The Defense Innovation Unit is bringing together the best of commercially available artificial intelligence technology and the Defense Department's vast cache of archived medical data to teach computers how to identify cancers and other medical irregularities.
The result will be new tools medical professionals can use to more accurately and more quickly identify medical issues in patients.
The new DIU project, called "Predictive Health," also involves the Defense Health Agency, three private-sector businesses and the Joint Artificial Intelligence Center.
The new capability directly supports the development of the JAIC's warfighter health initiative, which is working with the Defense Health Agency and the military services to field AI solutions that are aimed at transforming military health care. The JAIC is also providing the funding and adding technical expertise for the broader initiative.
"The JAIC's contributions to this initiative have engendered the strategic development of required infrastructure to enable AI-augmented radiographic and pathologic diagnostic capabilities," said Navy Capt. (Dr.) Hassan Tetteh, the JAIC's Warfighter Health Mission Initiative chief. "Given the military's unique, diverse, and rich data, this initiative has the potential to compliment other significant military medical advancements to include antisepsis, blood transfusions, and vaccines."
A big part of the Predictive Health project will involve training AI to look at de-identified DOD medical imagery to teach it to identify cancers. The AI can then be used with augmented reality microscopes to help medical professionals better identify cancer cells.
Nathanael Higgins, the support contractor managing the program for DIU, explained what the project will mean for the department.
"From a big-picture perspective, this is about integrating AI into the DOD health care system," Higgins said. "There are four critical areas we think this technology can impact. The first one is, it's going to help drive down cost."
The earlier medical practitioners can catch a disease, Higgins said, the easier it will be to anticipate outcomes and to provide less invasive treatments. That means lower cost to the health care system overall, and to the patient, he added.
Another big issue for DOD is maximizing personnel readiness, Higgins said.
"If you can cut down on the number of acute issues that come up that prevent people from doing their job, you essentially help our warfighting force," he explained.
Helping medical professionals do their jobs better is also a big part of the Predictive Health project, Higgins said.
"Medical professionals are already overworked," he said. "We're essentially giving them an additional tool that will help them make confident decisions and know that they made the right decision so that we're not facing as many false negatives or false positives. And ultimately we're able to identify these types of disease states earlier, and that'll help the long-term prognosis."
In line with the department adding an additional line of effort focused on taking care of people to the National Defense Strategy, Higgins said using AI to identify medical conditions early will help to optimize warfighter performance as well.
"Early diagnosis equals less acute injuries, which means less invasive procedures, which means we have more guys and gals in our frontline forces and less cost on the military health care system," he said. "The ultimate value here is really saving lives as people are our most valuable resource."
Using AI to look for cancer first requires researchers to teach AI what cancer looks like. This requires having access to a large set of training data. For the Predictive Health project, this will mean a lot of medical imagery of the kind produced by CT scans, MRIs, X-rays and slide imagery made from biopsies, and knowing ahead of time that the imagery depicts the kind of illnesses, such as cancer, that researchers hope to train the AI to identify.
DOD has access to a large set of this kind of data. Dr. Niels Olson, the DIU chief medical officer and originator of the Predictive Health project, said DOD also has a very diverse set of data, given its size and the array of people for which the department's health care system is responsible.
"If you think about it, the DOD, through retired and active duty service, is probably one of the largest health care systems in the world, at about 9 million people," Olson said. "The more data a tool has available to it, the more effective it is. That's kind of what makes DOD unique. We have a larger pool of information to draw from, so that you can select more diverse cases."
"Unlike some of the other large systems, we have a pretty good representation of the U.S. population," he said. "The military actually has a nice smooth distribution of population in a lot of ways that other regional systems don't have. And we have it at scale."
While DOD does have access to a large set of diverse medical imaging data that can be used to train an AI, Olson said privacy will not be an issue.
"We'll use de-identified information, imaging, from clinical specimens," Olson said. "So this means actual CT images and actual MRI images of people who have a disease, where you remove all of the identifiers and then just use the diagnostic imaging and the actual diagnosis that the pathologist or radiologist wrote down."
AI doesn't need to know who the medical imaging has come from it just needs to see a picture of cancer to learn what cancer is.
