Sunday, August 01, 2021

 

Trauma Informed Care can help break the cycle of violence

Multidisciplinary American College of Surgeons ISAVE group proposes strategies for trauma centers to address root causes of violence

Peer-Reviewed Publication

AMERICAN COLLEGE OF SURGEONS

Author video 

VIDEO: ROCHELLE A. DICKER, MD, FACS, DISCUSSES HOW TRAUMA CENTERS CAN HELP ADDRESS ROOT CAUSES OF VIOLENCE, IMPROVE HEALTH, AND REDUCE INEQUITIES IN MARGINALIZED COMMUNITIES. view more 

CREDIT: AMERICAN COLLEGE OF SURGEONS

Key takeaways

  • Trauma Informed Care accounts for both the mental and physical aspects of trauma.
  • Trauma centers and hospitals should invest directly in at-risk communities to create opportunities for financial and educational inclusion.
  • Engaging at-risk communities can help address structural racism and social determinants of health and create a solutions-based narrative.

CHICAGO (July 30, 2021): Trauma surgeons are often the first point of contact with the health care system for victims of violence. However, their role can extend beyond caring for a patient’s physical injuries. Trauma centers can help address root causes of violence, improve health, and reduce inequities in marginalized communities, according to the American College of Surgeons (ACS) Improving Social Determinants to Attenuate Violence (ISAVE) workgroup. The ISAVE workgroup published four strategies to help break the cycle of violence in an article published on the Journal of the American College of Surgeons website in advance of print.

“Violence, in and of itself, is very much the end result of social determinants of health, structural racism, and structural barriers in our country that have existed for a long time,” said Rochelle A. Dicker, MD, FACS, of the division of trauma and critical care, University of California at Los Angeles Geffen School of Medicine. “The strategies we propose are very action-oriented. Trauma is not just about the physical injury but has a broader definition. We need to be more comprehensive and aware of that as we treat our patients.”

Four strategies to address the root causes of violence

The ISAVE workgroup proposes four strategies to improve health and health care for marginalized communities that are disproportionally impacted by violence:

  • Development and Implementation of Trauma Informed Care in All Trauma Centers
  • Integrating Social Care into Trauma Care
  • The Trauma Center’s Role in Investing in At-Risk Communities
  • Advocacy

These strategies form ISAVE’s vision of the future of care for victims of violence. These efforts extend beyond the confines of trauma centers, reaching into communities plagued by this violence epidemic.

A key feature of the ISAVE strategies is the Trauma Informed Care (TIC) curriculum. The authors note that trauma has traditionally had two definitions: 

  1. From the mental health perspective, a deeply distressing and disturbing experience 
  2. From the perspective of trauma surgery and emergency medical services, an acute physical injury

The authors note that having two different definitions of trauma can lead to a fragmentation of care. The TIC curriculum takes into account the full scope of trauma and can “foster a sense of empowerment, autonomy, and partnership in the injured person to help patients thrive, not just survive.” 

Focusing on at-risk communities

The authors address violence and the social determinants of health with a broad lens, noting the risk of perpetuating a cycle of inequity, disparity, and inequality if underlying causes of death and ill health are not addressed. The authors suggest a strategy to invest directly in at-risk communities to treat patients with a full scope of understanding the underlying factors.

“It is important that people have access to trauma centers, but the other piece is hospitals investing in their communities,” Dr. Dicker said. “For example, putting in place vocational training programs so that the community is part of the employment process in a hospital itself. Also, whether the hospital uses local vendors for food; that’s an investment in the local community. Investment truly is the ability to put dollars into the communities that are in such great need.”

Health and wealth are inextricably tied to one another, the authors note. “Black and Brown communities suffer heavily from a racial wealth gap relative to white communities, although rural white Americans are also deeply impacted by this gap and share a common lack of access to mechanisms to build financial security,” they write. “Creating opportunities for financial and educational inclusion may not be seen on the surface as a health-related matter but, in fact, it is at its core.”

Advocacy is the overarching theme that informs the strategies proposed by ISAVE. The authors note that it is an intrinsic duty for trauma center personnel to use advocacy to address the social determinants of health that lead to violence. Specific policy suggestions include engaging hospital and health system administrators to leverage the Affordable Care Act’s Community Health Needs Assessment to encourage hospitals to engage in addressing poverty and unemployment.

“Physical trauma leads to psychological trauma and psychological trauma predisposes to physical trauma. Optimally addressing one, requires addressing the other,” the authors conclude. “Although complex, effective interventions for violence are not as complex as those required to combat a novel corona virus pandemic, and as the COVID-19 pandemic has plainly demonstrated, we are all in this together. What affects one of us, affects all of us.”

Infographic 

CAPTION

Four ways for trauma centers to address root causes of violence.

CREDIT

American College of Surgeons

The ISAVE workgroup was established in 2019 by the ACS Committee on Trauma (COT) and  first outlined steps the medical community must take to understand and address the root causes of firearm violence at a panel presentation during the 2020 ACS Clinical Congress virtual. The ACS COT has been working to prevent firearm related injury, death, and disability by working together to address the root causes of violence and simultaneously making firearm ownership as safe as possible. Learn more about the ACS COT’s efforts that focus on treating firearm violence as a public health problem.

Article coauthors with Dr. Dicker are Arielle Thomas, MD, MPH; Eileen M. Bulger, MD, FACS; Ronald M. Stewart, MD, FACS; Stephanie Bonne, MD, FACS; Tracy A. Dechert, MD, FACS; Randi Smith, MD, FACS; Altovise Love-Craighead, MS; Fatimah Dreier, MA; Meera Kotagal, MD, FACS; Tamara Kozyckyj, MPH; and Holly Michaels, MPH.

The article authors have no relevant financial relationships to disclose.

“FACS” designates that a surgeon is a Fellow of the American College of Surgeons.

Citation: Strategies for Trauma Centers to Address the Root Causes of Violence: Recommendations from the Improving Social Determinants to Attenuate Violence (ISAVE) Workgroup of the American College of Surgeons Committee on Trauma. Journal of the American College of Surgeons. DOI: doi.org/10.1016/j.jamcollsurg.2021.06.016.

 

About the American College of Surgeons
The American College of Surgeons is a scientific and educational organization of surgeons that was founded in 1913 to raise the standards of surgical practice and improve the quality of care for all surgical patients. The College is dedicated to the ethical and competent practice of surgery. Its achievements have significantly influenced the course of scientific surgery in America and have established it as an important advocate for all surgical patients. The College has more than 82,000 members and is the largest organization of surgeons in the world. For more information, visit www.facs.org.

 

Army award-winning research to transform Soldier-robot communication

Grant and Award Announcement

U.S. ARMY RESEARCH LABORAT

Army award-winning research to transform Soldier-robot communication 

IMAGE: ARMY RESEARCHERS DEVELOP GROUND-BREAKING TECHNOLOGY THAT WILL ENHANCE HOW SOLDIERS AND ROBOTS COMMUNICATE AND CARRY OUT TASKS IN TACTICAL ENVIRONMENTS. view more 

CREDIT: NEIL ADAMS

PHILADELPHIA, Md. -- Army researchers developed ground-breaking technology that will enhance how Soldiers and robots communicate and carry out tasks in tactical environments.

This research sets out to develop a natural language understanding, or NLU, pipeline for robots that would be easily ported over to any computational system or agent and incrementally tames the variation that we see in natural language, said Army researcher Dr. Claire Bonial from the U.S. Army Combat Capabilities Development Command, known as DEVCOM, Army Research Laboratory.

This means that regardless of how a Soldier chooses to express him or herself to the robot, the underlying intent of that language is understood and can be acted on, given both the current conversational and environmental or situational context.

To do this, the NLU pipeline first automatically parses the input language into Abstract Meaning Representation, or AMR, which captures the basic meaning of the content of the language, Bonial said. It then converts and augments the AMR into Dialogue-AMR, which captures additional elements of meaning needed for two-way human robot dialogue in particular, such as what the person is trying to do with the utterance in the conversational context, for example give a command, ask a question, state a fact about the environment, etc.

“This is unique in comparison to other NLU components within dialogue systems, many of which forego any kind of semantic representation in favor of a deep-learning approach,” Bonial said.

This research was presented at the 14th International Conference on Computational Semantics, or IWCS 2021, where it received the Outstanding Paper Award.

The award citation noted that “The authors are not afraid of using old-fashined hand-written rules when they do the job, something which is lacking in much current work in NLP,“ and that “Anyone who wants to work on human-robot dialogue will want to see this first go at parsing in this new domain.”

“This award was incredibly gratifying for several reasons,” Bonial said. “First, this paper represents research efforts that were planted and have been growing since I was a doctoral student. I was part of the first group of researchers establishing what has become one of the most widely used semantic representations in natural language processing, AMR.”

