Key result
Electrodermal activity and skin temperature measured by wearable sensors achieved an area under the curve greater than 0.95 for identifying stress states.
Why the study?
To improve the productivity of individuals by identifying stress, including positive or negative stress.
Observational (n=12)
No
Effect estimate: AUC > 0.95
Non-invasive wearable sensors measuring electrodermal activity and skin temperature can accurately identify the presence and type (positive vs. negative) of stress using machine learning, which may help optimize task allocation and productivity.
Wearable EDA and temperature signals show promise for stress detection; hypothesis-generating and requires prospective clinical validation.
To improve the productivity of individuals, this study proposes a method to identify stress, which is also divided into positive or negative one. The method takes features in the time course into account. The paper presents important variables to estimate stress states. Whether the proposed method can identify stress states is confirmed through experiments, whose details are explained in the paper. The paper also discusses how to use non-invasive and low-cost wearable sensors along with the method.
No takes yet. Share an insight, caveat, or question.
Wakabayashi et al. (2022) conducted an observational in Stress (n=12). Wearable sensors (electrodermal activity and skin temperature) vs. Other physiological signals was evaluated on Stress state classification (AUC) (AUC > 0.95). Electrodermal activity and skin temperature measured by wearable sensors achieved an area under the curve greater than 0.95 for identifying stress states.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: