Search

Background: Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group. Methods: We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality. Results: We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance. Conclusion: These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.

Abstract Background Posttraumatic stress disorder (PTSD) is associated with markers of accelerated aging. Estimates of brain age, compared to chronological age, may clarify the effects of PTSD on the brain and may inform treatment approaches targeting the neurobiology of aging in the context of PTSD. Method Adult subjects (N = 2229; 56.2% male) aged 18–69 years (mean = 35.6, SD = 11.0) from 21 ENIGMA‐PGC PTSD sites underwent T1‐weighted brain structural magnetic resonance imaging, and PTSD assessment (PTSD+, n = 884). Previously trained voxel‐wise (brainageR) and region‐of‐interest (BARACUS and PHOTON) machine learning pipelines were compared in a subset of control subjects (n = 386). Linear mixed effects models were conducted in the full sample (those with and without PTSD) to examine the effect of PTSD on brain predicted age difference (brain PAD; brain age − chronological age) controlling for chronological age, sex, and scan site. Results BrainageR most accurately predicted brain age in a subset (n = 386) of controls (brainageR: ICC = 0.71, R = 0.72, MAE = 5.68; PHOTON: ICC = 0.61, R = 0.62, MAE = 6.37; BARACUS: ICC = 0.47, R = 0.64, MAE = 8.80). Using brainageR, a three‐way interaction revealed that young males with PTSD exhibited higher brain PAD relative to male controls in young and old age groups; old males with PTSD exhibited lower brain PAD compared to male controls of all ages. Discussion Differential impact of PTSD on brain PAD in younger versus older males may indicate a critical window when PTSD impacts brain aging, followed by age‐related brain changes that are consonant with individuals without PTSD. Future longitudinal research is warranted to understand how PTSD impacts brain aging across the lifespan.

Background: Given critical care nurses' high prepandemic levels of moral distress and burnout, the COVID-19 pandemic will most likely have a tremendous influence on intensive care unit (ICU) nurses' mental health and continuation in the ICU workforce., Objective: To describe the experiences of ICU nurses during the COVID-19 pandemic in the United States., Methods: Nurses who worked in ICUs in the United States during the COVID-19 pandemic were recruited to complete a survey from October 2020 through early January 2021 through social media and the American Association of Critical-Care Nurses. Three open-ended questions focused on the experiences of ICU nurses during the pandemic., Results: Of 498 nurses who completed the survey, 285 answered the open-ended questions. Nurses reported stress related to a lack of evidence-based treatment, poor patient prognosis, and lack of family presence in the ICU. Nurses perceived inadequate leadership support and inequity within the health care team. Lack of consistent community support to slow the spread of COVID-19 or recognition that COVID-19 was real increased nurses' feelings of isolation. Nurses reported physical and emotional symptoms including exhaustion, anxiety, sleeplessness, and moral distress. Fear of contracting COVID-19 or of infecting family and friends was also prevalent., Conclusions: Intensive care unit nurses in the United States experienced unprecedented and immense burden during the COVID-19 pandemic. Understanding these experiences provides insights into areas that must be addressed to build and sustain an ICU nurse workforce. Studies are needed to further describe nurses' experiences during the COVID-19 pandemic and identify effective resources that support ICU nurse well-being., (©2022 American Association of Critical-Care Nurses.)