Using HeartInsight Algorithm to Predict Acute Heart Failure in Patients with Biotronik ICD or CRT-D Devices Study of Real-World Clinical Use and Workflow

What this Trial Is About

This research investigates the real-world use of the HeartInsight algorithm, designed to predict acute heart failure events in patients with implanted Biotronik ICD or CRT-D devices that have atrial sensing and Home Monitoring capabilities. Heart failure is a serious condition with high rates of hospitalizations and healthcare costs. The HeartInsight algorithm, validated in previous studies, monitors trends in seven physiological parameters to provide early warnings about worsening heart failure, aiming to improve patient management by alerting healthcare providers well in advance. Patients enrolled in this prospective, multicenter observational registry will be followed for 12 months across approximately 14 centers in Italy. The study does not require additional diagnostic tests beyond standard care. When HeartInsight issues an alert, a standardized workflow guides clinical responses such as device adjustments, therapy changes, or extra visits. Patients may also choose to use the HeartInsight Patient App to assist in monitoring. The study collects data on how often alerts occur, the clinical actions taken, patient interviews, and hospitalizations. Participants will have their device data remotely monitored and attend regular clinical visits as part of routine care. Researchers will track the proportion of alerts that lead to clinical actions and measure secondary outcomes like alert frequency, duration of alert periods, patient interviews, hospitalizations, and app usage. Data are collected securely via electronic forms and monitored for quality. The study aims to provide insights into integrating predictive monitoring tools into everyday practice to potentially enhance heart failure care over a 12-month period.

heaRtInsiGHT Alert guIDE: RightAIDE Application of the HeartInsight Acute Heart Failure Predictor in Routine Clinical Practice: Organizational Models and Workflow.