RU-STRESSed? Researching Unseen STRESS Through Real-time Evaluation in Simulated healthcare Settings (EN)

Problem statement

Half of the healthcare workforce in Flanders experiences excessive workload and stress, which may lead to reduced quality of care and absenteeism. However, the majority of research on work-related stress is based on self-report measures, which are vulnerable to subjective bias, underestimation, and social desirability bias. As a result, stress is difficult to measure accurately and in a time-sensitive manner, creating a barrier to the development of effective stress-reduction interventions.

There is therefore a need for objective, context-specific measurement methods that provide insight into how, when, and why stress occurs among healthcare professionals.

Research objective

Medical wearables enable the monitoring of physiological stress indicators. Because they can be used in real-life settings, these sensors have the potential to generate groundbreaking insights into stress prevention and reduction.

When combined with Experience Sampling Methods (ESM), which collect both physiological data and personal experiences, a powerful hybrid measurement approach emerges. This approach provides insight into the temporal relationships between stress responses and specific work-related contexts.

This creates opportunities for AI-driven stress prevention. In the future, patterns may be identified that predict stress, enabling applications such as real-time monitoring and early warning systems.

In this project, we take a first step in that direction by exploring how artificial intelligence can contribute to identifying predictive stress factors. In addition, we aim to build expertise in the use of ECGMove4 sensors and explore how this technology can support stress prevention and mental resilience among healthcare professionals.

Research question

What added value do ECGMove4 sensors and signal-based Experience Sampling Methods provide in identifying and reducing stress responses among healthcare professionals and healthcare students?

Research approach

This practice-oriented scientific study uses ECGMove4 sensors (Movisens) to objectively measure work-related stress in a multidisciplinary group of international healthcare students during simulation scenarios.

We will test the sensors, optimize their use, and investigate whether brief interventions (such as breathing techniques, mindfulness exercises, or repeated practice) influence measured stress levels.

By linking sensor data with ESM data, we will gain in-depth insights into stress moments and their contexts. In addition, artificial intelligence will be used to identify potential predictive stress factors.

The project will provide a foundation for larger-scale research and future AI-driven stress prevention strategies.

Expected outputs

1. ECGMove4 Sensor User Guide
   A practical guide containing procedures, lessons learned, and key considerations.
2. Scientific Final Report
   A detailed description of the methodology, results, and recommendations for future research.
3. Publication(s)
   Scientific article(s) presenting the project findings.
4. Follow-up Project
   Focused on the development of AI-driven stress detection and intervention, or on scaling up to broader clinical applications.
5. Presentations and Workshops
   Both internal (KdG) and external dissemination activities highlighting the potential of wearables and ESM for stress monitoring.
6. Educational Application
   Concrete recommendations for integrating stress recognition and stress-reduction strategies into healthcare curricula.
7. Business Case
   Exploration of valorisation opportunities, such as services related to stress detection and prevention in healthcare.

Researchers

• jente.bontinck@kdg.be
• Jurgen.heyman@kdg.be
• margo.wouters@kdg.be