To Scan or Not to Scan: Overutilization of Computed Tomography for Minor Head Injury at a Pediatric Trauma Center.

BACKGROUND: Degree of compliance with Pediatric Emergency Care Applied Research Network (PECARN) recommendations for radiographic evaluation following minor head injury in children is not well understood. The aim of this study was to assess PECARN compliance at a pediatric trauma center. The secondary aim was to determine whether children with indeterminate history of loss of consciousness (LOC) are at greater risk for clinically important traumatic brain injury (ciTBI) than those with no LOC. MATERIALS AND METHODS: We identified children aged 0-17 y who presented <24 h after minor head injury with Glasgow Coma Scale ≥14 in our institutional trauma registry. Predictor variables for ciTBI (TBI resulting in admission ≥2 nights, intubation ≥24 h, neurosurgery, or death) were reviewed. Simple and multivariate logistic regressions were performed to estimate the independent effects of demographic and clinical characteristics on the outcome of ciTBI. RESULTS: We included 739 children. Incidence of ciTBI was 5.4%. Only 5.6% did not undergo computed tomography (CT). PECARN compliance was 92.6% overall, but only 23.0% in those for whom CT was not indicated. Among those for whom either CT or observation was acceptable, 93.7% underwent CT. LOC history was indeterminate in 8.5%. On multivariate analysis, indeterminate LOC was not a risk factor for ciTBI. Vomiting and presence of occipital/parietal/temporal scalp hematoma were independent risk factors for ciTBI. CONCLUSIONS: CT is overutilized in pediatric trauma patients presenting to our institution after minor head injury when compared to PECARN criteria. Indeterminate LOC history was not a risk factor for ciTBI. Education of parents and clinicians regarding the risk to benefit ratio of CT in trauma patients with minor head injury is needed.

Neural correlates of face perception modeled with a convolutional recurrent neural network.

Objective.Event-related potential (ERP) sensitivity to faces is predominantly characterized by an N170 peak that has greater amplitude and shorter latency when elicited by human faces than images of other objects. We aimed to develop a computational model of visual ERP generation to study this phenomenon which consisted of a three-dimensional convolutional neural network (CNN) connected to a recurrent neural network (RNN).Approach.The CNN provided image representation learning, complimenting sequence learning of the RNN for modeling visually-evoked potentials. We used open-access data from ERP Compendium of Open Resources and Experiments (40 subjects) to develop the model, generated synthetic images for simulating experiments with a generative adversarial network, then collected additional data (16 subjects) to validate predictions of these simulations. For modeling, visual stimuli presented during ERP experiments were represented as sequences of images (time x pixels). These were provided as inputs to the model. By filtering and pooling over spatial dimensions, the CNN transformed these inputs into sequences of vectors that were passed to the RNN. The ERP waveforms evoked by visual stimuli were provided to the RNN as labels for supervised learning. The whole model was trained end-to-end using data from the open-access dataset to reproduce ERP waveforms evoked by visual events.Main results.Cross-validation model outputs strongly correlated with open-access (r= 0.98) and validation study data (r= 0.78). Open-access and validation study data correlated similarly (r= 0.81). Some aspects of model behavior were consistent with neural recordings while others were not, suggesting promising albeit limited capacity for modeling the neurophysiology of face-sensitive ERP generation.Significance.The approach developed in this work is potentially of significant value for visual neuroscience research, where it may be adapted for multiple contexts to study computational relationships between visual stimuli and evoked neural activity.