Real-time stress detection based on artificial intelligence for people with an intellectual disability

ABSTRACT

People with severe intellectual disabilities (ID) could have difficulty expressing their stress which may complicate timely responses from caregivers. The present study proposes an automatic stress detection system that can work in real-time. The system uses wearable sensors that record physiological signals in combination with machine learning to detect physiological changes related to stress. Four experiments were conducted to assess if the system could detect stress in people with and without ID. Three experiments were conducted with people without ID (n = 14, n = 18, and n = 48), and one observational study was done with people with ID (n = 12). To analyze if the system could detect stress, the performance of random, general, and personalized models was evaluated. The mixed ANOVA found a significant effect for model type, F(2, 134) = 116.50, p < .001. Additionally, the post-hoc t-tests found that the personalized model for the group with ID performed better than the random model, t(11) = 9.05, p < .001. The findings suggest that the personalized model can detect stress in people with and without ID. A larger-scale study is required to validate the system for people with ID.

KEYWORDS:

• artificial intelligence
• challenging behavior
• intellectual disability
• real-time stress detection
• wearables

Disclosure statement

Employees S. de Vries and F. van Oost and owners E. Meinders and R. Smits of Mentech Innovation b.v. have a commercial interest in the findings from the study. The remaining authors have no conflicts of interest to declare.

Data availability statement

Participants of this study did not agree for their data to be shared publicly, so supporting data is not available.

Additional information

Funding

The work was supported by the Health~Holland [LSHM21001].