New York, researchers have developed an artificial intelligence (AI) tool to predict the life expectancy of patients with heart failure.
The machine learning algorithm, based on de-identified electronic health, records data for 5,822 hospitalized or ambulatory patients at UC San Diego Health in the United States.
“We wanted to develop a tool that predicts life expectancy for patients with heart failure, with apps where algorithms are looking for all sorts of things you want to buy,” said University of California professor Avi Yagill. .
“We needed similar tools to make medical decisions. It’s important to predict mortality in patients with heart failure. Current risk prediction strategies are only moderately successful and can be subjective,” Yagil added.
From this model, a risk score was obtained that determined the low and high risk of death by detecting eight readily available variables for most heart disease patients: diastolic blood pressure, creatinine, blood urea nitrogen, white blood cell count, platelets, albumin and red blood cells. Distribution of blood vessels.
Yagill said the newly developed model was able to accurately predict life expectancy 88 percent of the time, and performed better than other popular published models.
“This tool gives us insight, for example, about the likelihood that a given patient will die of heart failure in the next three months or a year,” says researcher Eric Adler.
“It is incredibly valuable এটি It allows us to make informed decisions based on proven methodology and does not need to look at the crystal ball,” he added.
The tool was additionally examined using de-identified patient data from the University of California San Francisco and data bases obtained from 1 European Medical Center.
“It was a success on these teams as well,” said Yagil.
Yagil adds, “It is important to be able to reconsider our discoveries in an independent community, thus validating our approach and its results.”
The researchers stated that the partnership between physicists and cardiologists was a reliable tool and critical for developing broad knowledge and experience on both sides.
The study was published in the European Journal of Heart Failure.