Bonial started work with this group in 2010, and has been actively involved in refining and extending the representation ever since. Thus, this paper represents a body of research spanning over a decade for Bonial.

This includes work to represent language expressed through semi-idiomatic constructions, for example “the higher you fly, the harder you’ll fall!,” and most recently extending AMR so that it can better capture two-way dialogue, and specifically task-oriented, situated dialogue between people and robots, in an augmented version of the representation called Dialogue-AMR, she said.

Efforts to develop Dialogue-AMR started in 2018 with dialogue expert Dr. David Traum as part of the University Affiliated Research Center previously established between DEVCOM ARL and the Institute for Creative Technologies at the University of Southern California.

Dialogue-AMR draws upon ARL and ICT’s Bot Language research collaboration focused on robot dialogue systems, which was initiated by one of the IWCS paper’s co-authors, Dr. Clare Voss, in 2012.

Second, Bonial said, this paper reports on a critical step in the research trajectory: the researchers’ experiments to robustly and critically evaluate Dialogue-AMR as a computational semantic representation, as well as the NLU pipeline used to automatically obtain the correct Dialogue-AMR representation when given unconstrained natural language input.

These experiments were also done in collaboration with Traum of ICT, as well as an ARL student intern and recent graduate of Georgetown University, Mitchell Abrams. Abrams was recently selected as a Department of Defense Science, Mathematics, And Research For Transformation scholar, and will be coming back to the lab after completing his fully-funded doctoral program.

This evaluation is significant because the researchers evaluate in two problem domains: first, the domain of human-robot dialogue for collaborative search and navigation tasks, and second the domain of human-human dialogue in the virtual Minecraft gaming environment, where participants are collaboratively building blocks structures.

The Minecraft dialogue data that made this comparative evaluation possible was obtained from Dr. Martha Palmer of the University of Colorado, Boulder, and Dr. Julia Hockenmaier of the University of Illinois at Urbana-Champaign.

Evaluating in these two domains gets at a key question regarding the utility of such a representation and the NLU pipeline in general.

Bonial questioned how efficiently and with what accuracy the pipeline and representation can be applied in one problem domain, and then transferred and refined to a new problem domain. Or, in other words, how feasible is it for us to use this approach for communicating with a robot when that robot needs to tackle new problems and environments?

“Any Army application requires a system that can efficiently and flexibly act in dynamic circumstances,” Bonial said. “Our evaluation demonstrates that our NLU pipeline can obtain human-level performance in the first, human-robot dialogue domain, such that the output Dialogue-AMR representations agree with, or are similar to, human gold-standard representations at a rate similar to representations manually created by different humans.”

Further their evaluation demonstrates that with just a small amount of additional training data (several hours’ worth of annotation work amounting to about 200 additional training instances for the machine learning elements of the pipeline), the NLU pipeline obtains promising performance in the second domain of human-human dialogue in the Minecraft domain, she said.

The researchers noted that while the performance is somewhat lower than performance on the original human-robot dialogue domain, it is comparable or better than the performance of other automatic semantic parsers for other semantic representations and language domains.

“These promising results demonstrate that this NLU pipeline leverages a valid approach for communicating with robots in collaborative tasks across multiple domains,” Bonial said. “I am very excited for the promise of this research to provide transformational overmatch in our computational systems’ ability to understand the underlying meaning of Soldiers’ instructions, despite difference in their dialects, accents and other types of noise sure to arise in Army-relevant applications.”

In the research team’s next steps, they are connecting the output semantic representation with a system that grounds the pieces of the representation to both entities in the environments and the executable behaviors of the robot in joint work with Dr. Thomas Howard of the University of Rochester.

“We are optimistic that the deeper semantic representation will provide the structure needed for superior grounding of the language in both the conversational and physical environment such that robots can communicate and act more as teammates to Soldiers, as opposed to tools,” Bonial said.

Visit the laboratory's Media Center to discover more Army science and technology stories

 

Spatial relationship between damaged understory and felled trees in a shelterwood forest

Peer-Reviewed Publication

SHINSHU UNIVERSITY

image 1 

IMAGE: THE UNDERSTORY WILL NOT BE DAMAGED UNLESS IT IS HIT DIRECTLY, ESPECIALLY ON THE TRUNK. view more 

CREDIT: DAI OTSUKA, SHINSHU UNIVERSITY

The shelterwood forest system is a natural regeneration method of forest management that supplies the next generation of trees from overstory tree seeds without planting. This method lowers the cost of forest management by reducing the need for artificial reforestation through planting. This means that the understory trees must be preserved from felled trees during harvest.

