116. AI Early Detection of Sepsis, Improving Old Age Learning, DeepMind Finds More Protein Structures


Manage episode 336070057 series 2832936
Av Adam Buckingham oppdaget av Player FM og vårt samfunn — opphavsrett er eid av utgiveren, ikke Plaer FM, og lyd streames direkte fra deres servere. Trykk på Abonner knappen for å spore oppdateringer i Player FM, eller lim inn feed URLen til andre podcast apper.

Bedside AI warning system for sepsis reduces mortality by nearly 20% | New Atlas (01:23)

  • Infections can trigger all kinds of reactions in the human body, and one of the most extreme is sepsis.
    • Occurs as a result of an infection that triggers a severe immune response in the body.
    • Begins with widespread inflammation and can end in blood clots, leaky blood vessels, organ failure or death.
    • Diagnosing the condition is difficult in its early stages.
  • This life-threatening complication causes more than 250,000 deaths in the US each year, but a new artificial intelligence system developed at Johns Hopkins University promises to make a real difference in this area, by catching key symptoms early on.
    • Early diagnosis is critical because a patient experiencing sepsis can deteriorate quickly, with the condition killing around 30% of those who develop it.
  • The Johns Hopkins team is looking to leverage advanced artificial intelligence to identify patients at risk.
    • Does this by analyzing a patient's medical history and combining that with current symptoms, clinical notes and lab results.
    • The AI tracks patients from the moment they are admitted to hospital until the moment they are discharged.
    • Called the Targeted Real-Time Early Warning System
  • By monitoring them throughout the time at the hospital, the system is designed to ensure no important, or potentially dangerous, medical details fall through the cracks.
  • Developed and deployed in collaboration with Johns Hopkins spinoff Bayesian Health, the tool was put to use across five hospitals as part of a two-year trial, involving more than 700,000 patients.
  • According to the researchers, the system proved very effective, leading to the detection of sepsis on average almost six hours earlier than traditional methods, with a sensitivity rate of 82%.
    • It also fostered a high rate of adoption among healthcare providers of 89%.
    • The result was significant reductions in morbidity, the length of hospital stay and, most importantly, a reduction in mortality of 18.2%.
  • Neri Cohen, MD, PhD, who collaborated on the study explains the significance of this:
    • “There aren't many things left in medicine that have a 30% mortality rate like sepsis … What makes it so vexing, is that it is relatively common and we still have made very little progress in recognizing it early enough to materially reduce the morbidity and mortality. To reduce mortality by nearly 20% is remarkable and translates to many lives saved."

Artificial Muscles Woven Into Smart Textiles Could Make Clothing Hyperfunctional | IEEE Spectrum (07:44)

  • Engineers at the University of New South Wales (UNSW), Sydney, Australia, have developed a new class of fluid-driven smart textiles that can “shape-shift” into 3D structures.
  • According to Thanh Nho Do, senior lecturer at the UNSW’s Graduate School of Biomedical Engineering, who led the study, development of active textiles is “either limited with slow response times due to the requirement of heating and cooling, or difficult to knit, braid, or weave in the case of fluid-driven textiles.”
  • The researchers used a simple, low-cost fabrication technique, in which a long, thin silicone tube is directly inserted into a hollow micro coil to produce the artificial muscles, with a diameter ranging from a few hundred micrometers to several millimeters.
    • Allowing them to mass-produce these soft artificial muscles at any scale and size
  • The combination of hydraulic pressure, fast response times, light weight, small size, and high flexibility makes the UNSW’s smart textiles versatile and programmable.
  • This versatility opens up potential applications in soft robotics, including shape-shifting structures, biomimicking soft robots, locomotion robots, and smart garments.
    • Possibilities for use as medical/therapeutic wearables, as assistive devices for those needing help with movement, and as soft robots to aid the rescue and recovery of people trapped in confined spaces.
  • These artificial muscles are still a proof of concept, Do is optimistic about commercialization in the near future, stating:
    • “We have a Patent Cooperation Treaty application around these technologies … We are also working on clinical validation of our technology in collaborations with local clinicians, including smart compression garments, wearable assistive devices, and soft haptic interfaces.”

Brain stimulation improves motor skill learning at older age | MedicalXPress (11:53)

  • Studies involving older individuals show that the older we get, the harder it is and the longer it takes to learn new motor skills, suggesting an age-related decrease in learning ability.
  • A new study by researchers at EPFL has found that non-invasive electrical brain stimulation can help older adults learn new motor skills much faster.
  • The study used a common way of evaluating how well a person learns new motor skills called the "finger-tapping task."
    • key feature of learning
    • involves typing a sequence of numbers as fast and as accurately as possible.
    • The task simulates activities that require high dexterity, while providing an objective measure of "improvement," defined as a person increasing their speed without losing accuracy (shift in the speed-accuracy tradeoff)
  • One of the ways the brain achieves this shift for learning is by grouping individual motor actions into so called "motor chunks":
    • spontaneously emerging brain structures that reduce a person's mental load, while optimizing the mechanical execution of the motor sequence.
  • Ph.D. student Pablo Maceira-Elvira, who worked on the study talks about the differences of young and old trying to learn this task:
    • “Older adults showed decreased fast online learning and absent offline learning … In other words, while young adults show sharp performance increases early in training and improve overnight, older adults improve at a more moderate pace and even worsen overnight."
  • The researchers applied atDCS to the participants and found that it helped older adults to improve their accuracy sharply earlier on in training and in a pattern similar to that seen in young adults.
    • atDCS: Anodal Transcranial Direct Current Stimulation
  • Maceira-Elvira relays the results:
    • “Stimulation accelerated the shift in the speed-accuracy tradeoff and enabled an earlier emergence of efficient motor chunks, with 50% of older adults generating these structures during the first training session.”
  • What does that suggest? Maceira-Elvira explains that it “suggests that atDCS can at least partially restore motor skill acquisition in individuals with diminished learning mechanisms, by facilitating the storage of task-relevant information, quickly reducing mental load and allowing the optimization of the mechanical execution of the sequence."
  • This could open up atDCS as a non-invasive way to help improve mental function that’s declining due to aging or disorders like stroke.

Small molecule prevents tumor cells from spreading | Phys.org (17:35)

  • Leiden chemists, together with colleagues at the University of York (UK) and Technion (Israel) have discovered a small, sugar-like molecule that maintains the integrity of tissue around a tumor during cancer.
    • prevents tumor cells from spreading from the primary cancer site
  • What makes cancer so lethal?
    • It’s ability to metastasize
    • Metastasis, the spread of cancer cells to distant sites in the body.
    • It depends on the ability of cancer cells to detach from the primary tumor site, and invade through blood vessel walls and tissue barriers to reach secondary sites of growth.
    • Enzymes enable cancer cells to pass through the gaps created through the digestion of proteins and sugars in the space around cells
  • Metastatic cancer cells produce large amounts of heparanase enzyme, which helps them to spread around the body.
    • Inhibiting the heparanase is a major target for anti-cancer therapy.
  • Researchers developed and tested a new sugar-like molecule that reacts with the enzyme heparanase.
    • Once attached, the heparanase enzyme is unable to bind or cut heparin sulfate sugar chains around cells.
    • The tissue around the cells remains firm and inaccessible to dislodged cells.
  • They already studied the new molecule in mouse models of lung cancer, breast cancer and blood cancer.
    • The results are promising and the institutes involved have already applied for a patent on the molecule.
  • Leiden chemist Hermen Overkleeft believes that this molecule deserves a chance to find out its effect in the human body:
    • “Now we have to find out whether the compound is stable, safe for the human body, ends up in the right place in sufficient quantities, and so on. That takes a couple of years, it may come to nothing and someone has to be willing to take that financial risk…. Our molecule is one of the few agents that can inhibit heparanase tightly and specifically. Small, well-defined molecules like this one may be easier to develop into a clinical drug than the large, heterogeneous polysaccharides that have been tried up to now."

DeepMind found the structure of nearly every protein known to science | The Verge (22:22)

  • Deepmind, a subsidiary of Google parent Alphabet, announced this past Thursday (July 28th) they will be releasing a free expanded database with its predictions of the structure of nearly every protein known to science.
    • over 200 million structures
  • We’ve discussed DeepMind’s AlphaFold AI system in past episodes, but in short, this system produces highly accurate predictions of the structures of proteins.
    • This predicted information can help scientists understand how they work, which can help treat diseases and develop medications.
  • Demis Hassabis, CEO of DeepMind, said during a press briefing:
    • “You can think of it as covering the entire protein universe … We’re at the beginning of a new era now in digital biology.”
  • Protein structures from AlphaFold are already widely used by research teams around the world.
    • Cited in research on things like a malaria vaccine candidate and honey bee health.
  • Having easy access to predicted protein structures gives scientists a boost in research efforts across the scientific landscape.
    • Those trying to understand how complex processes work in the body or which molecules can be used to target things like pollution.
  • We’ll end it off with a statement from Eric Topol, founder and director of the Scripps Research Translational Institute:
    • “With this new addition of structures illuminating nearly the entire protein universe, we can expect more biological mysteries to be solved each day.”

136 episoder