A wearable sensor that works with artificial intelligence (AI) to help doctors remotely detect critical changes in heart failure patients days before a health crisis occurs has been developed by researchers at University of Utah Health and VA Salt Lake City Health Care System.

The researchers say the system could eventually help avert up to one in three heart failure readmissions in the weeks following initial discharge from the hospital and help patients sustain a better quality of life.

“This study shows that we can accurately predict the likelihood of hospitalisation for heart failure deterioration well before doctors and patients know that something is wrong,” said the study’s lead author, Josef Stehlik, co-chief of the advanced heart failure programme at University of Utah Health. “Being able to readily detect changes in the heart sufficiently early will allow physicians to initiate prompt interventions that could prevent rehospitalisation and stave off worsening heart failure.”

Stehlik also serves as medical director of the heart failure and heart transplant programme at George E Wahlen VA Medical Center in Salt Lake.

The study appears in Circulation: Heart Failure, an American Heart Association journal. 

About 6.2 million Americans live with heart failure and it is the top hospital discharge diagnosis in the USA. Up to 30% of these patients will likely be readmitted to the hospital within 90 days of discharge with recurrent symptoms including shortness of breath, fatigue and fluid build-up. In many cases, hospitalisation diminishes a patient’s ability to care for themselves independently.

“Those individuals who have repeated hospitalisations for heart failure have significantly higher mortality,” said Biykem Bozkurt, a study co-author and director of the Winters Center for Heart Failure Research at the Baylor College of Medicine in Houston. “Even if patients survive, they have poor functional capacity, poor exercise tolerance and low quality of life after hospitalisations. This patch, this new diagnostic tool, could potentially help us prevent hospitalisations and decline in patient status.”

Information is transmitted from the sensor via Bluetooth to a smartphone and then passed on to an analytics platform, developed by PhysIQ, on a secure server, which derives heart rate, heart rhythm, respiratory rate, walking, sleep, body posture and other normal activities. Using artificial intelligence, the analytics establishes a normal baseline for each patient. When the data deviate from normal, the platform generates an indication that the patient’s heart failure is getting worse.

In tests, the system accurately predicted the impending need for hospitalisation more than 80 per cent of the time. On average, this prediction occurred 10.4 days before a readmission took place (median 6.5 days).

“There’s a high risk for readmission in the 90 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, and the overall quality of their lives will be better with the help of this technology.”

Next, the researchers plan to conduct a large clinical trial that will not only use the system to alert doctors of changes in a patient’s condition but also track if early intervention based on these alerts leads to fewer rehospitalisations for heart failure.

In addition to Stehlik and Bozhurt, University of Utah Health researchers Jose Nativi-Nicolau, Peter Wohlfahrt and Heather Hanson contributed to this study. Collaborators from other institutions include C Schmalfuss, S Wegerich, K Rose, R Ray, R Schofield, A Deswal, S Anand, H Hanson, D Richards, M Pipke, J Sekaric and M Phram. The Department of Veterans Affairs Office of Information & Technology and VHA Innovation Ecosystem funded the study. PhysIQ developed the analytics platform. Pipke, Wegerich, Rose, Anand, Sekaric and Richards are employed by PhysIQ. Stehlik is a consultant to Medtronic and Abbo.