Gentili C, et al. – The current study was expected to explore whether Heart Rate Variability (HRV)–multi–feature analysis discriminates cardiac surgery patients (CSP) with or without depression and provides an effective estimation of symptoms severity. Based on the results of the present study, the high informative power of HRV–nonlinear metrics suggested their possible pathophysiological role both in depression and in coronary heart disease (CHD). Findings revealed that the high–accuracy of the algorithm at single–subject level opens to its translational use as a screening tool in clinical practice.

Methods

• For the purpose of this study, 31 patients admitted to cardiac rehabilitation after first-time cardiac surgery were enrolled.
• After that, depressive symptoms were surveyed with the Center for Epidemiologic Studies Depression Scale (CES-D).
• Finally, HRV features in time, frequency, and nonlinear domains were extracted from 5-min-ECG recordings at rest and used as predictors of “least absolute shrinkage and selection” (LASSO) operator regression model to estimate patients' CES-D score and to foresee depressive state.

Results

• The study results showed that the model significantly anticipated the CES-D score in all subjects (the total explained variance of CES-D score was 89.93%).
• Additionally it separated depressed and non-depressed CSP with 86.75% accuracy.
• It was noted that 7 of the 10 most informative metrics belonged to non-linear-domain.