Stress Monitoring in Pandemic Screening: Insights from GSR Sensor and Machine Learning Analysis.

Area of Science:

• Biomedical Engineering
• Psychophysiology
• Public Health

Background:

• Assessing patient stress during infectious disease screening is crucial for effective public health strategies.
• Anxiety related to diagnostic procedures can influence patient compliance and data accuracy.

Purpose of the Study:

• To investigate and quantify the stress levels experienced by individuals undergoing rapid severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) screening.
• To explore the utility of galvanic skin response (GSR) sensors and machine learning in objectively measuring stress during COVID-19 testing.

Main Methods:

• Collected GSR data from 51 participants at SARS-CoV-2 testing sites using a microcontroller-connected sensor.
• Compared empirical GSR data with theoretical stress estimates.
• Employed machine learning classification algorithms for automated analysis and identification of stress states ('stressed' or 'not stressed').

Main Results:

• A significant increase in stress levels was observed in individuals during the rapid COVID-19 testing procedure.
• GSR sensor data, when analyzed by machine learning, accurately identified stress responses.
• The study confirmed a correlation between the screening process and elevated anxiety.

Conclusions:

• Rapid COVID-19 screening procedures demonstrably induce significant patient stress.
• Objective stress measurement using GSR and machine learning is feasible and provides valuable insights.
• Heightened anxiety during screening may deter participation, potentially undermining public health efforts for infectious disease control.