Prediction of Heart Failure Events With the HeartLogic Algorithm: Real-World Validation

HeartLogic is an algorithm that uses implantable cardioverter-defibrillator (ICD)/cardiac resynchronization therapy-defibrillator (CRT-D) sensor data for the prediction of heart failure (HF) events. The algorithm integrates heart sounds, respiration, thoracic impedance, heart rate, and activity measures. When early changes suggestive of decompensation are identified alerts are sent remotely to healthcare providers. The algorithm was developed and validated in separate cohorts of CRT-D patients from the MultiSENSE study.1 In the present study we sought to revalidate algorithm performance in an independent cohort, including ICD patients, by using a novel real -world data approach.