The Application of Machine Learning to Identify Large Animal Blast Exposure Thresholds.

INTRODUCTION: The Office of Naval Research sponsored the Blast Load Assessment Sense and Test program to develop a rapid, in-field solution that could be used by team leaders, commanders, and medical personnel to make science-based stand-down decisions for service members exposed to blast overpressure. Toward this goal, the authors propose an ensemble approach based on machine learning (ML) methods to derive a threshold surface for potential neurological deficits that encompasses the intensity of the blast events, the number of exposures, and the period over which the exposures occurred. Because of collection challenges presented by human subjects, the authors utilized data representing a comprehensive set of measures, including structural, behavioral, and cellular changes, from preclinical large animal studies on minipig models. This article describes the development process used to procure the resulting methodology from these studies. METHODS AND MATERIALS: Using an ensemble of ML methods applied to experimental data obtained from 71 Yucatan minipigs, the relationship between blast exposure and neurological deficits was delineated. Despite a relatively small sample size, ML methods with k-fold cross-validation (with k = 5) were justified because of the complexity of the dataset reflecting numerous nonlinear relationships between cellular, structural, and behavioral markers. Based on the physiological responses and environmental measures collected during the large animal study, two models were developed to investigate the relationship between multiple outcome measures and exposure to blast. The histological features model was trained on single-exposure animal data to predict a binary injury response (injured or not) using histological features. The environmental features model related the observed behavioral changes to the environmental parameters collected. RESULTS: The histological features model predicted a binary injury outcome from cellular and physiological measurements. Features identified in developing this classification model showed some level of correlation to observed behavioral changes, suggesting that glial activation inflammation and neurodegenerative responses occur even at the lowest levels of blast exposures tested. The results of the environmental features model, which estimated injury risk from environmental blast exposure characteristics, suggested that the observed changes are not just a function of impulse but an average dynamic impulse rate. Noticeable behavioral deficits were observed at loading rates of 100 kPa (impulse/positive duration) or peak pressures of 300-350 kPa, with an approximate positive phase duration of 3.4 ms for single exposure. Based on this analysis, a 3D threshold surface was developed to characterize the potential risk of neurological deficits. CONCLUSIONS: The ensemble approach facilitated the identification of a pattern of changes across multiple variables to predict the occurrence of changes in brain function. Many changes observed after blast exposure were subtle, making them difficult to measure in human subjects. ML methodologies applied to minipig data demonstrated the value of these techniques in analyzing complex datasets to complement human studies. Importantly, the threshold surface supports the development of science-based blast exposure guidelines.

Development of a Minipig Model of BINT From Blast Exposure Using a Repeatable Mobile Shock Expansion Tube.

