The risk of posttraumatic stress disorder (PTSD) following trauma is heritable, but robust common variants have yet to be identified. In a multi-ethnic cohort including over 30,000 PTSD cases and 170,000 controls we conduct a genome-wide association study of PTSD. We demonstrate SNP-based heritability estimates of 5–20%, varying by sex. Three genome-wide significant loci are identified, 2 in European and 1 in African-ancestry analyses. Analyses stratified by sex implicate 3 additional loci in men. Along with other novel genes and non-coding RNAs, a Parkinson’s disease gene involved in dopamine regulation, PARK2, is associated with PTSD. Finally, we demonstrate that polygenic risk for PTSD is significantly predictive of re-experiencing symptoms in the Million Veteran Program dataset, although specific loci did not replicate. These results demonstrate the role of genetic variation in the biology of risk for PTSD and highlight the necessity of conducting sex-stratified analyses and expanding GWAS beyond European ancestry populations.

Major depressive disorder (MDD) is associated with premature mortality and is an independent risk factor for a broad range of diseases, especially those associated with aging, such as cardiovascular disease, diabetes, and Alzheimer’s disease. However, the pathophysiology underlying increased rates of somatic disease in MDD remains unknown. It has been proposed that MDD represents a state of accelerated cellular aging, and several measures of cellular aging have been developed in recent years. Among such metrics, estimators of biological age based on predictable age-related patterns of DNA methylation (DNAm), so-called ‘epigenetic clocks’, have shown particular promise for their ability to capture accelerated aging in psychiatric disease. The recently developed DNAm metric known as ‘GrimAge’ is unique in that it was trained on time-to-death data and has outperformed its predecessors in predicting both morbidity and mortality. Yet, GrimAge has not been investigated in MDD. Here we measured GrimAge in 49 somatically healthy unmedicated individuals with MDD and 60 age-matched healthy controls. We found that individuals with MDD exhibited significantly greater GrimAge relative to their chronological age (‘AgeAccelGrim’) compared to healthy controls (p = 0.001), with a median of 2 years of excess cellular aging. This difference remained significant after controlling for sex, current smoking status, and body-mass index (p = 0.015). These findings are consistent with prior suggestions of accelerated cellular aging in MDD, but are the first to demonstrate this with an epigenetic metric predictive of premature mortality.

Active-duty Army personnel can be exposed to traumatic warzone events and are at increased risk for developing post-traumatic stress disorder (PTSD) compared with the general population. PTSD is associated with high individual and societal costs, but identification of predictive markers to determine deployment readiness and risk mitigation strategies is not well understood. This prospective longitudinal naturalistic cohort study—the Fort Campbell Cohort study—examined the value of using a large multidimensional dataset collected from soldiers prior to deployment to Afghanistan for predicting post-deployment PTSD status. The dataset consisted of polygenic, epigenetic, metabolomic, endocrine, inflammatory and routine clinical lab markers, computerized neurocognitive testing, and symptom self-reports. The analysis was computed on active-duty Army personnel (N = 473) of the 101st Airborne at Fort Campbell, Kentucky. Machine-learning models predicted provisional PTSD diagnosis 90–180 days post deployment (random forest: AUC = 0.78, 95% CI = 0.67–0.89, sensitivity = 0.78, specificity = 0.71; SVM: AUC = 0.88, 95% CI = 0.78–0.98, sensitivity = 0.89, specificity = 0.79) and longitudinal PTSD symptom trajectories identified with latent growth mixture modeling (random forest: AUC = 0.85, 95% CI = 0.75–0.96, sensitivity = 0.88, specificity = 0.69; SVM: AUC = 0.87, 95% CI = 0.79–0.96, sensitivity = 0.80, specificity = 0.85). Among the highest-ranked predictive features were pre-deployment sleep quality, anxiety, depression, sustained attention, and cognitive flexibility. Blood-based biomarkers including metabolites, epigenomic, immune, inflammatory, and liver function markers complemented the most important predictors. The clinical prediction of post-deployment symptom trajectories and provisional PTSD diagnosis based on pre-deployment data achieved high discriminatory power. The predictive models may be used to determine deployment readiness and to determine novel pre-deployment interventions to mitigate the risk for deployment-related PTSD.

In this review, we compiled convolutional neural network (CNN) methods which have the potential to automate the manual, costly and error-prone processing of medical images. We attempted to provide a thorough survey of improved architectures, popular frameworks, activation functions, ensemble techniques, hyperparameter optimizations, performance metrics, relevant datasets and data preprocessing strategies that can be used to design robust CNN models. We also used machine learning algorithms for the statistical modeling of the current literature to uncover latent topics, method gaps, prevalent themes and potential future advancements. The statistical modeling results indicate a temporal shift in favor of improved CNN designs, such as a shift from the use of a CNN architecture to a CNN-transformer hybrid. The insights from statistical modeling point that the surge of CNN practitioners into the medical imaging field, partly driven by the COVID-19 challenge, catalyzed the use of CNN methods for detecting and diagnosing pathological conditions. This phenomenon likely contributed to the sharp increase in the number of publications on the use of CNNs for medical imaging, both during and after the pandemic. Overall, the existing literature has certain gaps in scope with respect to the design and optimization of CNN architectures and methods specifically for medical imaging. Additionally, there is a lack of post hoc explainability of CNN models and slow progress in adopting CNNs for low-resource medical imaging. This review ends with a list of open research questions that have been identified through statistical modeling and recommendations that can potentially help set up more robust, improved and reproducible CNN experiments for medical imaging.