Wearing an adhesive patch sensor that streams data to an analytical platform can accurately predict worsening heart failure (HF) and the need for hospitalisation several days before it is necessary, according to research published in Circulation: Heart Failure.
The LINK-HF study (Multisensor non-invasive remote monitoring for prediction of heart failure) examined the performance of a personalised analytical platform using continuous data streams to predict rehospitalisation after HF admission. The multicentre study enrolled 100 HF patients, all of whom were veterans, with an average age of 68 years at four Veterans Affairs (VA) hospitals—in Salt Lake City, Palo Alto, Houston, and Gainesville—after an initial acute HF admission. Study subjects were fitted with a wearable sensor (Vital Connect) secured on their chest by an adhesive surface. The unit has two electrodes facing the skin used for ECG detection and collects continuous echocardiogram (ECG) waveform and three-axis accelerometry.
The sensor patch was paired via bluetooth with an android phone, to which data from the sensors were continuously streamed. Participants wore the sensor on their chest for 24 hours a day for a minimum of 30 days and up to three months after their initial hospital discharge for a heart failure event. Of the eligible participants, 90% continued to wear the sensor at 30 days, and at 90 days; data were collected from August 2015 through December 2016.
The cloud-based analytics platform, developed by PhysIQ, used data from the sensor to derive heart rate, heart rhythm, respiratory rate, walking, sleep, body posture and other normal activities. Using artificial intelligence, the platform established a normal baseline for each patient. When the data deviated from normal, the platform generated an indication that the patient’s heart failure was getting worse.
The clinical event of interest was hospital readmission after the index discharge from the HF exacerbation hospitalisation. The study team examined hospitalisations due to worsening HF and all unplanned, non-trauma related hospitalisations.
Results from the study show that a total of 27 HF hospitalisations took place during the 90 days of follow-up. The analytic platform predicted the HF hospitalisations with a sensitivity of 87% and specificity of 85%, at a median time of 6.5 days before the hospitalisation took place. The investigators state that this interval should provide sufficient time for an intervention aimed at preventing hospitalisation.
“With the use of remote data from the sensor and through data analysis by machine learning, we have shown that we can predict the future. Next, we will look at whether we can change the future,” said lead study author Josef Stehlik from the Salt Lake City Veterans Affairs Medical Center and the University of Utah School of Medicine (Salt Lake City, USA).
“In chronic heart failure, a person’s condition can get worse with shortness of breath, fatigue and fluid build-up, to the point many end up in the emergency room and spend days in the hospital to recover,” said Stehlik. “If we can identify patients before heart failure worsens and if doctors have the opportunity to change therapy based on this novel prediction, we could avoid or reduce hospitalisations, improve patients’ lives and greatly reduce health care costs. With the evolution of technology and with artificial intelligence statistical methods, we have new tools to make this happen.”
In a future study, the researchers will test changing patient treatment based on the alert generated by the algorithm. “We are hoping that with this information, we can intervene and decrease the hospitalisation rate, improve quality of life, and, for patients who end up being admitted to the hospital, shorten the length of stay,” Stehlik said.
Limitations of the study were noted to include that study participants were 98% male, so it is not known if the findings would be consistent in females. Additionally, a majority of the participants had heart failure with reduced ejection fraction (HFrEF), so further study in patients with HFpEF is needed. And, additional research is necessary to determine if treatment changes based on the alerts could lead to improved patient outcomes, the study team note.
The Department of Veterans Affairs Office of Information & Technology and VHA Innovation Ecosystem funded the study. PhysIQ developed the analytics platform.