INTRODUCTION: The Office of Naval Research (ONR) sponsored the Blast Load Assessment Sense and Test (BLAST) program to provide an approach to operationally relevant monitoring and analysis of blast exposure for optimization of service member performance and health. Of critical importance in this effort was the development of a standardized methodology for preclinical large animal studies that can reliably produce outcome measures that cannot be measured in human studies to support science-based guidelines. The primary advantage of this approach is that, because animal studies report physiological measures that correlate with human neuropathology, these data can be used to evaluate potential risks to service members by accounting for the anatomical and physiological differences between humans and large animal models. This article describes the methodology used to generate a comprehensive outcome measure dataset correlated with controlled blast exposure. METHODS AND MATERIALS: To quantify outcomes associated with a single exposure to blast, 23 age- and weight-matched Yucatan minipigs were exposed to a single blast event generated by a large-bore, compressed gas shock tube. The peak pressure ranged from 280 to 525 kPa. After a post-exposure 72-hour observation period, the physiological response was quantified using a comprehensive set of neurological outcome measures that included neuroimaging, histology, and behavioral measures. Responses of the blast-exposed animals were compared to the sham-treated cohort to identify statistically significant and physiologically relevant differences between the two groups. RESULTS: Following a single exposure, the minipigs were assessed for structural, behavioral, and cellular changes for 3 days after exposure. The following neurological changes were observed: Structural-Using Diffusion Tensor Imaging, a statistically significant decrement (P < .001) in Fractional Anisotropy across the entire volume of the brain was observed when comparing the exposed group to the sham group. This finding indicates that alterations in brain tissue following exposure are not focused at a single location but instead a diffuse brain volume that can only be observed through a systematic examination of the neurological tissue. Cellular-The histopathology results from several large white matter tract locations showed varied cellular responses from six different stains. Using standard statistical methods, results from stains such as Fluoro-Jade C and cluster of differentiation 68 in the hippocampus showed significantly higher levels of neurodegeneration and increased microglia/macrophage activation in blast-exposed subjects. However, other stains also indicated increased response, demonstrating the need for multivariate analysis with a larger dataset. Behavioral-The behavior changes observed were typically transient; the animals' behavior returned to near baseline levels after a relatively short recovery period. Despite behavioral recovery, the presence of active neurodegenerative and inflammatory responses remained. CONCLUSIONS: The results of this study demonstrate that (1) a shock tube provides an effective tool for generating repeatable exposures in large animals and (2) exposure to blast overpressure can be correlated using a combination of imaging, behavioral, and histological analyses. This research demonstrates the importance of using multiple physiological indicators to track blast-induced changes in minipigs. The methodology and findings from this effort were central to developing machine-learning models to inform the development of blast exposure guidelines.

Transfer Function for Relative Blast Overpressure Through Porcine and Human Skulls In Situ.

INTRODUCTION: The overarching objective of the Office of Naval Research sponsored Blast Load Assessment Sense and Test (BLAST) program was to quantify neurofunctional risk from repeated blast exposure. However, human studies have limitations in data collection that can only be addressed by animal models. To utilize a large animal model in this work, researchers developed an approach for scaling blast exposure data from animal to human-equivalent loading. For this study, energy interacting with the brain tissue was selected as a translation metric because of the hypothesized association between observed neurological changes and energy transmitted through the skull. This article describes the methodology used to derive an energy-based transfer function capable of serving as a global correspondence rule for primary blast injury exposure, allowing researchers to derive human-appropriate thresholds from animal data. METHODS AND MATERIALS: To generate data for the development of the transfer functions, three disarticulated cadaveric Yucatan minipigs and three postmortem human surrogate heads were exposed to blast overpressure using a large bore, compressed-gas shock tube. Pressure gauges in the free field, on the skull surface, and pressure probes within the brain cavity filled with Sylgard silicone gel recorded the pressure propagation through the skull of each specimen. The frequency components of the freefield and brain cavity measurements from the pig and human surrogates were interrogated in the frequency domain. Doing so quantifies the differences in the amount of energy, in each frequency band, transmitted through both the porcine and the human skull, and the transfer function was calculated to quantify those differences. RESULTS: Nonlinear energy transmission was observed for both the porcine and human skulls, indicating that linear scaling would not be appropriate for developing porcine to human transfer functions. This study demonstrated similar responses between species with little to no attenuation at frequencies below 30 Hz. The phase of the pressure transmission to the brain is also similar for both species up to approximately 10 kHz. There were two notable differences between the porcine and human surrogates. First, in the 40-100 Hz range, human subjects have approximately 8 dB more pressure transmitted through the skull relative to porcine subjects. Second, in the 1-10 kHz range, human subjects have up to 10 dB more pressure transmitted into the brain (10 dB more attenuation) relative to the porcine subjects. CONCLUSIONS: The fundamental goal of this study was to develop pig-to-human transfer functions to allow researchers to interpret data collected from large animal studies and aid in deriving risk functions for repeated blast exposures. Similarities in porcine and human brain physiology make the minipig experimental model an excellent candidate for blast research. However, differences in the skull geometry have historically made the interpretation of animal data difficult for the purposes of characterizing potential neurological risk in humans. Human equivalent loading conditions are critical so that the thresholds are not over- or underpredicted due to differences in porcine skull geometry. This research provides a solution to this challenge, providing a robust methodology for interpreting animal data for blast research.

