Using data collected from patients’ vital signs, researchers at the University of Florida have designed an artificial intelligence system that can accelerate and focus physician decision-making during the crucial early stages of treatment. hospitalization.
The algorithm works by taking torrents of data from six vital signs measured within six hours of hospital admission. It then concentrates that data into one of four distinct groups, giving doctors clearer, faster, and more accurate insight into a patient’s prognosis and likely medical outcomes. The results were published Oct. 13 in the journal PLOS Digital Health.
The approach uses artificial intelligence to analyze patient data faster and more thoroughly than physicians, said Azra Bihorac, MD, senior associate dean for research affairs at UF College of Medicine and director of the UF’s Intelligent Critical Care Center. Within hours, the system can identify patients at risk of poor outcomes.
“This system has the potential to speed up physicians’ decision-making as well as make it more accurate,” Bihorac said.
The findings are the result of a collaboration between a dozen UF researchers specializing in surgery, computer science, medicine, anesthesiology and biomedical engineering.
To evaluate the system, the researchers used an anonymized database of adult patients admitted to UF Health Shands hospital between 2014 and 2016. The algorithm was validated and tested using data from nearly 100,000 people. of all age groups.
When machine learning, a type of artificial intelligence, was applied to routine early vital signs data, the system identified patients with unique disease categories and distinct clinical outcomes. The patients were then grouped into one of four separate “groups”. Patients assigned to either group showed early signs of low blood pressure, increased heart activity, and low-grade inflammation. Although these conditions can be serious in their early stages, they also have the potential to resolve and lead to favorable outcomes. The algorithm grouped other patients into another group most likely to have chronic kidney disease and cardiovascular disease. They were also more likely to die within three years, the researchers found.
The value of the algorithm lies in its ability to quickly collect and analyze multiple patient data points, Bihorac said. For example, low blood pressure can be an early indicator of various future medical issues. When combined with other patient data and analyzed by an algorithm, doctors have a clearer picture of the patient’s trajectory.
“It’s really like a warning sign. Within six hours, this can help identify patients who may not have a good outcome. This tells us which patients are at risk of deteriorating and which need more attention immediately,” she said.
Next, Bihorac said she is seeking additional grants that will allow the team to further study the system and possibly test its effectiveness in currently hospitalized patients. Such a system could likely be deployed without significant cost, she said.
“It’s such a simple and elegant solution. It takes data that is already collected and uses it to its full potential for the benefit of the patient,” Bihorac said.
Colleagues at UF Intelligent Critical Care Center who have made notable research contributions include Yuanfang Ren, Ph.D., computer expert and science assistant at UF College of Medicine; Tyler J. Loftus, MD, assistant professor in the department of surgery; and Gilbert R. Upchurch, MD, professor and chair of the department of surgery, Bihorac said.
The research was supported by several grants from the National Institutes of Health, the National Science Foundation and the University of Florida.
Media contact: Doug Bennett, email@example.com, 352-265-9400
#researchers #system #doctors #insight #patient #status