Stories
Slash Boxes
Comments

SoylentNews is people

posted by janrinok on Monday December 18, @09:35PM   Printer-friendly
from the bug-off dept.

Microscopes enhanced with artificial intelligence (AI) could help clinical microbiologists diagnose potentially deadly blood infections and improve patients' odds of survival, according to microbiologists at Beth Israel Deaconess Medical Center (BIDMC). In a paper published in the Journal of Clinical Microbiology, the scientists demonstrated that an automated AI-enhanced microscope system is "highly adept" at identifying images of bacteria quickly and accurately. The automated system could help alleviate the current lack of highly trained microbiologists, expected to worsen as 20 percent of technologists reach retirement age in the next five years.

"This marks the first demonstration of machine learning in the diagnostic area," said senior author James Kirby, MD, Director of the Clinical Microbiology Laboratory at BIDMC and Associate Professor of Pathology at Harvard Medical School. "With further development, we believe this technology could form the basis of a future diagnostic platform that augments the capabilities of clinical laboratories, ultimately speeding the delivery of patient care."

[...] While human technologists routinely provide highly accurate diagnoses, demand for these highly skilled workers exceeds supply in the United States. Nine percent of lab technologists remain unfilled, and that number is expected to dramatically increase as technologists of the Baby Boomer generation begin to retire in droves, according to a 2014 survey from the American Society for Clinical Pathology.

What's more, these images can be sent remotely, bringing the highest level expertise anywhere the internet reaches. That's critical, as rapid identification and delivery of antibiotic medications is the key to treating bloodstream infections, which can kill up to 40 percent of patients who develop them. Each day a patient goes untreated is linked with an increased risk of mortality.

In addition to its clinical uses, the new tool could also have applications in microbiology training and research, Kirby noted.

"The tool becomes a living data repository as we use it," he said. "And could be used to train new staff and ensure competency. It can provide unprecedented level of detail as a research tool."

Kenneth P. Smith, Anthony D. Kang, James E. Kirby. Automated Interpretation of Blood Culture Gram Stains using a Deep Convolutional Neural Network. Journal of Clinical Microbiology, 2017; JCM.01521-17 DOI: 10.1128/JCM.01521-17

Source: http://www.bidmc.org/News/PRLandingPage/2017/December/Kirby.aspx


Original Submission

This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough

Mark All as Read

Mark All as Unread

The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
(1)
  • (Score: 0) by Anonymous Coward on Monday December 18, @09:55PM

    by Anonymous Coward on Monday December 18, @09:55PM (#611592)

    The man keeps boned even burn victim tautology. Christ alive!

  • (Score: 2) by DannyB on Monday December 18, @10:34PM (2 children)

    by DannyB (5839) on Monday December 18, @10:34PM (#611611)

    Microscopes enhanced with artificial intelligence . . .

    First . . . that is amazing. Just stop and think about it for a second.

    Next, when watching the old 1960's ST:TOS, the controls and devices seem rather primitive. Maybe due to budget. Maybe because the microcomputer revolution hadn't happened and they couldn't really visualize how advanced devices might work. By the 1980's it was obvious to have touch screen interfaces, ala, ST:TNG. Now the old ST:TOS microscope comes back to believability. Gadgets like intercoms, communicators. Computer interfaces. And . . . microscopes, have relatively simple physical controls because of the advanced AI built into the devices.

    We will go through a phase where more devices have touch screens for configuration and commands. Then more and more things will start to lose those touch screen controls in favor of AI, and simply be smart enough to recognize when a slide of something interesting is inserted into the microscope, automatically analyze it, and directly display the results without pushing any buttons, or giving commands. And why not just automatically recognize who the current microscope user is, and link the detailed analysis, and summary, and diagnosis if appropriate to their smartphone . . . er, um tricorder / communicator. For common types of slide samples, the microscope would anticipate every interesting feature of this slide sample, analyze it in detail, and provide a summary linked to the detail. Basically as devices get more smarts, they might start to look more like very simple instruments.

    And the microscope could automatically bill your health insurance provider.

    • (Score: 2) by unauthorized on Monday December 18, @11:47PM

      by unauthorized (3776) on Monday December 18, @11:47PM (#611639)

      First . . . that is amazing. Just stop and think about it for a second.

      It might have sounded amazing if I couldn't buy countless video games enhanced with artificial intelligence from the comfort of my home.

    • (Score: 2) by legont on Tuesday December 19, @01:17AM

      by legont (4179) on Tuesday December 19, @01:17AM (#611665)

      So, why don't we see Watson and/or Alpha Go Zero competing against your average greedy doctor? Prime time TV show would be nice. Conspiracy?

      --
      "Wealth is the relentless enemy of understanding" - John Kenneth Galbraith.
  • (Score: 4, Insightful) by Anonymous Coward on Tuesday December 19, @08:04AM

    by Anonymous Coward on Tuesday December 19, @08:04AM (#611745)

    The automated system could help alleviate the current lack of highly trained microbiologists, expected to worsen as 20 percent of technologists reach retirement age in the next five years.

    Yes, right... with 50 people waiting for a job for every graduate in microbiology... all you need to do is look at the number of qualified submissions for every job advertised at any prominent microbiology lab. Never mind the endless supply of postdocs that linger and linger until most just fall off the train since there is no job for them. So please, stop with the bullshit of "lack of microbiologists". It's the same bullshit as with "there is not enough programmers"

    http://www.telegraph.co.uk/finance/jobs/10949825/Employers-receive-39-applications-for-every-graduate-job.html [telegraph.co.uk]
    http://www.news.com.au/finance/work/careers/as-many-as-46-university-graduates-are-competing-for-each-graduate-job-vacancy/news-story/3fd001319edee40543d06d7fdf9d4648 [news.com.au]

  • (Score: 1, Informative) by Anonymous Coward on Tuesday December 19, @11:36AM

    by Anonymous Coward on Tuesday December 19, @11:36AM (#611777)

    Similar news was on the Dutch TV last week, except it was used to do an initial screen for cancerous cells. The AI helped the specialist to give an indication of which cells looked cancerous (single cell slides, ca. 1000 - 5000 cells, about 10 slides per patient), normally it took the specialist about 20 minutes to screen all the slides, the AI reduced it to a few minutes. This was the new tech, they also showed the old tech, where a specialist could mark groups of cells where he wasn't sure about and the AI would give a score with a probability of it being cancerous. This tech was about 10 years old according to the specialist.

  • (Score: 2) by HiThere on Tuesday December 19, @06:19PM

    by HiThere (866) on Tuesday December 19, @06:19PM (#611890)

    There have been stories about AI's diagnosing various diseases by cell studied for many years. It's not clear what makes this more significant than any of the others, though I'm not saying it isn't...for one thing prices may have fallen enough to justify it.

    --
    Put not your faith in princes.
(1)