Evaluation of a Field-Ready Neurofunctional Assessment Tool for Use in a Military Environment.

INTRODUCTION: The Office of Naval Research sponsored the Blast Load Assessment Sense and Test (BLAST) program to develop a rapid, in-field solution that could be used by team leaders, commanders, and medical personnel to provide a standardized approach to operationally relevant monitoring and analysis of service members exposed to single or repeated low-level blast. A critical piece of the BLAST team's solution was the development of the Brain Gauge technology which includes a cognitive assessment device that measures neurofunctional changes by testing sensory perceptions and a suite of mathematical algorithms that analyze the results of the test. The most recent versions of the technology are easily portable; the device is in the size and shape of a computer mouse. Tests can be administered in a matter of minutes and do not require oversight by a clinician, making Brain Gauge an excellent choice for field use. This paper describes the theoretical underpinnings and performance of a fieldable Brain Gauge technology for use with military populations. MATERIALS AND METHODS: The methods used by the Brain Gauge have been documented in over 80 peer-reviewed publications. These papers are reviewed, and the utility of the Brain Gauge is described in terms of those publications. RESULTS: The Brain Gauge has been demonstrated to be an effective tool for assessing blast-induced neurotrauma and tracking its recovery. Additionally, the method parallels neurophysiological findings of animal models which provide insight into the sensitivity of specific metrics to mechanisms of information processing. CONCLUSIONS: The overall objective of the work was to provide an efficient tool, or tools, that can be effectively used for (1) determining stand-down criteria when critical levels of blast exposure have been reached and (2) tracking the brain health history until return-to-duty status is achieved. Neurofunctional outcome measures will provide the scientific link between blast sensors and the impact of blast on biological health. This calibration process is strengthened with outcome measures that have a biological basis that are paralleled in animal models. The integrative approach that utilizes the Brain Gauge technology will provide a significant advance for assessing the impact of blast exposure and support rapid, science-based decision-making that will ensure mission success and promote the protection of brain health in service members.

Development of a Fast-Running Algorithm to Approximate Incident Blast Parameters Using Body-Mounted Sensor Measurements.

INTRODUCTION: The Office of Naval Research sponsored the Blast Load Assessment-Sense and Test program to develop a rapid, in-field solution that could be used by team leaders, commanders, and medical personnel to make science-based stand-down decisions for service members exposed to blast overpressure. However, a critical challenge to this goal was the reliable interpretation of surface pressure data collected by body-worn blast sensors in both combat and combat training scenarios. Without an appropriate standardized metric, exposures from different blast events cannot be compared and accumulated in a service member's unique blast exposure profile. In response to these challenges, we developed the Fast Automated Signal Transformation, or FAST, algorithm to automate the processing of large amounts of pressure-time data collected by blast sensors and provide a rapid, reliable approximation of the incident blast parameters without user intervention. This paper describes the performance of the FAST algorithms developed to approximate incident blast metrics from high-explosive sources using only data from body-mounted blast sensors. METHODS AND MATERIALS: Incident pressure was chosen as the standardized output metric because it provides a physiologically relevant estimate of the exposure to blast that can be compared across multiple events. In addition, incident pressure serves as an ideal metric because it is not directionally dependent or affected by the orientation of the operator. The FAST algorithms also preprocess data and automatically flag "not real" traces that might not be from blasts events (false positives). Elimination of any "not real" blast waveforms is essential to avoid skewing the results of subsequent analyses. To evaluate the performance of the FAST algorithms, the FAST results were compared to (1) experimentally measured pressures and (2) results from high-fidelity numerical simulations for three representative real-world events. RESULTS: The FAST results were in good agreement with both experimental data and high-fidelity simulations for the three case studies analyzed. The first case study evaluated the performance of FAST with respect to body shielding. The predicted incident pressure by FAST for a surrogate facing the charge, side on to charge, and facing away from the charge was examined. The second case study evaluated the performance of FAST with respect to an irregular charge compared to both pressure probes and results from high-fidelity simulations. The third case study demonstrated the utility of FAST for detonations inside structures where reflections from nearby surfaces can significantly alter the incident pressure. Overall, FAST predictions accounted for the reflections, providing a pressure estimate typically within 20% of the anticipated value. CONCLUSIONS: This paper presents a standardized approach-the FAST algorithms-to analyze body-mounted blast sensor data. FAST algorithms account for the effects of shock interactions with the body to produce an estimate of incident blast conditions, allowing for direct comparison of individual exposure from different blast events. The continuing development of FAST algorithms will include heavy weapons, providing a singular capability to rapidly interpret body-worn sensor data, and provide standard output for analysis of an individual's unique blast exposure profile.