However, protection of understory trees reduces harvesting efficiency, and thus increases the cost of logging. To evaluate whether the conservation of understory trees is commensurate with the increase in harvesting costs, it is necessary to quantitatively clarify the relationship between removing the overstory trees and the emergence pattern of the understory loss. A research group led by Dai Otsuka of Shinshu University's Faculty of Agriculture has proposed a model to measure such damage to the understory spatial distribution.

Researcher Otsuka states that the group was able to come to a simple but clear conclusion that, "felled trees should be worked on so they do not come into contact with conservation targets." The group counted the number of understory trees before and after final cutting, as well as the extent of damage to the trees per spatial grid. Geographic Information System was used to reproduce the felling direction and physical contact between the harvested trees and understory trees. Logistic regression was performed using the extracted frequencies of physical contact as explanatory variables and variables important for reproducing the spatial pattern of the damaged understory were selected.

This method of avoiding damage to the understory has a low barrier to entry for forest management. The research made clear that widely assumed ideas from the field are not wrong. Through a real damage model, forest owners can predict in advance potential losses for harvesting. This will be useful especially in natural renewal operations.

In upcoming research projects, Otsuka hopes to minimize damage to understory in areas targeted in this paper. He hopes to also clarify if natural renewal operations are cost-effective or disadvantageous compared to general clear-cutting, which requires the cost of artificial planting.

This study was supported by the Japan Society for the Promotion of Science Grant 15H04508 and 20H03023. 

For more information, please read Spatial relationship between damaged understory and felled trees during the final cutting in a shelterwood forest in the International Journal of Forest Engineering

CAPTION

The forest before harvest.

CREDIT

Dai Ostuka, Shinshu University


Disclaimer: AAAS an

 

SwRI scientists help identify water vapor in atmosphere of icy Jupiter moon


Ganymede’s atmospheric composition varies significantly on day, night sides

Peer-Reviewed Publication

SOUTHWEST RESEARCH INSTITUTE

Juno Ganymede flyby 

IMAGE: USING HUBBLE SPACE TELESCOPE DATASETS AND COMPARING THEM TO THE EXPECTED VALUES OF ATMOSPHERIC EMISSIONS, SOUTHWEST RESEARCH INSTITUTE SCIENTISTS PLAYED A CRUCIAL ROLE IN THIS DISCOVERY OF WATER VAPOR IN THE ATMOSPHERE OF JUPITER’S ICY MOON GANYMEDE, SHOWN HERE IN A RECENT IMAGE CAPTURED BY THE JUNO SPACECRAFT. view more 

CREDIT: NASA/JPL-CALTECH/SWRI/MSSS/KEVIN M. GILL

SAN ANTONIO — July 26, 2021 — Using spectral images from the Hubble Space Telescope (HST), a team of scientists led by Dr. Lorenz Roth of the KTH Royal Institute of Technology in Stockholm, Sweden, has determined that water vapor forms a large fraction of the atmosphere of Jupiter’s icy moon Ganymede. Southwest Research Institute scientists played a crucial role in this discovery, looking at the HST datasets and comparing them to the expected values of atmospheric emissions.

Ganymede’s atmosphere is produced by charged particle erosion and sublimation of its icy surface. Sublimation occurs when an ice changes directly into a gas without first turning into a liquid. Previous far-ultraviolet observations found both molecular oxygen (O2) and atomic oxygen (O) in the moon’s atmosphere but did not detect the water scientists had expected to find. The new observations find that H2O is more abundant than oxygen near the subsolar point, when the Sun is at its zenith, directly overhead, where the Sun's rays strike the planet most intensely.

“Sublimated water vapor at high noon on Ganymede, where the surface is relatively warm, is likely a key feature of the tenuous atmospheres of Jupiter’s icy moons,” said SwRI’s Dr. Kurt Retherford, a co-author of the Nature Astronomy paper describing this research. “As we prepare to launch NASA’s Ultraviolet Spectrograph (UVS) instrument, built and led by SwRI, aboard the European Space Agency’s (ESA’s) Jupiter Icy Moons Explorer (JUICE) mission next year, this new understanding of Ganymede’s atmosphere will let us better plan our observations and enhance our science return.”

