Aims Childhood adversities (CAs) predict heightened risks of posttraumatic stress disorder (PTSD) and major depressive episode (MDE) among people exposed to adult traumatic events. Identifying which CAs put individuals at greatest risk for these adverse posttraumatic neuropsychiatric sequelae (APNS) is important for targeting prevention interventions. Methods Data came from n = 999 patients ages 18-75 presenting to 29 U.S. emergency departments after a motor vehicle collision (MVC) and followed for 3 months, the amount of time traditionally used to define chronic PTSD, in the Advancing Understanding of Recovery After Trauma (AURORA) study. Six CA types were self-reported at baseline: physical abuse, sexual abuse, emotional abuse, physical neglect, emotional neglect and bullying. Both dichotomous measures of ever experiencing each CA type and numeric measures of exposure frequency were included in the analysis. Risk ratios (RRs) of these CA measures as well as complex interactions among these measures were examined as predictors of APNS 3 months post-MVC. APNS was defined as meeting self-reported criteria for either PTSD based on the PTSD Checklist for DSM-5 and/or MDE based on the PROMIS Depression Short-Form 8b. We controlled for pre-MVC lifetime histories of PTSD and MDE. We also examined mediating effects through peritraumatic symptoms assessed in the emergency department and PTSD and MDE assessed in 2-week and 8-week follow-up surveys. Analyses were carried out with robust Poisson regression models. Results Most participants (90.9%) reported at least rarely having experienced some CA. Ever experiencing each CA other than emotional neglect was univariably associated with 3-month APNS (RRs = 1.31-1.60). Each CA frequency was also univariably associated with 3-month APNS (RRs = 1.65-2.45). In multivariable models, joint associations of CAs with 3-month APNS were additive, with frequency of emotional abuse (RR = 2.03; 95% CI = 1.43-2.87) and bullying (RR = 1.44; 95% CI = 0.99-2.10) being the strongest predictors. Control variable analyses found that these associations were largely explained by pre-MVC histories of PTSD and MDE. Conclusions Although individuals who experience frequent emotional abuse and bullying in childhood have a heightened risk of experiencing APNS after an adult MVC, these associations are largely mediated by prior histories of PTSD and MDE.

The authors sought to characterize adverse posttraumatic neuropsychiatric sequelae (APNS) symptom trajectories across ten symptom domains (pain, depression, sleep, nightmares, avoidance, re-experiencing, anxiety, hyperarousal, somatic, and mental/fatigue symptoms) in a large, diverse, understudied sample of motor vehicle collision (MVC) survivors. More than two thousand MVC survivors were enrolled in the emergency department (ED) and completed a rotating battery of brief smartphone-based surveys over a 2-month period. Measurement models developed from survey item responses were used in latent growth curve/mixture modeling to characterize homogeneous symptom trajectories. Associations between individual trajectories and pre-trauma and peritraumatic characteristics and traditional outcomes were compared, along with associations within and between trajectories. APNS across all ten symptom domains were common in the first two months after trauma. Many risk factors and associations with high symptom burden trajectories were shared across domains. Both across and within traditional diagnostic boundaries, APNS trajectory intercepts, and slopes were substantially correlated. Across all domains, symptom severity in the immediate aftermath of trauma (trajectory intercepts) had the greatest influence on the outcome. An interactive data visualization tool was developed to allow readers to explore relationships of interest between individual characteristics, symptom trajectories, and traditional outcomes (http://itr.med.unc.edu/aurora/parcoord/). Individuals presenting to the ED after MVC commonly experience a broad constellation of adverse posttraumatic symptoms. Many risk factors for diverse APNS are shared. Individuals diagnosed with a single traditional outcome should be screened for others. The utility of multidimensional categorizations that characterize individuals across traditional diagnostic domains should be explored.

