RESUMEN

We employed wearable multimodal sensing (heart rate and triaxial accelerometry) with machine learning to enable early prediction of impending exertional heat stroke (EHS). US Army Rangers and Combat Engineers (N = 2,102) were instrumented while participating in rigorous 7-mile and 12-mile loaded rucksack timed marches. There were three EHS cases, and data from 478 Rangers were analyzed for model building and controls. The data-driven machine learning approach incorporated estimates of physiological strain (heart rate) and physical stress (estimated metabolic rate) trajectories, followed by reconstruction to obtain compressed representations which then fed into anomaly detection for EHS prediction. Impending EHS was predicted from 33 to 69 min before collapse. These findings demonstrate that low dimensional physiological stress to strain patterns with machine learning anomaly detection enables early prediction of impending EHS which will allow interventions that minimize or avoid pathophysiological sequelae. We describe how our approach can be expanded to other physical activities and enhanced with novel sensors.

Asunto(s)

Asunto(s)

RESUMEN

INTRODUCTION: Military personnel during training and military operations are exposed to a large number of repeated exposures to low-level blast overpressure from a variety of sources. These exposures rarely produce a concussion, but anecdotal evidence from soldiers indicates that it can still cause transient neurological effects. Impulsive acoustic sources, such as the ones encountered during military training, are characterized by a broadband energy distribution with resulting pressure measurements that exhibit frequency components well within the infrasound range. This infrasound can couple directly with the human body and in this way alter or influence physiological processes up to inducing concussion-like symptoms. MATERIALS AND METHODS: This study explores the presence of infrasound energy in measured acoustic signals collected during grenade training at Ft. Benning, GA. Acoustic data from traditional microphones and specialized infrasound microphones were collected during one training session and time and time-frequency analysis was performed to highlight the frequency content of the signals. RESULTS: The analysis of the collected measurements indicates peak SPLs between 140 and 160 dB during explosions corresponding to the shockwave. Also, high-intensity infrasound was observed during grenade explosions with significant energy in the infrasound range and in particular below 3 Hz. This energy appears in the form of three distinct tones at frequencies of 1.987, 2.296, and 2.528 Hz that are present only for the duration of the blast wave. CONCLUSIONS: The results presented in this article suggest that reported symptoms from military personnel exposed to repeated low-level blast may also be because of acoustic loading. Therefore, to take into account these findings, future studies aimed at characterizing the effects of repeated low-level blast exposure should consider including acoustic measurements in their investigations.

Asunto(s)

RESUMEN

The field of brain connectomics develops our understanding of the brain's intrinsic organization by characterizing trends in spontaneous brain activity. Linear correlations in spontaneous blood-oxygen level dependent functional magnetic resonance imaging (BOLD-fMRI) fluctuations are often used as measures of functional connectivity (FC), that is, as a quantity describing how similarly two brain regions behave over time. Given the natural spectral scaling of BOLD-fMRI signals, it may be useful to represent BOLD-fMRI as multiple processes occurring over multiple scales. The wavelet domain presents a transform space well suited to the examination of multiscale systems as the wavelet basis set is constructed from a self-similar rescaling of a time and frequency delimited kernel. In the present study, we utilize wavelet transforms to examine fluctuations in whole-brain BOLD-fMRI connectivity as a function of wavelet spectral scale in a sample (N = 31) of resting healthy human volunteers. Information theoretic criteria measure relatedness between spectrally-delimited FC graphs. Voxelwise comparisons of between-spectra graph structures illustrate the development of preferential functional networks across spectral bands.