When physics meets biology: low and high-velocity penetration, blunt impact, and blast injuries to the brain.

The incidence of traumatic brain injuries (TBI) in the US has reached epidemic proportions with well over 2 million new cases reported each year. TBI can occur in both civilians and warfighters, with head injuries occurring in both combat and non-combat situations from a variety of threats, including ballistic penetration, acceleration, blunt impact, and blast. Most generally, TBI is a condition in which physical loads exceed the capacity of brain tissues to absorb without injury. More specifically, TBI results when sufficient external force is applied to the head and is subsequently converted into stresses that must be absorbed or redirected by protective equipment. If the stresses are not sufficiently absorbed or redirected, they will lead to damage of extracranial soft tissue and the skull. Complex interactions and kinematics of the head, neck and jaw cause strains within the brain tissue, resulting in structural, anatomical damage that is characteristic of the inciting insult. This mechanical trauma then initiates a neuro-chemical cascade that leads to the functional consequences of TBI, such as cognitive impairment. To fully understand the mechanisms by which TBI occurs, it is critically important to understand the effects of the loading environments created by these threats. In the following, a review is made of the pertinent complex loading conditions and how these loads cause injury. Also discussed are injury thresholds and gaps in knowledge, both of which are needed to design improved protective systems.

Ubiquitin carboxy-terminal hydrolase-l1 as a serum neurotrauma biomarker for exposure to occupational low-level blast.

Repeated exposure to low-level blast is a characteristic of a few select occupations and there is concern that such occupational exposures present risk for traumatic brain injury. These occupations include specialized military and law enforcement units that employ controlled detonation of explosive charges for the purpose of tactical entry into secured structures. The concern for negative effects from blast exposure is based on rates of operator self-reported headache, sleep disturbance, working memory impairment, and other concussion-like symptoms. A challenge in research on this topic has been the need for improved assessment tools to empirically evaluate the risk associated with repeated exposure to blast overpressure levels commonly considered to be too low in magnitude to cause acute injury. Evaluation of serum-based neurotrauma biomarkers provides an objective measure that is logistically feasible for use in field training environments. Among candidate biomarkers, ubiquitin carboxy-terminal hydrolase-L1 (UCH-L1) has some empirical support and was evaluated in this study. We used daily blood draws to examine acute change in UCH-L1 among 108 healthy military personnel who were exposed to repeated low-level blast across a 2-week period. These research volunteers also wore pressure sensors to record blast exposures, wrist actigraphs to monitor sleep patterns, and completed daily behavioral assessments of symptomology, postural stability, and neurocognitive function. UCH-L1 levels were elevated as a function of participating in the 2-week training with explosives, but the correlation of UCH-L1 elevation and blast magnitude was weak and inconsistent. Also, UCH-L1 elevations did not correlate with deficits in behavioral measures. These results provide some support for including UCH-L1 as a measure of central nervous system effects from exposure to low-level blast. However, the weak relation observed suggests that additional indicators of blast effect are needed.

Marine Corps Breacher Training Study: auditory and vestibular findings.

