Stress response index for traumatic childhood experience based on the fusion of hypothalamus pituitary adrenocorticol and autonomic nervous system biomarkers

• Main Authors: Salleh, N. A., Balakrishnan, M., Whitttaker, A. C.
• Format: Article
• Language: English
• Published: ASTES Publishers 2020
• Subjects: Q Science (General)
• Online Access: http://eprints.utm.my/id/eprint/87083/1/NoorAimieSalleh2020_StressResponseIndexforTraumaticChildhood.pdf; http://eprints.utm.my/id/eprint/87083/; http://www.dx.doi.org/10.25046/aj050140

Stress occurring in the early days of an individual was often assumed to cause several health consequences. A number of reports indicated that having to deal with unfavourable events or distress situation at a young age could tweak stress responses leading to a broad spectrum of poor mental and physical health condition. Therefore, changes identified within stress response were recommended to be taken as a measure in regulating and managing such health situation. This study combines the biomarker that represents both autonomic nervous system (ANS) and hypothalamic-pituitary-adrenocorticol (HPA) as a single measure to classify the stress response based on traumatic childhood experience and propose a stress response index as a future health indicator. Electrocardiograph (ECG), blood pressure, pulse rate and salivary cortisol (SCort) were collected from 12 participants who had traumatic childhood experience while the remaining 11 acted as the control group. The recording session was done during a Paced Auditory Serial Addition Test (PASAT). HRV was then computed from the ECG and the HRV features were extracted. Next, the best HRV features were selected using Genetic Algorithm (GA). Biomarkers such as BP, PR and SCort were then integrated with 12 HRV features picked from GA. The integrations were conducted using two fusion methods which are Euclidean distance and serial fusion. The differences in reaction of the fused features were then identified. Based on the result, the Euclidean distance (ed) which is the fused feature by the parallel fusion, displayed the most efficient reaction with accuracy, sensitivity, and specificity at 80.0%, 83.3% and 78.3%, respectively. Support Vector Machine (SVM) was utilized to attain such result. The fused feature performance was then fed into SVM which produced indexes on stress responses. The result retrieved from these indexes acts as a measure in handling future health deliverability and perhaps could eventually enhance the health care platform for midlife individuals.