Linear and nonlinear indices of heart rate variability (HRV) have been shown to predict mortality in congestive heart failure (CHF). However, most nonlinear indices describe only the fractality or complexity of HRV but not the intrinsic chaotic properties. In the present study, we performed linear (time- and frequency-domain), complexity (sample entropy), fractal (detrended fluctuation analysis) and chaos (numerical titration) analyses on the HRV of 50 CHF patients from the United Kingdom heart failure evaluation and assessment of risk trial database. Receiver operating characteristic and survival analysis yielded the chaos level to be the best predictor of mortality (followed by low/high frequency power ratio, LF/HF), such that these indices were significant in both univariate and multivariate models. These results indicate the power of heart rate chaos analysis as a potential prognostic tool for CHF.