This article presents an overview of a contemporary research protocol conducted at the Marine Corps Weapons Training Battalion, Quantico, VA. The study was a comprehensive collaborative research initiative that evaluated a variety of environmental, auditory, and vestibular factors among Marines enrolled in the Breacher Training Course. The length of each course is 2 weeks and involves multiple exposures to blast overpressure and physical shock from ingress strategies used during the training. Observational data were collected pretraining, during training, and posttraining between September and June 2007. There was no change in the way the Marines conducted their training, and all data were collected based on the actual training scenario. The primary objective of this research protocol was to determine if Marines in the Breacher Training Course were at risk of injury during standard training practices. The principal conclusions were that hearing loss was statistically and clinically significant whereas the vestibular findings were overall unremarkable.

Head injury as a PTSD predictor among Oklahoma City bombing survivors.

BACKGROUND: The aim of the Oklahoma City (OKC) bombing retrospective review was to investigate the relationship between physical injury, environmental contributors, and psychiatric disorders such as posttraumatic stress disorder (PTSD) in an event-based, matched design study focused on injury. METHODS: The 182 selected participants were a random subset of the 1,092 direct survivors from the OKC bombing. Only 124 of these 182 cases had a full complement of medical/clinical data in the OKC database. These 124 cases were assessed to explore relationships among PTSD diagnoses, levels of blast exposure, and physical injuries. Associations among variables were statistically tested using contingency analysis and logistic regression. RESULTS: Comparison of the PTSD cases to symptoms/diagnoses reported in the medical records reveals a statistically significant association between PTSD and head/brain injuries associated with head acceleration. PTSD was not highly correlated with other injuries. Although blast pressure and impulse were highly correlated with head injuries, the correlation with PTSD was not statistically significant. Thus, a correlation between blast pressure and PTSD may exist, but higher fidelity pressure calculations are required to elucidate this potential relationship. CONCLUSIONS: This study provides clear evidence that head injury is associated with subsequent PTSD, giving caregivers' information on what physical injuries may suggest the development of psychologic disorders to aid them in developing a profile for the identification of future survivors of terrorist attacks and Warfighters with brain injuries and potential PTSD.

Relationship between temporomandibular joint dynamics and mouthguards: feasibility of a test method.

A test system was developed establishing the feasibility of collecting biomechanical data as they relate to the use of mouthguards. Previous experimental studies have examined the physical and mechanical properties of mouthguard materials. This information has been used as a guide for establishing material standards and specifications for the fabrication of mouthguards, but it lacks the key biomechanical parameters required for a thorough mouthguard evaluation. The current study was designed to assess whether the impact force, condylar deflection, and strain superior to the temporomandibular joint region could be measured. A drop test was conducted on a cadaveric specimen to simulate loading at the chin point. To measure the force of impact, an accelerometer was attached to an impactor of known mass. High-speed biplanar (1000 frames per second) radiographs were used to determine condylar displacement. Radio-opaque markers were inserted into the bone at predetermined locations. Total displacement of these markers was determined in reference to anatomical landmarks. Strain gauges were attached to the mandible and skull to monitor the effects of the condyle impacting the base of the skull. Based on the data collected, forces were calculated by determining the product of the time-based acceleration and known mass. A measurable change in force between the mouthguards and the control (no mouthguard) was demonstrated. The average condylar displacement was successfully measured and indicated as an increase in total deflection for impacts conducted with mouthguards. Quantifiable strain was measured in the region above the mandibular fossa with and without the insertion of a mouthguard at all impact conditions. However, it was determined that additional gauges would provide critical data. Key biomechanical parameters for chin-point impacts were determined in the current study. The technique demonstrated that both displacement within the mandibular fossa and loading of the condyles occur during the impact event. Although the current study established a technique that can be used to examine the relationship between mouthguards and jaw-joint injuries, the role, if any, mouthguards play in the reduction of injuries cannot be established until a thorough analysis is completed.