Key result
Nonlinear features from non-EEG signals improve machine learning accuracy for detecting stress and neurological states.
Why the study?
Continuous stress monitoring is needed to prevent under-diagnosis, but popular EEG-based approaches are impractical for continuous remote monitoring during daily activities.
Does using nonlinear features from non-EEG data improve the accuracy of machine learning models in detecting different states of stress in healthy adults?
Does using nonlinear features from non-EEG data improve the accuracy of machine learning models in detecting different states of stress in healthy adults?
Nonlinear features from non-EEG wearable data improve the accuracy of stress detection models, potentially enabling continuous remote monitoring without complex algorithms.
May support wearable-based stress monitoring in healthy adults; leaves open validation in clinical populations.
Continuous monitoring of stress in individuals during their daily activities has become an inevitable need in present times. Unattended stress is a silent killer and may lead to fatal physical and mental disorders if left unidentified. Stress identification based on individual judgement often leads to under-diagnosis and delayed treatment possibilities. EEG-based stress monitoring is quite popular in this context, but impractical to use for continuous remote monitoring.Continuous remote monitoring of stress using signals acquired from everyday wearables like smart watches is the best alternative here. Non-EEG data such as heart rate and ectodermal activity can also act as indicators of physiological stress. In this work, we have explored the possibility of using nonlinear features from non-EEG data such as (a) heart rate, (b) ectodermal activity, (c) body temperature (d) SpO2 and (e) acceleration in detecting four different types of neurological states; namely (1) Relaxed state, (2) State of Physical stress, (3) State of Cognitive stress and (4) State of Emotional stress. Physiological data of 20 healthy adults have been used from the noneeg database of PhysioNet.Results: We used two machine learning models; a linear logistic regression and a nonlinear random forest to detect (a) stress from relaxed state and (4) the four different neurological states. We trained the models using linear and nonlinear features separately. For the 2-class and 4-class problems, using nonlinear features increased the accuracy of the models. Moreover, it is also proved in this study that by using nonlinear features, we can avoid the use of complex machine learning models.
No takes yet. Share an insight, caveat, or question.
Udhayakumar et al. (2023) studied Stress (n=20). Nonlinear features from non-EEG data vs. Linear features was evaluated on Accuracy of detecting stress and four different neurological states. Using nonlinear features from non-EEG multi-modal signals increased the accuracy of machine learning models in detecting stress and different neurological states.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: