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

News: <p><a href='https://newatlas.com/medical/bedside-ai-warning-system-sepsis-mortality-20/'>Bedside AI warning system for sepsis reduces mortality by nearly 20%</a> | New Atlas (01:23)</p> <ul><li style="font-weight:400;">Infections can trigger all kinds of reactions in the human body, and one of the most extreme is sepsis.<ul><li style="font-weight:400;">Occurs as a result of an infection that triggers a severe immune response in the body.</li> <li style="font-weight:400;">Begins with widespread inflammation and can end in blood clots, leaky blood vessels, organ failure or death.</li> <li style="font-weight:400;">Diagnosing the condition is difficult in its early stages.</li> </ul> </li> <li style="font-weight:400;">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.<ul><li style="font-weight:400;">Early diagnosis is critical because a patient experiencing sepsis can deteriorate quickly, with the condition killing around 30% of those who develop it.</li> </ul> </li> <li style="font-weight:400;">The Johns Hopkins team is looking to leverage advanced artificial intelligence to identify patients at risk.<ul><li style="font-weight:400;">Does this by analyzing a patient's medical history and combining that with current symptoms, clinical notes and lab results.</li> <li style="font-weight:400;">The AI tracks patients from the moment they are admitted to hospital until the moment they are discharged.</li> <li style="font-weight:400;">Called the Targeted Real-Time Early Warning System</li> </ul> </li> <li style="font-weight:400;">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.</li> <li style="font-weight:400;">Developed and deployed in collaboration with Johns Hopkins spinoff Bayesian Health, the tool