"All the computer sees is an image that is associated with some kind of disease, condition or cancer," Olson said. "We are ensuring that we mitigate all risk associated with [the Health Insurance Portability and Accountability Act of 1996], personally identifiable information and personal health information."
Using the DOD's access to training data and commercially available AI technology, the DIU's Predictive Health project will need to train the AI to identify cancers. Olson explained that teaching an AI to look at a medical image and identify what is cancer is a process similar to that of a parent teaching a child to correctly identify things they might see during a walk through the neighborhood.
"The kid asks 'Mom, is that a tree?' And Mom says, 'No, that's a dog,'" Olson explained. "The kids learn by getting it wrong. You make a guess. We formally call that an inference, a guess is an inference. And if the machine gets it wrong, we tell it that it got it wrong."
The AI can guess over and over again, learning each time about how it got the answer wrong and why, until it eventually learns how to correctly identify a cancer within the training set of data, Olson said, though he said he doesn't want it to get too good.
Overtraining, Olson said, means the AI has essentially memorized the training set of data and can get a perfect score on a test using that data. An overtrained system is unprepared, however, to look at new information, such as new medical images from actual patients, and find what it's supposed to find.
"If I memorize it, then my test performance will be perfect, but when I take it out in the real world, it would be very brittle," Olson said.
Once well trained, the AI can be used with an "augmented reality microscope," or ARM, so pathologists can more quickly and accurately identify diseases in medical imagery, Olson said.
"An augmented reality microscope has a little camera and a tiny little projector, and the little camera sends information to a computer and the computer sends different information back to the projector," Olson said. "The projector pushes information into something like a heads-up display for a pilot, where information is projected in front of the eyes."
With an ARM, medical professionals view tissue samples with information provided by an AI overlaid over the top information that helps them more accurately identify cells that might be cancerous, for instance.
While the AI that DIU hopes to train will eventually help medical professionals do a better job of identifying cancers, it won't replace their expertise. There must always be a medical professional making the final call when it comes to treatment for patients, Higgins said.
"The prototype of this technology that we're adopting will not replace the practitioner," he said. "It is an enabler it is not a cure-all. It is designed to enhance our people and their decision making. If there's one thing that's true about DOD, it's that people are our most important resource. We want to give them the best tools to succeed at their job.
"AI is obviously the pinnacle of that type of tool in terms of what it can do and how it can help people make decisions," he continued. "The intent here is to arm them with an additional tool so that they make confident decisions 100% of the time."
The Predictive Health project is expected to end within 24 months, and the project might then make its way out to practitioners for further testing.
The role of DIU is taking commercial technology, prototyping it beyond a proof of concept, and building it into a scalable solution for DOD.
See the rest here:
- The Next Generation Of Artificial Intelligence - Forbes - October 16th, 2020
- St. Louis Is Grappling With Artificial Intelligence's Promise And Potential Peril - St. Louis Public Radio - October 16th, 2020
- Looper column: Artificial intelligence, humanity and the future - SouthCoastToday.com - October 16th, 2020
- For artificial intelligence to flourish, governments need to think ahead about its responsible use - Firstpost - October 16th, 2020
- MediFind Selected as Finalist for Best in Artificial Intelligence in the Shorty Social Good Awards - The Wellsboro Gazette - October 16th, 2020
- The relentless threat of artificial intelligence taking our jobs away - Mint - October 16th, 2020
