State Anxiety Biomarker Discovery: Electrooculography and Electrodermal Activity in Stress Monitoring

TL;DR

This study investigates non-invasive wearable sensors, specifically electrooculography and electrodermal activity, to identify novel biomarkers for real-time state anxiety monitoring, enhancing personalized mental health assessment.

Contribution

It introduces new anxiety-specific biomarkers derived from EOG and EDA signals and demonstrates their effectiveness using SHAP analysis for improved stress detection.

Findings

Identification of multiple new anxiety biomarkers from EOG and EDA data

Enhanced real-time stress detection accuracy using combined physiological signals

Validation of biomarkers with datasets from blink events and Cold Pressor Test

Abstract

Anxiety has become a significant health concern affecting mental and physical well-being, with state anxiety, a transient emotional response, linked to adverse cardiovascular and long-term health outcomes. This research explores the potential of non-invasive wearable technology to enhance the real-time monitoring of physiological responses associated with state anxiety. Using electrooculography (EOG) and electrodermal activity (EDA), we have reviewed novel biomarkers that reveal nuanced emotional and stress responses. Our study presents two datasets: 1) EOG signal blink identification dataset BLINKEO, containing both true blink events and motion artifacts, and 2) EOG and EDA signals dataset EMOCOLD, capturing physiological responses from a Cold Pressor Test (CPT). From analyzing blink rate variability, skin conductance peaks, and associated arousal metrics, we identified multiple new anxiety-specific biomarkers. SHapley Additive exPlanations (SHAP) were used to interpret and refine our model, enabling a robust understanding of the biomarkers that correlate strongly with state anxiety. These results suggest that a combined analysis of EOG and EDA data offers significant improvements in detecting real-time anxiety markers, underscoring the potential of wearables in personalized health monitoring and mental health intervention strategies. This work contributes to the development of context-sensitive models for anxiety assessment, promoting more effective applications of wearable technology in healthcare.