Infections can trigger all kinds of reactions in the human body, and one of the most extreme is sepsis. This life-threatening complication causes more than 250,000 deaths in the United States each year, but a new artificial intelligence system developed at Johns Hopkins University promises to make a real difference in this area, by detecting the main symptoms early. .
Sepsis occurs as a result of an infection that triggers a severe immune response in the body. This triggers a sequence of events that begins with widespread inflammation and can end in blood clots, leaky blood vessels, organ failure, or death. Obvious symptoms like fever or confusion can be misinterpreted as symptoms of other conditions, making it difficult to diagnose the disease in its early stages.
And that’s critical, because a patient with sepsis can deteriorate rapidly, with the disease killing around 30% of those who develop it. We have seen some promising technologies aimed at improving the odds in these situations by clearly and quickly detecting sepsis. These include devices that capture key biomarkers in the blood within minutes and tools to quickly spot the pathogens causing the initial infection.
The Johns Hopkins team took a different approach, seeking to leverage advanced artificial intelligence to identify at-risk patients. It does this by analyzing a patient’s medical history and combining it with current symptoms, clinical notes, and lab results. Called the Targeted Real-Time Early Warning System, the AI tracks patients from the time they are admitted to the hospital to the time they are discharged. By monitoring them in this way, the system is designed to ensure that no important or potentially dangerous medical details slip through the cracks.
Developed and deployed in collaboration with Johns Hopkins spin-off Bayesian Health, the tool has been used in five hospitals in a two-year trial, involving more than 700,000 patients. In this bedside setting, the early warning system is designed to send alerts to physicians and healthcare providers when there is cause for concern. According to the researchers, the system proved to be very effective, leading to the detection of sepsis on average almost six hours earlier than traditional methods, with a sensitivity rate of 82%. It has also driven a high adoption rate among healthcare providers of 89%.
This resulted in significant reductions in morbidity, length of hospitalization and, most importantly, an 18.2% reduction in mortality.
“There aren’t many things left in medicine that have a 30% mortality rate like sepsis,” said Neri Cohen, MD, PhD, president of the Center for Healthcare Innovation that collaborated with the researchers. “What makes it so upsetting is that it is relatively common and we have yet made very little progress in recognizing it early enough to materially reduce morbidity and mortality. Reducing mortality by almost 20% is remarkable and translates into many lives saved.”
Researchers are also adapting bedside technology to detect other conditions, such as pressure ulcers or acute respiratory failure.
“This is the first instance where AI is being implemented at the bedside, used by thousands of providers, and where we’re seeing lives saved,” said Suchi Saria, lead author of the studies. “This is an extraordinary leap that will save thousands of sepsis patients each year. And the approach is now being applied to improve outcomes in other important problem areas beyond sepsis.”
The research was published in a trio of articles in Nature Digital Medicine and natural medicine , [2.]
Sources: Johns Hopkins University, Bayesian Health