Automatic identification of rapid eye movement sleep based on random forest using heart rate variability

There is broad evidence that the abnormality of rapid eye movement (REM) sleep may be an indicator of some diseases. The scientific identification of REM sleep thus plays a vital role in sleep medicine. Since the activity of autonomic nervous system (ANS) which can be reflected in heart rate variability (HRV) was associated with sleep states, we aimed to develop an automatic REM detecting system based on HRV analysis and machine learning. HRV signals which derived from 45 healthy participants were adopted and 69 HRV features were extracted and fed into a random forest (RF) classifier. We compared different strategies for the segmentation of HRV time series. The results showed a relative good classification performance by segmenting the whole record into overlapping sections, suggesting that the Surrounding Strategy overwhelms the Truncating one in RF based REM identification. Moreover, the classification performance exhibited a non-monotonic trend along with the length of the symmetric surrounding window. When there was 390 data points in such a window, we got the best performance to distinguish REM and non-REM sleeps with an accuracy of 0.84, a sensitivity of 0.80, a specificity of 0.88, a positive predictive value of 0.90, a negative predictive value of 0.85 and a kappa coefficient of 0.68. Our study showed the promising application of HRV-based methods in REM detecting, and furthermore, we threw light on the scientific segmentation of HRV signals in sleep staging. As the Surrounding strategy proposed in this study makes it possible to produce enough learning samples, our results may bring more impetus on machine learning-based algorithm, such as deep learning in this field.