Analysis of heart rate (HR) variability has become an important widely used method for assessing cardiac autonomic regulation. Conventionally, HR variability has been analyzed with time and frequency domain methods. Analysis of HR dynamics by methods based on nonlinear systems theory has opened a novel approach for studying the abnormalities in HR behavior. Recent studies have shown that these measures, particularly scaling analysis methods of HR dynamics, are altered among various patients populations with cardiovascular diseases, and they provide prognostic information. Altered long-term scaling properties of HR dynamics and more random short-term HR fluctuation has been observed, e.g., among patients with previous myocardial infarction, and these alterations have been shown to be associated with increased mortality rate. A relatively large body of data indicate that altered scaling properties of R-R intervals are physiologically deleterious. These findings support the notion that some nonlinear methods, such as scaling and complexity measures, give clinically valuable information for risk stratification among various patient populations. This article provides a review of our current knowledge of the usefulness of dynamical measures of HR fluctuation.