Scientists expect that molecular oxygen is globally the most abundant constituent in Ganymede’s atmosphere, as it is gravitationally bound, stable and less likely to react with surface materials. The lighter products of the ice surface erosion, atomic hydrogen (H) and hydrogen gas (H2), escape quickly and are less abundant. Ganymede’s surface temperatures range from 80 Kelvin (-315 F) to perhaps as high as 150 K (-190 F), but water molecules only sublimate and fly off where it’s hotter than 110 K (-260 F) and get stuck frozen on colder surfaces, limiting the abundance of water elsewhere in the atmosphere. Atmospheric modeling suggests a dichotomy in the atmosphere between an H2O-dominated atmosphere near the warmer region where the Sun is overhead, and an O2-dominated atmosphere everywhere else.

“Showing that water vapor is a large fraction of the atmosphere of Ganymede — at least where the Sun is high — is a very timely result,” said SwRI’s Dr. Randy Gladstone, another co-author. “NASA’s Juno spacecraft is currently making close-up observations of Ganymede, including the emissions observed by HST, and these new results will be used to plan future observations with JUICE, which is designed to orbit Ganymede in 2033.”

“It’s interesting to think of an atmosphere that has a very different composition on its dayside relative to its nightside, with completely different processes driving the production of gases at different locations,” said Dr. Philippa Molyneux, a third SwRI co-author. “Imagine if Earth’s atmosphere worked that way, and how life might have evolved to adapt to that changing environment.”

###


For more information, see paper at DOI: 10.1038/s41550-021-01426-9, visit https://www.swri.org/planetary-science.

 

First detection of light from behind a black hole

Peer-Reviewed Publication

STANFORD UNIVERSITY

Wilkins illustration 

IMAGE: RESEARCHERS OBSERVED BRIGHT FLARES OF X-RAY EMISSIONS, PRODUCED AS GAS FALLS INTO A SUPERMASSIVE BLACK HOLE. THE FLARES ECHOED OFF OF THE GAS FALLING INTO THE BLACK HOLE, AND AS THE FLARES WERE SUBSIDING, SHORT FLASHES OF X-RAYS WERE SEEN – CORRESPONDING TO THE REFLECTION OF THE FLARES FROM THE FAR SIDE OF THE DISK, BENT AROUND THE BLACK HOLE BY ITS STRONG GRAVITATIONAL FIELD. view more 

CREDIT: DAN WILKINS

Watching X-rays flung out into the universe by the supermassive black hole at the center of a galaxy 800 million light-years away, Stanford University astrophysicist Dan Wilkins noticed an intriguing pattern. He observed a series of bright flares of X-rays – exciting, but not unprecedented – and then, the telescopes recorded something unexpected: additional flashes of X-rays that were smaller, later and of different “colors” than the bright flares.

According to theory, these luminous echoes were consistent with X-rays reflected from behind the black hole – but even a basic understanding of black holes tells us that is a strange place for light to come from.

“Any light that goes into that black hole doesn’t come out, so we shouldn’t be able to see anything that’s behind the black hole,” said Wilkins, who is a research scientist at the Kavli Institute for Particle Astrophysics and Cosmology at Stanford and SLAC National Accelerator Laboratory. It is another strange characteristic of the black hole, however, that makes this observation possible. “The reason we can see that is because that black hole is warping space, bending light and twisting magnetic fields around itself,” Wilkins explained.

The strange discovery, detailed in a paper published July 28 in Nature, is the first direct observation of light from behind a black hole – a scenario that was predicted by Einstein’s theory of general relativity but never confirmed, until now.

“Fifty years ago, when astrophysicists starting speculating about how the magnetic field might behave close to a black hole, they had no idea that one day we might have the techniques to observe this directly and see Einstein’s general theory of relativity in action,” said Roger Blandford, a co-author of the paper who is the Luke Blossom Professor in the School of Humanities and Sciences, Stanford professor of physics and SLAC professor of particle physics and astrophysics.

How to see a black hole

The original motivation behind this research was to learn more about a mysterious feature of certain black holes, called a corona. Material falling into a supermassive black hole powers the brightest continuous sources of light in the universe, and as it does so, forms a corona around the black hole. This light – which is X-ray light – can be analyzed to map and characterize a black hole.

The leading theory for what a corona is starts with gas sliding into the black hole where it superheats to millions of degrees. At that temperature, electrons separate from atoms, creating a magnetized plasma. Caught up in the powerful spin of the black hole, the magnetic field arcs so high above the black hole, and twirls about itself so much, that it eventually breaks altogether – a situation so reminiscent of what happens around our own Sun that it borrowed the name “corona.”

“This magnetic field getting tied up and then snapping close to the black hole heats everything around it and produces these high energy electrons that then go on to produce the X-rays,” said Wilkins.

