FDA clears advanced AI model for predicting heart failure risk

Implicity, a U.S. company focused on remote monitoring technology for heart patients, has received clearance from the U.S. Food and Drug Administration (FDA) for a new artificial intelligence (AI) model that can anticipate heart failure events.

The new algorithm, SignalHF, was trained and validated using information from the Health Data Hub database. It uses machine learning to evaluate cardiac implantable electronic device (CIED) data—including information captured by implantable cardiac defibrillators, pacemakers and cardiac resynchronization therapy devices—and monitors patients for changes that suggest they face a heightened risk of heart failure or being hospitalized for heart failure in the near future.

If a patient’s symptoms start to get worse in a way that suggests a heart failure event may occur in the next few weeks, for example, SignalHF will send an automatic alert to their cardiologist and other members of the care team. Clinicians can then work to help prepare in advance and potentially even prevent the adverse event from happening.

“Heart failure remains a significant healthcare challenge, contributing to approximately one million hospitalizations each year,” electrophysiologist Arnaud Rosier, MD, PhD, Implicity’s CEO, said in a prepared statement. “Preventing even a portion of these would be a game-changer in cardiac care. SignalHF is an innovative and effective tool that physicians can use to assess risk of hospitalization due to heart failure earlier, enabling interventions that can lead to better outcomes and reduce hospital admissions.”

“Comprehensive heart failure management includes treatment, prevention, and personalization. Implicity's solution is part of this approach,” added Issam Ibnouhsein, Implicity’s head of data. “Our alerts are generated in context with a patient's medical profile to help personalize care management plans. Furthermore, 75% of the alerts preceding a patient hospitalization are sent at least 14 days in advance—offering a two-week window to adjust medications or take proactive measures.”

Michael Walter
Michael Walter, Managing Editor

Michael has more than 18 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.

Around the web

Ron Blankstein, MD, professor of radiology, Harvard Medical School, explains the use of artificial intelligence to detect heart disease in non-cardiac CT exams.

Eleven medical societies have signed on to a consensus statement aimed at standardizing imaging for suspected cardiovascular infections.

Kate Hanneman, MD, explains why many vendors and hospitals want to lower radiology's impact on the environment. "Taking steps to reduce the carbon footprint in healthcare isn’t just an opportunity," she said. "It’s also a responsibility."