Abstract
Prediction of mental states, such as stress and anxiety, can be important in situations where reduced job performance due to increased mental strain can lead to critical situations (e.g., front-line healthcare workers and first responders). While recent advances in biomedical wearable sensor technologies have allowed for collection of multiple physiological signals in everyday environments, numerous challenges emerge from such uncontrolled settings, including increased noise levels and artifacts, confounding effects from other psychological states (e.g., mental fatigue), as well as physical variables (e.g., physical activity). These factors can be particularly detrimental for heart rate variability (HRV) measures which, in controlled settings, have been shown to accurately track stress and anxiety states. In this paper, we propose two new ways of computing HRV proxies which we show are more robust to such artifacts and confounding factors. The proposed features measure spectral and complexity properties of different aspects of the autonomic nervous system, as well as their interaction. Across two separate “in-the-wild” datasets, the proposed features showed to not only outperform benchmark HRV metrics, but to also provide complementary information, thus leading to significantly greater accuracy levels when fused together. Feature ranking analysis further showed the proposed features appearing in 45–64% of the top features, thus further emphasizing their importance. In particular, features derived from the high frequency band showed to be most important in the presence of fatigue and physical activity confounding factors, thus corroborating their importance for mental state assessment in highly ecological settings.
Highlights
The COVID-19 pandemic has put tremendous pressure on healthcare systems worldwide, leading to increased cases of burnout (Kannampallil et al, 2020; Sultana et al, 2020) in frontline healthcare workers
“Band-All” corresponds to the fusion of band -spectral and complexity features, “Fuse-Complexity” to fusion of benchmark set with band-complexity features, “Fuse spectral” to fusion of benchmark set with band-spectral features, “Fuse RR-Complexity” to fusion of benchmark set with RR complexity features, “Fuse-Band-All” to fusion of benchmark set with “Band-All” features, and “Fuse-All” to the fusion of all extracted features sets
We propose novel heart rate variability (HRV) features for in-the-wild mental state monitoring applications
Summary
The COVID-19 pandemic has put tremendous pressure on healthcare systems worldwide, leading to increased cases of burnout (Kannampallil et al, 2020; Sultana et al, 2020) in frontline healthcare workers. HRV Features for Mental State Monitoring increased instances of depression worldwide (Choi et al, 2020; Dozois, 2020; Hyland et al, 2020). Even before the COVID-19 pandemic, mental health problems were already on the rise worldwide. It was already projected that the economic burden due to poor mental health worldwide would grow six-fold in the 30 years (Doran and Kinchin, 2019). These trends clearly highlight the need for automated mental state monitoring systems (Zhou et al, 2020) that can be used in everyday environments
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
