Quantitative assessment for self-tracking of acute stress based on triangulation principle in a wearable sensor system

Wanqing Wu, Sandeep Pirbhulal, Heye Zhang, Subhas Chandra Mukhopadhyay

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

Due to the variation in factors surrounding humans, the physiological impact of stress is reported to be different for each individual. Thus, an efficient stress monitoring system needs to assess both the physiological and psychological impact of stress on individual basis and translate these assessments into an accurate quantitative metric that is of value to the individual. Therefore, this study proposed a logistic regression based model that integrates data from psychological Stress Response Inventory, biochemical (salivary cortisol), and physiological (HRV measures) domains via a principle of triangulation for achieving high reliability and consistency during stress assessment. With the proposed model, a mental stress index (MSI) based on the correlation between salivary cortisol and HRV time-/frequency-domain features were established. A total of 30 college students were recruited to verify the feasibility of proposed method by identifying targeted stressful event. The obtained results reveal that MSI values were sensitive to acute stress, and could predict the association level of normal individual to a stress group with approximately 97% accuracy. Findings from this study could provide potential insight on self-tracking and training of individual's stress with adoption of wearable sensor system in a dynamic setting.

Original languageEnglish
Pages (from-to)703-713
Number of pages11
JournalIEEE Journal of Biomedical and Health Informatics
Volume23
Issue number2
Early online date1 May 2018
DOIs
Publication statusPublished - Mar 2019

Fingerprint Dive into the research topics of 'Quantitative assessment for self-tracking of acute stress based on triangulation principle in a wearable sensor system'. Together they form a unique fingerprint.

  • Cite this