Stress Classification during Dental Procedure
4
Issued Date
2022-01-01
Resource Type
Scopus ID
2-s2.0-85133394395
Journal Title
19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2022
Rights Holder(s)
SCOPUS
Bibliographic Citation
19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2022 (2022)
Suggested Citation
Thanungkul P., Jirakittayakorn N., Wongsawat Y. Stress Classification during Dental Procedure. 19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2022 (2022). doi:10.1109/ECTI-CON54298.2022.9795647 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/84631
Title
Stress Classification during Dental Procedure
Author(s)
Author's Affiliation
Other Contributor(s)
Abstract
Stress is a response to negative events which challenge and threat to an individual. Several methods have been used to measure it including questionnaire, blood, and saliva. The saliva is used due to its non-invasive technique, but it has low temporal resolution which cannot detect sudden change. EEG is chosen to solve this problem. This study aims to investigate change of salivary biomarkers responding to stress and to develop real-Time automated stress evaluation algorithm using EEG. Eight participants were included to receive entire mouth dental scaling. Saliva samples were collected before and after intervention while EEG signal was recorded along dental procedure with self-Trigger button to mark stress events. ELISA technique was performed to evaluate biomarkers' activities. Neural network was developed for stress classification. No significance occurred with salivary cortisol and salivary α-Amylase, but sIgA showed due to period of acute stress over 10 minutes. Highest accuracy of the model was around 74% but true positive classification of stressed data was 46% due to small dataset of stressed data. However, this model could be implied in real-Time classification by apply more dataset for training.