RESUMEN

Measures of whole-brain activity, from techniques such as functional Magnetic Resonance Imaging, provide a means to observe the brain's dynamical operations. However, interpretation of whole-brain dynamics has been stymied by the inherently high-dimensional structure of brain activity. The present research addresses this challenge through a series of scale transformations in the spectral, spatial, and relational domains. Instantaneous multispectral dynamics are first developed from input data via a wavelet filter bank. Voxel-level signals are then projected onto a representative set of spatially independent components. The correlation distance over the instantaneous wavelet-ICA state vectors is a graph that may be embedded onto a lower-dimensional space to assist the interpretation of state-space dynamics. Applying this procedure to a large sample of resting-state and task-active data (acquired through the Human Connectome Project), we segment the empirical state space into a continuum of stimulus-dependent brain states. Upon observing the local neighborhood of brain-states adopted subsequent to each stimulus, we may conclude that resting brain activity includes brain states that are, at times, similar to those adopted during tasks, but that are at other times distinct from task-active brain states. As task-active brain states often populate a local neighborhood, back-projection of segments of the dynamical state space onto the brain's surface reveals the patterns of brain activity that support many experimentally-defined states.

Asunto(s)

RESUMEN

While functional connectivity has typically been calculated over the entire length of the scan (5-10min), interest has been growing in dynamic analysis methods that can detect changes in connectivity on the order of cognitive processes (seconds). Previous work with sliding window correlation has shown that changes in functional connectivity can be observed on these time scales in the awake human and in anesthetized animals. This exciting advance creates a need for improved approaches to characterize dynamic functional networks in the brain. Previous studies were performed using sliding window analysis on regions of interest defined based on anatomy or obtained from traditional steady-state analysis methods. The parcellation of the brain may therefore be suboptimal, and the characteristics of the time-varying connectivity between regions are dependent upon the length of the sliding window chosen. This manuscript describes an algorithm based on wavelet decomposition that allows data-driven clustering of voxels into functional regions based on temporal and spectral properties. Previous work has shown that different networks have characteristic frequency fingerprints, and the use of wavelets ensures that both the frequency and the timing of the BOLD fluctuations are considered during the clustering process. The method was applied to resting state data acquired from anesthetized rats, and the resulting clusters agreed well with known anatomical areas. Clusters were highly reproducible across subjects. Wavelet cross-correlation values between clusters from a single scan were significantly higher than the values from randomly matched clusters that shared no temporal information, indicating that wavelet-based analysis is sensitive to the relationship between areas.

Asunto(s)

RESUMEN

In recent U.S. military experience, widespread exposure to improvised explosive devices has been implicated in noticeable changes in the incidence of brain injuries inversely related to reduced mortality--thought to be the unintended consequence of increase in exposure to blast wave effects--secondary to improved vital organ protection, improved personal protective equipment. Subsequently, there is a growing need for the development and fielding of fully integrated sensor systems capable of both capturing dynamic effects (i.e., "blast") on the battlefield--providing critical information for researchers, while providing value to the medical community and leaders--for development of pre-emptive measures and policies. Obtaining accurate and useful data remains a significant challenge with a need for sensors which feed systems that provide accurate interpretation of dynamic events and lend to an enhanced understanding of their significance to the individual. This article describes lessons learned from a data analysis perspective of a collaborative effort led by a team formed at Georgia Tech Research Institute to develop a "sensor agnostic" system that demonstrates full integration across variant platforms/systems. The system is designed to allow digital and analog time/frequency data synchronization and analysis, which facilitated the development of complex multimodal modeling/algorithms.

Asunto(s)

RESUMEN

Spurned by the increasing concern and consciousness of traumatic brain injuries in deployed U.S. service members, the U.S. Army Rapid Equipping Force sought help from the Georgia Tech Research Institute to rapidly develop and deploy a system capable of gathering relevant soldier-centric data-the Integrated Blast Effects Sensor Suite. To meet aggressive program milestones and requirements, Georgia Tech Research Institute engaged in rapid systems engineering efforts focused on leveraging iterative development and test methodologies. Ultimately, an integrated system of systems composed of vehicle systems, soldier-worn headset and torso systems, and data retrieval systems was deployed to troops in Afghanistan for an operational assessment. The Integrated Blast Effects Sensor Suite development process and parallel efforts investigating injury dosimetry methodologies have yielded unique findings and lessons learned, which should be incorporated into future evolutions of similar systems.

Asunto(s)