Introduction: Heart failure (HF) is associated with high rates of mortality and hospital readmission. Current strategies for risk stratification are limited. Recently, we introduced EntropyX, a novel measure of non-linear patterns underlying physiological variability using newer concepts of entropy estimation and machine learning. EntropyX of cardiac repolarization (EntropyX QT ) enhanced the predictive value of all established risk factors in a multicenter study of HF patients (PMID: 27044982). Herein, we test the hypothesis that EntropyX of ventricular activation (EntropyX RR ) during sleep enhances the performance of established mortality risk factors in asymptomatic community adults with HF. We interpret our results in context of fundamental mechanistic studies in animal models and modern theories of systems biology. Methods & Results: We followed 96 NYHA class I HF adults in sinus rhythm for 6.5±3.0 years (1994-2011; SHHS NCT#00005275). Baseline exposures included demographics, history, medications, labs, PSG metrics [e.g., sleep disordered breathing (SDB)], ECG analyses [e.g., heart rate (HRV), QT variability (QTV)], and EntropyX RR . The cohort had mean age of 70±10 years, 49% women, 11% African Americans, and 46 deaths (48%; N=35 from cardiovascular events) over 4.6±2.6 years. After adjusting for exposures, the adjusted hazard ratios (4th to 1st quartile) for mortality for EntropyX RR was 2.3 (95% CI, 1.1-4.6) and age was 4.5 (1.9-10.3), consistent with machine learning-based classification and regression tree analysis. Addition of EntropyX RR to a multivariate model (comprised of age, diabetes, myocardial infarction, SDB) improved continuous net reclassification by 43% (37-48). Conclusions: EntropyX RR during sleep predicts mortality over follow-up of asymptomatic community adults with HF, independent of conventional risk factors and linear/deterministic measures (e.g., HRV, QTV, SDB). Unlike simpler concepts of RR variability, EntropyX RR is a fundamentally different measure, reflecting the complexity of multi-directional physiological network properties that regulate homeostatic function under changing conditions. This new paradigm complements conventional measures of risk and has potential for broad application.