RESUMEN
Nowadays, considering society's highly demanding lifestyles, it is important to consider the usefulness of relaxation from the perspective of both psychology and clinical practice. The response towards relaxation (RResp) is a mind-body interaction that relaxes the organism or compensates for the physiological effects caused by stress. This work aims to automatically detect the different mental states (relaxation, rest and stress) in which RResps may occur so that complete feedback about the quality of the relaxation can be given to the subject itself, the psychologist or the doctor. To this end, an experiment was conducted to induce both states of stress and relaxation in a sample of 20 university students (average age of 25.76 ± 3.7 years old). The electrocardiographic and electrodermal activity signals collected from the participants produced a dataset with 1641 episodes or instances in which the previously mentioned mental states take place. This data was used to extract up to 50 features and train several supervised learning algorithms (rule-based, trees, probabilistic, ensemble classifiers, etc.) using and not using feature selection techniques. Besides, the authors synthesised the cardiac activity information into a single new feature and discretised it down to three levels. The experimentation revealed which features were most discriminating, reaching a classification average accuracy of up to 94.01 ± 1.73 % with the 6 most relevant features for the own-collected dataset. Finally, being restrictive, the same solution/subspace was tested with a dataset referenced in the bibliography (WESAD) and scored an average accuracy of 90.36 ± 1.62 %.
RESUMEN
Autonomic dysreflexia (AD) is a life-threatening condition for individuals with cervical or high-thoracic spinal cord injury (SCI). The profile of autonomic dysfunction in AD using validated clinical autonomic tests has not been described so far, although it could be useful to identify SCI patients at greater risk of developing AD non-invasively. With this objective, 37 SCI patients (27% female) were recruited, and hemodynamic and cardiac parameters were continuously monitored to determine the presence of AD, defined as an increase of systolic blood pressure of 20 mmHg or higher after bladder filling with saline. Then, standard autonomic function testing was performed, including Deep Breathing, Valsalva Manoeuvre and Tilt Table Test. Finally, baroreflex sensitivity (BRS), and spectral analysis of heart rate and blood pressure variability were measured at rest. Catecholamines and vasopressin levels were also measured at supine and upright positions. The severity of SCI was assessed through clinical and radiological examinations. AD was observed in 73.3% of SCI patients, being 63.6% of them asymptomatic during the dysreflexive episode. AD patients displayed a drop in sympathetic outflow, as determined by decreased noradrenalin plasma levels, reduced sympathovagal balance and increased BRS. In line with decreased sympathetic activity, the incidence of neurogenic orthostatic hypotension was higher in AD patients. Our results provide novel evidence regarding the autonomic dysfunction in SCI patients with AD compared to non-AD patients, posing non-invasively measured autonomic parameters as a powerful clinical tool to predict AD in SCI patients.
