Automatic Methods for the Detection of Accelerative Cardiac Defense Response

• Published in: IEEE transactions on affective computing Vol. 7; no. 3; pp. 286 - 298
• Main Authors: Gravina, Raffaele, Fortino, Giancarlo
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.07.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acceleration; Activation; Algorithms; Automation; Cardiac defense response; Computation; Disorders; ECG analysis; Electrocardiography; Emotion recognition; Health; Heart rate; Methods; pattern recognition; Physiology; Psychology; Reflexes; startle reflex; Stimuli; Stress
• ISSN: 1949-3045; 1949-3045
• DOI: 10.1109/TAFFC.2016.2515094

Cardiac Defense Response (CDR) is a basic psycho-physiological response related to startle reflex and preceding negative emotional states including fear. In the health-care context, the definition of methods to automatically identify the CDR is a relevant issue, because frequent CDR activations (not associated to proper danger stimuli) can pose the subject to health risk and eventually develop into severe psychophysical disorders. Therefore, providing tools for automatic identification of this defense mechanism can significantly help psychologists and caregivers in understanding the patient's mental and health status as well as patients themselves to self-regulate and self-control against excessive defense and stress responses. This work discusses and compares different methods and specifically proposes a novel algorithm designed to detect the CDR by analyzing the electrocardiogram (ECG) signal. It is based on the extraction of specific features from a signal, directly generated from the ECG, which are compared against an ad-hoc computed reference CDR template. The proposed method has been tested on real ECG traces, a number of them containing full activations of the CDR pattern, and compared against other techniques, discussed in the paper, reaching an improvement of 10 percent in sensitivity, 18 percent in specificity, and 24 percent in precision with respect to the best performance of the other related methods.