A Privacy Preserving Platform for Organizational and Individual Resilience

This research develops a privacy-friendly software platform to detect and reduce work-related stress early, for both individuals and organisations. Work-related stress often leads to burnout, absenteeism, lower productivity, and strains healthcare systems. While organisations collect relevant data, concerns about privacy and distrust prevent its full utilisation. I am working on digital solutions that enable stress-resilient measures while respecting privacy and ethical considerations. The goal is timely support, reduced harm, and healthier work environments. In doing so, this research contributes to sustainable working conditions and societal resilience.

Research method

This research involves developing a modular, scalable software platform that combines data from wearables, self-reports, and organisational contexts—without centrally storing sensitive personal data. Using software engineering, privacy-by-design, and machine learning, the researchers create interpretable stress indicators that are reusable across different organisations. The platform encourages collaboration with societal partners to ensure solutions align with practical needs. Data and AI support decision-making without replacing human judgement. In this way, we contribute to responsible, user-friendly technology that detects stress signals early and ethically.

The research delivers a reusable digital platform, enabling organisations to responsibly deploy stress-resilient tools. The platform provides secure data streams, reliable stress indicators, and applications for reflection, dialogue, and targeted action. This allows schools, healthcare institutions, and workplaces to detect stress patterns earlier, tailor interventions locally, and measure effectiveness. By lowering technical and ethical barriers, my work supports better policies, improved practices, and a shift from reactive burnout care to preventive resilience.

Researcher

David Carrascosa, PhD candidate

Academic supervisors

  • Dr. Kate Labunets, Department of Information and Computing Sciences, Utrecht University
  • Dr. Slinger Jansen, Department of Information and Computing Sciences, Utrecht University