As Wilkins took a closer look to investigate the origin of the flares, he saw a series of smaller flashes. These, the researchers determined, are the same X-ray flares but reflected from the back of the disk – a first glimpse at the far side of a black hole.

“I’ve been building theoretical predictions of how these echoes appear to us for a few years,” said Wilkins. “I’d already seen them in the theory I’ve been developing, so once I saw them in the telescope observations, I could figure out the connection.”

Future observations

The mission to characterize and understand coronas continues and will require more observation. Part of that future will be the European Space Agency’s X-ray observatory, Athena (Advanced Telescope for High-ENergy Astrophysics). As a member of the lab of Steve Allen, professor of physics at Stanford and of particle physics and astrophysics at SLAC, Wilkins is helping to develop part of the Wide Field Imager detector for Athena.

“It’s got a much bigger mirror than we’ve ever had on an X-ray telescope and it’s going to let us get higher resolution looks in much shorter observation times,” said Wilkins. “So, the picture we are starting to get from the data at the moment is going to become much clearer with these new observatories.”

Co-authors of this research are from Saint Mary’s University (Canada), Netherlands Institute for Space Research (SRON), University of Amsterdam and The Pennsylvania State University.

This work was supported by the NASA NuSTAR and XMM-Newton Guest Observer programs, a Kavli Fellowship at Stanford University, and the V.M. Willaman Endowment at the Pennsylvania State University.

ESA illustration (IMAGE)

STANFORD UNIVERSITY



 

Computer science, environmental health experts at UIC team up to protect US Navy divers with AI


Office of Naval Research awards UIC, DPI researchers $725,000

Grant and Award Announcement

UNIVERSITY OF ILLINOIS AT CHICAGO

Underwater 

IMAGE: RESEARCHERS AT UIC ARE WORKING ON AN AI SYSTEM TO HELP SAILORS, THANKS TO A TWO-YEAR, $725,000 GRANT AWARD view more 

CREDIT: VLAD TCHOMPALOV/UNSPLASH

The U.S. Office of Naval Research has awarded University of Illinois Chicago researchers $725,000 to develop an artificial intelligence system that can help protect divers from waterborne bacteria, parasites, and other harmful pathogens and microbes.

Sailors are sent into all kinds of water as part of their service in the U.S. Navy, but they have limited resources to understand in real-time the health risks that may exist when they conduct underwater duties — everything from fleet maintenance and repairs to search and rescue and research missions. The most reliable water testing technologies typically rely on lab-based analysis of samples and scientists knowing which microbes to screen. But with dynamic weather, currents, water temperatures, and sewage and pollution factors, the exact condition of water, particularly of coastal water, at a specific time is hard to predict.

“By the time a water sample arrives at a lab and is tested, the conditions may have changed,” said Dr. Samuel Dorevitch, associate professor of environmental and occupational health sciences at the School of Public Health and co-principal investigator. “If Navy divers had real-time information, they could select the best protective equipment, dive duration and take other measures to prevent the various health issues, like heat stress or gastrointestinal, skin, and respiratory infections that may result from microbes in water.”

That’s where a new approach using artificial intelligence can make a difference.

“Artificial intelligence offers a way to synthesize a vast amount of information quickly for a specific calculation and this technology, if we can bring it to fruition, provides an opportunity for us to improve the tools available to the Navy,” said Isabel Cruz, distinguished professor of computer science at the College of Engineering and co-principal investigator.

The researchers hope that they can develop a system that can be used in any location by divers to analyze water conditions through a combination of user-provided and web-based information and human data, such as the age of the divers, their health, and the size of the diving team.

“This project is both exciting and challenging because of its multidimensionality,” Cruz said. “We hope to pull information from many sources that offer different types of data, and we will have to integrate data that are quite complex, heterogeneous, and often without metadata. We will build the artificial intelligence and machine learning methods in stages, and if we can teach our system to reliably and accurately filter and prioritize all these data for risk prediction, I think we will have something remarkable.”

“If we could provide divers or their commanders with a handheld device or app to evaluate the ever-changing ecosystem of a particular body of water and any potential health risks at the time they enter the water, they would be better able to plan their mission for optimal health and safety,” Dorevitch said. “For those in the Navy, getting in the water is not optional and anything we can do to aid quick, data-driven decision-making for mitigating health risk is beneficial.”

###

Charlie Catlett, senior research scientist at Discovery Partners Institute, is a co-investigator. The grant, which started May 16, will support this research for two years.