OBJECTIVE: Coronavirus disease 2019 (COVID-19) poses societal challenges that require expeditious data and knowledge sharing. Though organizational clinical data are abundant, these are largely inaccessible to outside researchers. Statistical, machine learning, and causal analyses are most successful with large-scale data beyond what is available in any given organization. Here, we introduce the National COVID Cohort Collaborative (N3C), an open science community focused on analyzing patient-level data from many centers. MATERIALS AND METHODS: The Clinical and Translational Science Award Program and scientific community created N3C to overcome technical, regulatory, policy, and governance barriers to sharing and harmonizing individual-level clinical data. We developed solutions to extract, aggregate, and harmonize data across organizations and data models, and created a secure data enclave to enable efficient, transparent, and reproducible collaborative analytics. RESULTS: Organized in inclusive workstreams, we created legal agreements and governance for organizations and researchers; data extraction scripts to identify and ingest positive, negative, and possible COVID-19 cases; a data quality assurance and harmonization pipeline to create a single harmonized dataset; population of the secure data enclave with data, machine learning, and statistical analytics tools; dissemination mechanisms; and a synthetic data pilot to democratize data access. CONCLUSIONS: The N3C has demonstrated that a multisite collaborative learning health network can overcome barriers to rapidly build a scalable infrastructure incorporating multiorganizational clinical data for COVID-19 analytics. We expect this effort to save lives by enabling rapid collaboration among clinicians, researchers, and data scientists to identify treatments and specialized care and thereby reduce the immediate and long-term impacts of COVID-19.

Background: A better understanding of the extent to which prior occurrences of posttraumatic stress disorder (PTSD) and major depressive episode (MDE) predict psychopathological reactions to subsequent traumas might be useful in targeting posttraumatic preventive interventions. Methods: Data come from 1306 patients presenting to 29 U.S. emergency departments (EDs) after a motor vehicle collision (MVC) in the advancing understanding of recovery after trauma study. Patients completed self-reports in the ED and 2-weeks, 8-weeks, and 3-months post-MVC. Associations of pre-MVC probable PTSD and probable MDE histories with subsequent 3-months post-MVC probable PTSD and probable MDE were examined along with mediation through intervening peritraumatic, 2-, and 8-week disorders. Results: 27.6% of patients had 3-month post-MVC probable PTSD and/or MDE. Pre-MVC lifetime histories of these disorders were not only significant (relative risk = 2.6–7.4) but were dominant (63.1% population attributable risk proportion [PARP]) predictors of this 3-month outcome, with 46.6% prevalence of the outcome among patients with pre-MVC disorder histories versus 9.9% among those without such histories. The associations of pre-MVC lifetime disorders with the 3-month outcome were mediated largely by 2- and 8-week probable PTSD and MDE (PARP decreasing to 22.8% with controls for these intervening disorders). Decomposition showed that pre-MVC lifetime histories predicted both onset and persistence of these intervening disorders as well as the higher conditional prevalence of the 3-month outcome in the presence of these intervening disorders. Conclusions: Assessments of pre-MVC PTSD and MDE histories and follow-ups at 2 and 8 weeks could help target early interventions for psychopathological reactions to MVCs.

Background: Obtaining medical data using wearable sensors is a potential replacement for in-hospital monitoring, but the lack of data for such sensors poses a challenge for development. One solution is using in-hospital recordings to boost performance via transfer learning. While there are many possible transfer learning algorithms, few have been tested in the domain of EEG-based sleep staging. Furthermore, there are few ways for determining which transfer learning method will work best besides exhaustive testing. Measures of transferability do exist, but are typically used for selection of pre-trained models rather than algorithms and few have been tested on medical signals. We tested several supervised transfer learning algorithms on a sleep staging task using a single channel of EEG (AF7-Fpz) captured from an in-home commercial system. Results: Two neural networks—one bespoke and another state-of-art open-source architecture—were pre-trained on one of six source datasets comprising 11,561 subjects undergoing clinical polysomnograms (PSGs), then re-trained on a target dataset of 75 full-night recordings from 24 subjects. Several transferability measures were then tested to determine which is most effective for assessing performance on unseen target data. Performance on the target dataset was improved using transfer learning, with re-training the head layers being the most effective in the majority of cases (up to 63.9% of cases). Transferability measures generally provided significant correlations with accuracy (up to r= - 0.53). Conclusion: Re-training the head layers provided the largest performance boost. Transferability measures are useful indicators of transfer learning effectiveness.

