A regression approach based on separability maximization for modeling a continuous-valued stress index from electrocardiogram data. (September 2018)

• Record Type: Journal Article
• Authors: Teixeira Ribeiro, Rui; Silva Cunha, João Paulo
• Is Part Of: Biomedical signal processing and control. Volume 46(2018)
• Page Start: 33
• Page End: 45
• Publication Date: 2018-09
• Subjects: Stress index -- Electrocardiogram -- Heart rate variability -- Linear discriminant analysis -- Bhattacharyya distance -- Regression; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2018.06.006
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A regression approach based on separability maximization (RASMa) is proposed. RASMa combines linear discriminant analysis (LDA) with the Bhattacharyya distance. RASMa was employed to model a continuous-valued stress index in individuals. Heart rate variability (HRV) features were used in the stress index model. A pilot study with 26 subjects was conducted with promising results. Abstract: In this work we propose a regression approach based on separability maximization (RASMa) for modeling a continuous-valued estimate of the stress level (we called it stress index) using some features extracted from electrocardiogram (ECG) data. Since no objective measure of the actual stress level (output) is available, finding the stress index cannot be addressed as a classical regression problem. Instead, the proposed approach finds the linear combination of features that maximizes the separability of stress index values for non-stress and stress events. In short, RASMa combines linear discriminant analysis with the Bhattacharyya distance, embedded in a leave-one-subject-out cross-validation scheme. A 26-case pilot study using 17 heart rate variability (HRV) features was conducted as a proof of concept. A near real-time application tool for monitoring stress level over time was also implemented based on the model obtained from the pilot study.