- Will artificial intelligence technology change the dairy industry - positivelyosceola.com - October 16th, 2020
- Penn Medicine researchers use artificial intelligence to identify early signs of Alzheimer's Disease - Express Computer - October 16th, 2020
- Futurism Reinforces Its Next-Gen Business Commerce Platform With Advanced Machine Learning and Artificial Intelligence Capabilities - Yahoo Finance - October 16th, 2020
- SparkCognition Advances the Science of Artificial Intelligence with 85 Patents - PRNewswire - October 16th, 2020
- Dont Be Afraid, BMW Promises To Keep Artificial Intelligence (AI) On A Tight Leash With These 7 Principles - CarScoops - October 16th, 2020
- Artificial Intelligence in Government: Global Markets 2020-2025 - ResearchAndMarkets.com - Business Wire - August 31st, 2020
- Import Screening Pilot Unleashes the Power of Data - FDA.gov - August 31st, 2020
- Supercharge vegetation management and outage prediction with artificial intelligence - Utility Dive - August 31st, 2020
- Automation, artificial intelligence to be central in the post-Covid world - Economic Times - August 31st, 2020
- Artificial Intelligence Is the Next Top Gun - Bloomberg - August 31st, 2020
- Toward a machine learning model that can reason about everyday actions - MIT News - August 31st, 2020
- How Artificial Intelligence is changing the way we search and find online - ITProPortal - August 31st, 2020
- TikTok Assets Cant Be Sold Without Chinas Approval - Bloomberg - August 31st, 2020
- Artificial Intelligence in Oil and Gas Market Global Size, Growth and Demand 2020 to 2030 - The News Brok - August 31st, 2020
- Rage Against the Algorithm: the Risks of Overestimating Military Artificial Intelligence - Chatham House - August 31st, 2020
- U of I to lead two of seven new national artificial intelligence institutes - University of Illinois News - August 31st, 2020
- Holocaust survivors will be able to share their stories after death thanks to a new project - 60 Minutes - CBS News - August 31st, 2020
- Funding boost for artificial intelligence in NHS to speed up diagnosis of deadly diseases - GOV.UK - August 31st, 2020
- Artificial Intelligence Identifies 80,000 Spiral Galaxies Promises More Astronomical Discoveries in the Future - SciTechDaily - August 31st, 2020
- Is Artificial intelligence the Future of IT Help Desk? - Analytics Insight - August 10th, 2020
- Experts Are Divided Over Future Of Artificial Intelligence But Agree On Its Growing Impact - Outlook India - August 10th, 2020
- "Artificial Intelligence Will Make Medicine Better in the Long Run" - Biophotonics.World - August 10th, 2020
- How machine learning and artificial intelligence can drive clinical innovation - PharmaLive - August 10th, 2020
- Top Artificial Intelligence and Robotics Investments in July 2020 - Analytics Insight - August 10th, 2020
- Job interviews: Recruiters are using artificial intelligence to analyse what you say to find the right hire - TechRepublic - August 10th, 2020
- The next frontier of human-robot relationships is building trust - Scroll.in - August 8th, 2020
- Game-Changing Artificial Intelligence Solution by PhotoShelter to Revolutionize Social Media Workflow as Premier Lacrosse League Returns to the Field... - August 8th, 2020
- How Artificial Intelligence is Helping to Fight against Coronavirus in India? - Analytics Insight - August 8th, 2020
- BLOG: How to capitalise on the Artificial Intelligence theme - Your Money - Your Money - August 8th, 2020
- Artificial Intelligence and Its Partners - Modern Diplomacy - August 8th, 2020
- Artificial intelligence isnt destroying jobs, its making them more inclusive - The Globe and Mail - August 8th, 2020
- RadNet and Hologic Announce Collaboration to Advance the Development of Artificial Intelligence Tools in Breast Health - GlobeNewswire - August 7th, 2020
- COVID-19 Impacts: Artificial Intelligence-as-a-Service (AIaaS) Market Will Accelerate at a CAGR of Over 48% Through 2020-2024|Growing Adoption of... - August 7th, 2020
- Artificial Intelligence in Business: The New Normal in Testing Times - Analytics Insight - August 7th, 2020
- VIEW: Digitisation in pathology and the promise of artificial intelligence - CNBCTV18 - August 7th, 2020
- What It Means to Be Human in the Age of Artificial Intelligence - Medium - August 7th, 2020
- Not so Artificial Intelligence When is AI really AI? - EFTM - August 3rd, 2020