Objective Whether short-term, low-potency opioid prescriptions for acute pain lead to future at-risk opioid use remains controversial and inadequately characterized. Our objective was to measure the association between emergency department (ED) opioid analgesic exposure after a physical, trauma-related event and subsequent opioid use. We hypothesized ED opioid analgesic exposure is associated with subsequent at-risk opioid use. Methods Participants were enrolled in AURORA, a prospective cohort study of adult patients in 29 U. S., urban EDs receiving care for a traumatic event. Exclusion criteria were hospital admission, persons reporting any non-medical opioid use (e.g., opioids without prescription or taking more than prescribed for euphoria) in the 30 days before enrollment, and missing or incomplete data regarding opioid exposure or pain. We used multivariable logistic regression to assess the relationship between ED opioid exposure and at-risk opioid use, defined as any self-reported non-medical opioid use after initial ED encounter or prescription opioid use at 3-months. Results Of 1441 subjects completing 3-month follow-up, 872 participants were included for analysis. At-risk opioid use occurred within 3 months in 33/620 (5.3%, CI: 3.7,7.4) participants without ED opioid analgesic exposure; 4/16 (25.0%, CI: 8.3, 52.6) with ED opioid prescription only; 17/146 (11.6%, CI: 7.1, 18.3) with ED opioid administration only; 12/90 (13.3%, CI: 7.4, 22.5) with both. Controlling for clinical factors, adjusted odds ratios (aORs) for at-risk opioid use after ED opioid exposure were: ED prescription only: 4.9 (95% CI 1.4, 17.4); ED administration for analgesia only: 2.0 (CI 1.0, 3.8); both: 2.8 (CI 1.2, 6.5). Conclusions ED opioids were associated with subsequent at-risk opioid use within three months in a geographically diverse cohort of adult trauma patients. This supports need for prospective studies focused on the long-term consequences of ED opioid analgesic exposure to estimate individual risk and guide therapeutic decision-making.

Background: It has been hypothesized that low access to healthy and nutritious food increases health disparities. Low-accessibility areas, called food deserts, are particularly commonplace in lower-income neighborhoods. The metrics for measuring the food environment’s health, called food desert indices, are primarily based on decadal census data, limiting their frequency and geographical resolution to that of the census. We aimed to create a food desert index with finer geographic resolution than census data and better responsiveness to environmental changes. Materials and methods: We augmented decadal census data with real-time data from platforms such as Yelp and Google Maps and crowd-sourced answers to questionnaires by the Amazon Mechanical Turks to create a real-time, context-aware, and geographically refined food desert index. Finally, we used this refined index in a concept application that suggests alternative routes with similar ETAs between a source and destination in the Atlanta metropolitan area as an intervention to expose a traveler to better food environments. Results: We made 139,000 pull requests to Yelp, analyzing 15,000 unique food retailers in the metro Atlanta area. In addition, we performed 248,000 walking and driving route analyses on these retailers using Google Maps’ API. As a result, we discovered that the metro Atlanta food environment creates a strong bias towards eating out rather than preparing a meal at home when access to vehicles is limited. Contrary to the food desert index that we started with, which changed values only at neighborhood boundaries, the food desert index that we built on top of it captured the changing exposure of a subject as they walked or drove through the city. This model was also sensitive to the changes in the environment that occurred after the census data was collected. Conclusions: Research on the environmental components of health disparities is flourishing. New machine learning models have the potential to augment various information sources and create fine-tuned models of the environment. This opens the way to better understanding the environment and its effects on health and suggesting better interventions.

