AI-Powered Wearable Predicts Heart Failure Before It Happens

Wearable sensors like this one could help doctors remotely detect cardiovascular changes in heart failure patients days before a crisis occurs (via Charlie Ehlert/University of Utah Health)

A new wearable sensor could save the lives of heart-failure patients.

The artificially intelligent technology helps doctors remotely detect critical changes days before a crisis occurs.

It may even prevent hospitalization, according to a study by University of Utah Health and VA Salt Lake City Health Care System scientists.

“This [device] can accurately predict the likelihood of hospitalization for heart failure deterioration well before doctors and patients know that something is wrong,” lead author Josef Stehlik, co-chief of the advanced heart failure program at U of U Health, said in a statement.

More than 6 million Americans live with heart failure—the top hospital discharge diagnosis in the US. Recurrent symptoms will land as many as 30 percent of those patients back in the hospital within 90 days of discharge.

But folks with repeated hospitalizations for heart failure also suffer from significantly higher mortality rates.

“Even if patients survive, they have poor functional capacity, poor exercise tolerance, and low quality of life,” study co-author Biykem Bozkurt, director of the Winter Center for Heart Failure Research at the Baylor College of Medicine, said. “This patch, this new diagnostic tool, could potentially help us prevent hospitalizations and decline in patient status.”

In initial tests, information collected by the wearable was transmitted via Bluetooth to a smartphone and passed on to a secure analytics platform, which extrapolates heart rate, heart rhythm, respiratory rate, walking, sleep, body posture, and other normal activities.

Using AI, the system establishes a baseline for each patient. When data deviates from “normal,” the platform generates a warning that that person’s heart failure is worsening.

Overall, the system accurately predicted an impending need for hospitalization more than 80 percent of the time; on average, the warning came 10 days before readmission.

“There’s a high risk for readmission in the 90s days after initial discharge,” Stehlik said. “If we can decrease this readmission rate through monitoring and early intervention, that’s a big advance.

“We’re hoping even in patients who might be readmitted that their stays are shorter,” he continued. “And the overall quality of their lives will be better with the help of this technology.”

The full study was published this week in American Heart Association journal Circulation: Heart Failure.

Moving forward, researchers plan to conduct a large clinical trial using the system to alert doctors of changes in a patient’s condition and track whether the alerts actually lead to fewer rehospitalizations for heart failure.

More on Geek.com:



from Geek.com https://ift.tt/2PwelVD
via IFTTT

0 comments:

Post a Comment