- IMD to explore artificial intelligence to improve forecasting, predict extreme weather events - Firstpost - August 3rd, 2020
- Examples of Failure in Artificial Intelligence - ReadWrite - August 3rd, 2020
- IMD plans to use artificial intelligence in weather forecasting - The Financial Express - August 3rd, 2020
- MLOps: What You Need To Know - Forbes - August 3rd, 2020
- Postdoctoral Research Associate in Artificial Intelligence job with DURHAM UNIVERSITY | 215559 - Times Higher Education (THE) - August 3rd, 2020
- How do CEO's Succeed with Artificial Intelligence at their Workplace? - Analytics Insight - August 3rd, 2020
- The future of Artificial Intelligence and what it means to the Enterprise? - Analytics Insight - August 3rd, 2020
- Artificial intelligence helps lead decisions over Intelligent automation and - 401kTV - August 3rd, 2020
- Artificial Intelligence and civil liability. Who pays the damages? - Lexology - August 3rd, 2020
- The AI-boost: Using more artificial intelligence will boost GDP growth - The Financial Express - August 3rd, 2020
- $19.9B Artificial Intelligence in Retail Industry, 2027 - Rising Focus on Blockchain and Adoption of 5G Technology - Yahoo Finance - August 3rd, 2020
- Artificial Intelligence Loses Some Of Its Edginess, But Is Poised To Take Off - Forbes - July 31st, 2020
- How artificial intelligence is transforming the world in the current pandemic situation? - Geospatial World - July 31st, 2020
- The NBA will use artificial intelligence and a tap-to-cheer app feature to help fans stuck at home get in the game - CNN - July 31st, 2020
- Different Scopes Of Artificial Intelligence To Dive In With! - Inventiva - July 31st, 2020
- Gatling Exploration to use artificial intelligence to identify possible gold targets at the Larder project in Ontario - Proactive Investors USA &... - July 31st, 2020
- Elon Musk Thinks that Artificial Intelligence Will Be 'Vastly Smarter' Than Humans in 5 Years - News18 - July 31st, 2020
- Church body recommends restrictions on Artificial Intelligence - The Tablet - July 31st, 2020
- How the Coronavirus Pandemic Is Breaking Artificial Intelligence and How to Fix It - Gizmodo - July 31st, 2020
- Using artificial intelligence to smell the roses - UC Riverside - July 30th, 2020
- Shield AI Recognized As One of the Most Promising Artificial Intelligence Companies - PR Web - July 30th, 2020
- Artificial intelligence needs an update on ethics to be able to help humanity in times of crisis - Economic Times - July 30th, 2020
- Reshaping Artificial Intelligence with the Help of Affordances - Analytics Insight - July 29th, 2020
- WISeKey to Showcase its Cybersecurity Solutions for Artificial Intelligence Used in Drones and Robots at SIDO 2020 - GlobeNewswire - July 28th, 2020
- GPT-3: The Next Revolution in Artificial Intelligence - Analytics Insight - July 28th, 2020
- FLY AI: the role of artificial intelligence in aviation - Airport Technology - July 28th, 2020
- Four university experts use Artificial Intelligence to discover that children don't like going to school on Mondays in Milton Keynes - Milton Keynes... - July 28th, 2020
- UF Announces $70 Million Artificial Intelligence Partnership with NVIDIA - University of Florida - July 28th, 2020
- People are using artificial intelligence to help sort out their divorce. Would you? - The Conversation AU - July 28th, 2020
- Artificial Intelligence Is the Hope 2020 Needs - Bloomberg - July 28th, 2020
- Top Five Data Privacy Issues that Artificial Intelligence and Machine Learning Startups Need to Know - insideBIGDATA - July 28th, 2020
- I Am a Model and I Know That Artificial Intelligence Will Eventually Take My Job - Vogue.com - July 28th, 2020
- Artificial Intelligence in Manufacturing Market Worth $16.7 Billion by 2026 - Exclusive Report by MarketsandMarkets - PRNewswire - July 28th, 2020
- The Global Artificial Intelligence in Accounting Market is expected to grow from USD 884.99 Million in 2019 to USD 4,779.11 Million by the end of 2025... - July 28th, 2020
- Imint is the Swedish firm that gives Chinese smartphones an edge in video production - TechCrunch - July 26th, 2020
- UF students, get used to this topic: artificial intelligence - Tampa Bay Times - July 26th, 2020
- Odisha to use artificial intelligence in organisation audit in big way - The New Indian Express - July 26th, 2020