Pre-ejection period (PEP) is an index of sympathetic nervous system activity that can be computed from electrocardiogram (ECG) and impedance cardiogram (ICG) signals, but sensitive to speech/motion artifact. We sought to validate an ICG noise removal method, three-stage ensemble-average algorithm (TEA), in data acquired from a clinical trial comparing active versus sham non-invasive vagal nerve stimulation (tcVNS) after standardized speech stress. We first compared TEA's performance versus the standard conventional ensemble-average algorithm (CEA) approach to classify noisy ICG segments. We then analyzed ECG and ICG data to measure PEP and compared group-level differences in stress states with each approach. We evaluated 45 individuals, of whom 23 had post-traumatic stress disorder (PTSD). We found that the TEA approach identified artifact-corrupted beats with intraclass correlation coefficient > 0.99 compared to expert adjudication. TEA also resulted in higher group-level differences in PEP between stress states than CEA. PEP values were lower in the speech stress (vs. baseline rest) group using both techniques, but the differences were greater using TEA (12.1 ms) than CEA (8.0 ms). PEP differences in groups divided by PTSD status and tcVNS (active vs. sham) were also greater when using the TEA versus CEA method, although the magnitude of the differences was lower. In conclusion, TEA helps to accurately identify noisy ICG beats during speaking stress, and this increased accuracy improves sensitivity to group-level differences in stress states compared to CEA, suggesting greater clinical utility.

A key feature of posttraumatic stress disorder (PTSD) is a disruption of hypothalamic-pituitary-adrenal (HPA) axis feedback sensitivity and cortisol levels. Despite known diurnal rhythmicity of cortisol, there has been little exploration of the circadian timing of the index trauma and consequent cortisol release. Stress-related glucocorticoid pulses have been shown to shift clocks in peripheral organs but not the suprachiasmatic nucleus, uncoupling the central and peripheral clocks. A sample of 425 participants was recruited in the Emergency Department following a DSM-IV-TR Criterion A trauma. The Zeitgeber time of the trauma was indexed in minutes since sunrise, which was hypothesized to covary with circadian blood cortisol levels (high around sunrise and decreasing over the day). Blood samples were collected M(SD)= 4.0(4.0) hours post-trauma. PTSD symptoms six months post-trauma were found to be negatively correlated with trauma time since sunrise (r(233) = −0.15, p = 0.02). The effect remained when adjusting for sex, age, race, clinician-rated severity, education, pre-trauma PTSD symptoms, and time of the blood draw (β = -0.21, p = 0.00057). Cortisol levels did not correlate with blood draw time, consistent with a masking effect of the acute stress response obscuring the underlying circadian rhythm. Interactions between trauma time and expression of NPAS2 (punadjusted=0.042) and TIMELESS (punadjusted=0.029) predicted six-month PTSD symptoms. The interaction of trauma time and cortisol concentration was significantly correlated with the expression of PER1 (padjusted=0.029). The differential effect of time of day on future symptom severity suggests a role of circadian effects in PTSD development, potentially through peripheral clock disruption.

Recent significant increases in affordable and accessible computational power and data storage have enabled machine learning to provide almost unbelievable classification and prediction performances compared to well-trained humans. There have been some promising (but limited) results in the complex healthcare landscape, particularly in imaging. This promise has led some individuals to leap to the conclusion that we will solve an ever-increasing number of problems in human health and medicine by applying `artificial intelligence' to `big (medical) data'. The scientific literature has been inundated with algorithms, outstripping our ability to review them effectively. Unfortunately, I argue that most, if not all of these publications or commercial algorithms make several fundamental errors. I argue that because everyone (and therefore every algorithm) has blind spots, there are multiple `best' algorithms, each of which excels on different types of patients or in different contexts. Consequently, we should vote many algorithms together, weighted by their overall performance, their independence from each other, and a set of features that define the context (i.e., the features that maximally discriminate between the situations when one algorithm outperforms another). This approach not only provides a better performing classifier or predictor but provides confidence intervals so that a clinician can judge how to respond to an alert. Moreover, I argue that a sufficient number of (mostly) independent algorithms that address the same problem can be generated through a large international competition/challenge, lasting many months and define the conditions for a successful event. Finally, I propose introducing the requirement for major grantees to run challenges in the final year of funding to maximize the value of research and select a new generation of grantees.