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

Abstract

This study investigates the impact of patient stress on COVID-19 screening. An attempt was made to measure the level of anxiety of individuals undertaking rapid tests for SARS-CoV-2. To this end, a galvanic skin response (GSR) sensor that was connected to a microcontroller was used to record the individual stress levels. GSR data were collected from 51 individuals at SARS-CoV-2 testing sites. The recorded data were then compared with theoretical estimates to draw insights into stress patterns. Machine learning analysis was applied for the optimization of the sensor results. Classification algorithms allowed the automatic reading of the sensor results and individual identification as "stressed" or "not stressed". The findings confirmed the initial hypothesis that there was a significant increase in stress levels during the rapid test. This observation is critical, as heightened anxiety may influence a patient's willingness to participate in screening procedures, potentially reducing the effectiveness of public health screening strategies.

Keywords: COVID-19 screening; biosensors; classification algorithms; galvanic skin response (GSR); machine learning analysis; physiological stress indicators; stress monitoring.

Figure 1

(a) The GSR sensor; (b) individual wearing the GSR contacts.

Figure 2

The equivalent electrical circuit.

Figure 3

Galvanic skin response (GSR) signal characteristics following a stimulus. The red dot and vertical dashed line indicate the stimulus time (t). Key parameters include latency (time from stimulus to response onset), rise time (time from onset to peak), amplitude (peak GSR value minus baseline), and recovery time (time to reach 50% of the peak amplitude after the peak) [14].

Figure 4

GSR response of four individuals; (a) stressed response (1); (b) stressed response (2); (c) not stressed response; (d) invalid measurement.

Figure 5

GSR signal visualizations; (a) raw GSR signal; (b) phasic GSR signal; (c) GSR peaks and mean value; (d) combined GSR and phasic signal.

Figure 6

GSR data classification; (a) result of applying a K-means clustering algorithm to the GSR data. Yellow indicates subjects who showed elevated levels of anxiety. In purple are those who showed no noticeable change in GSR data; (b) classification results with SVM algorithm. The circle represents the training set data while the symbol “x” represents the test set data. The data categorized as unstressed are represented in blue while the test set categorized as stressed are represented in red.

Figure 7

SVM Classification; (a) using a linear kernel; (b) using Radial Basis Function (RBF) Kernel with gamma value equal to 2.0; (c) using NuSVM with RBF kernel and ν = 0.02; (d) using NuSVM with RBF kernel and ν = 0.2.