Long-Term Care (LTC) staff consistently reported their job as stressful and with lower mental and physical health than healthy controls. Traditional measures of stress rely on biomarkers such as cortisol levels from blood or urine samples, which are time-consuming and inconvenient; thus, impractical to use in workplaces. In addition, stress levels are likely situational and dynamically changing over the course of the day. Therefore, a more fine-grained method to assess stress responses is desirable to understand their evolutionary pattern, thereby providing means for proactive, evidence-based, and data-driven interventions for emotion regulation or stress management. In recent years, wearable sensors have emerged promising alternatives to collect multivariate biophysical signals non-intrusively. Its application to stress measurement is emerging. However, most existing studies have occurred in controlled lab environments, with only a handful exploring its utility outside the lab. Research is even more sparse with healthcare workers such as those from LTC settings. This project is one of the first few studies on stress monitoring with healthcare workers that integrates biophysical data from wearable sensors and contextual information from smartphone-based EMA.
Funding Sources: ATIP 2021-2022
- Charan Duggirala (UMBC IS master student, Fall 2021 – present)
- Shifali Sharma (UMBC IS Ph.D. student, Summer 2021 – present)