NNL.20.003 – From work stress to burnout: using integrated dynamic stress profiles to understand and prevent burnout

Route: NeuroLabNL: the ultimate living lab for brain, cognition and behavioural research

Cluster question: 083 How do neurological, psychiatric, and mental disorders arise, and how can we prevent, mitigate, or cure them?

Burnout is one of the biggest challenges for modern societies in the Netherlands but also across the world. Each year, millions of individuals worldwide suffer from clinical burnout and many more from severe work-related stress. Burnout is undoubtedly a major public health problem. Even though stress is linked to the onset and course of burnout, there are large interindividual differences, and we currently cannot predict who is at risk and how to best prevent or treat burnout. Recent neuroscientific developments in the fields of stress and mental health have increased our understanding how individuals respond to and recover from stress. Specifically, to adequately respond to stress, an integrated and dynamic functionality of all stress systems at the biological, psychological, and behavioral level are vital. An individual’s unique background and context determines the impact and consequences of stress. These new insights are directly relevant to understand and tackle the major problem of work-related stress and burnout. We propose a completely novel approach to understand stress and burnout by focusing on integrated profiles which implement recent (neuro)biological and psychological insights and integrate these in ecologically valid, daily-life settings in the context of work and private life using smartphones and wearable devices. Our explicit aim is to create personalized dynamic stress profiles in healthy individuals, individuals at risk for burnout, and those suffering from a clinical burnout. To analyze this highly complex data, we will exploit techniques from the domain of artificial intelligence, and specifically machine learning, to extract and exploit such risk profiles from the data. Our project ultimately aims to use personalized dynamic stress profiles not only to predict risk for burnout but also to develop and guide personalized interventions to prevent and treat burnout.

Keywords

burnout, data integration, machine learning, personalized stress profiles, Stress, working environment

Other organisations

Radboud Medical Center (RUMC), Vrije Universiteit Amsterdam (VU)

Submitter

Organisation Amsterdam UMC (VUmc)
Name Dr. C.H. (Christiaan) Vinkers
E-mail c.vinkers@amsterdamumc.nl