Feb. 25 (UPI) -- A wearable sensor may be able to detect -- and thus prevent -- a major health emergency in patients with heart failure, according to a study published Tuesday in the journal Circulation: Heart Failure.
Researchers at University of Utah Health and VA Salt Lake City Health Care System say the new device, worn as a patch, uses artificial intelligence to help doctors detect critical changes in heart failure patients days before an actual heart-related emergency, like a heart attack, occurs.
The system could eventually prevent as many as one in three hospital re-admissions for heart failure in the weeks following initial discharge.
This alone would have a huge, and positive, impact on the quality of life of these patients, researchers say.
"This study shows that we can accurately predict the likelihood of hospitalization for heart failure deterioration well before doctors and patients know that something is wrong," study co-author Josef Stehlik, co-chief of the advanced heart failure program at University of Utah Health, said in a press release. "Being able to readily detect changes in the heart sufficiently early will allow physicians to initiate prompt interventions that could prevent re-hospitalization and stave off worsening heart failure."
Approximately 6.2 million Americans have heart failure, and it is the top hospital discharge diagnosis in the United States, according to the American Heart Association. As many as 30 percent of patients discharged from the hospital with heart failure are readmitted within 90 days due to recurrent symptoms like shortness of breath, fatigue and fluid buildup.
"Even if patients survive, they have poor functional capacity, poor exercise tolerance and low quality of life after hospitalizations," noted co-author Biykem Bozkurt, director of the Winters Center for Heart Failure Research at the Baylor College of Medicine in Houston. "This patch, this new diagnostic tool, could potentially help us prevent hospitalizations and decline in patient status."
Stehlik, Bozkurt and colleagues monitored 100 heart failure patients who had been diagnosed and treated at four VA hospitals in Salt Lake City and Houston, as well as in Palo Alto, Calif., and Gainesville, Fla. Following their discharge, study participants wore an adhesive sensor patch on their chests 24 hours a day for up to three months.
The device tracked the continuous electrocardiogram, or ECG, and motion of each study participant, and transmitted the data collected via Bluetooth to a smartphone, which in turn passed it on to an analytics platform, developed by PhysIQ. Housed on a secure server, the software calculated and stored data on heart rate, heart rhythm, respiratory rate, walking, sleep, body posture and other normal activities for each participant and, using AI, established a normal baseline for each patient.
When the data deviated from normal, the platform generated an indication to doctors that the patient's heart failure was getting worse. Overall, the researchers found, the system accurately predicted the need for hospitalization more than 80 percent of the time, and 10.4 days before a readmission took place.
The researchers plan to conduct a large clinical trial that will use the system to alert doctors of changes in a patient's condition, as well as track if early intervention based on these alerts leads to fewer re-hospitalizations for heart failure.
"We're hoping even in patients who might be readmitted that their stays are shorter, and the overall quality of their lives will be better with the help of this technology," Stehlik said.