An HRV-multi-feature approach for assessing depressive symptoms in cardiosurgical patients

Background: Heart Rate Variability (HRV) is reduced both in depression and in coronary heart disease (CHD) suggesting common pathophysiological mechanisms for the two disorders. Within CHD, cardiac surgery patients (CSP) affected by postoperative depression are at greater risk of adverse cardiac events. Therefore, CSP require special attention in order to perform an early diagnosis of depression. In the present study we tested whether HRV multi-feature analysis could discriminate CSP with or without depressive symptoms and provide an effective estimation of symptoms severity. Methods: Thirty-one patients admitted to cardiac rehabilitation program after first-time cardiac surgery were recruited. Depressive symptoms were assessed with the Center for Epidemiologic Studies Depression Scale (CES-D). 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 predict their depressive state. Findings: The model significantly predicted the CES-D score in all subjects as the mean square error (total explained variance of CES-D score was 89.93%). The model also discriminated depressed and non-depressed CSP with 86.75% overall accuracy. Seven of the ten most informative metrics belonged to non-linear-domain. Discussion: To our knowledge this is the first study using a multi-feature approach to evaluate depression in CSP. The high informative power of HRV-nonlinear metrics suggests their possible pathophysiological role both in depression and in CHD. The high-accuracy of the algorithm at single-subject level opens to its translational use as screening tool in clinical practice