman; Patrick S Calhoun; Alaattin Erkanli; Michael A Hertzberg; Jean C Beckham Journal: J Clin Psychiatry Date: 2006-09 Impact factor: 4.384
Authors: P Barttfeld; S Abboud; H Lagercrantz; U Adén; N Padilla; A D Edwards; L Cohen; M Sigman; S Dehaene; G Dehaene-Lambertz Journal: Brain Struct Funct Date: 2018-05-11 Impact factor: 3.270
Authors: Brianna M Byllesby; Jon D Elhai; Marijo Tamburrino; Thomas H Fine; Gregory Cohen; Laura Sampson; Edwin Shirley; Philip K Chan; Israel Liberzon; Sandro Galea; Joseph R Calabrese Journal: J Affect Disord Date: 2017-01-15 Impact factor: 4.839
Authors: Ronald A Cohen; Stuart Grieve; Karin F Hoth; Robert H Paul; Lawrence Sweet; David Tate; John Gunstad; Laura Stroud; Jeanne McCaffery; Brian Hitsman; Raymond Niaura; C Richard Clark; Alexander McFarlane; Alexander MacFarlane; Richard Bryant; Evian Gordon; Leanne M Williams Journal: Biol Psychiatry Date: 2006-04-17 Impact factor: 13.382
Authors: Jacklynn M Fitzgerald; Elisabeth Kate Webb; Carissa N Weis; Ashley A Huggins; Ken P Bennett; Tara A Miskovich; Jessica L Krukowski; Terri A deRoon-Cassini; Christine L Larson Journal: Biol Psychiatry Cogn Neurosci Neuroimaging Date: 2021-09-01