A Within-Subject Normal-Mixture Model with Mixed-Effects for Analyzing Heart Rate Variability.

Data on heart rate variability (HRV) have been used extensively to indirectly assess the autonomic control of the heart. The distributions of HRV measures, such as the RR-interval, are not necessarily normally distributed and current methodology does not typically incorporate this characteristic. In this article, a mixed-effects modeling approach under the assumption of a two-component normal-mixture distribution for the within-subject observations has been proposed. Estimation of the parameters of the model was performed through an application of the EM algorithm, which is different from the traditional EM application for the normal-mixture methods. An application of this method was illustrated and the results from a simulation study were discussed. Differences among other methods were also reviewed.