PI - PhD in Neurobiological and digital phenotyping towards digital mental health interventions in depression, at DeustoTech.

Purpose of the position:

Mental health problems are increasing worldwide. Major depressive disorder (MDD) is considered the worldwide leading source of disability. Therapeutic approaches are not fully understood and still improvable. Behavioral activation (BA), a successful therapeutic approach for nearly 50 years, increases activation by means of establishing short, and rewarding experiences in patients’ daily life, e.g., taking a shower. Current research clearly supports the effects of BA on MDD when comparing it to no intervention. However, BA alone is not superior to other specific forms of psychotherapy. To improve BA, we need to better understand the behavioral and neurobiological underpinnings. Most Most recently, researchers identified a new potential starting point for treating MDD: the momentary relationship between physical activity and feelings of energy in everyday life. While past research focused on exercise for treating MDD, we and others found that not sports (e.g., jogging) but everyday physical activity (e.g., walking stairs) improves energy.

This position assigned to a project called “MASE” has as its main research objective the application of artificial intelligence to identify, test, proof, and refine neurobiological phenotype – natural environment feature (e.g., time, place, context) combinations for the administration of individualized nonexercise activity interventions to reliably increase momentary subjective energy as an expedient prevention of and treatment strategy for major depressive disorder.

The hypothesis for this research are 1) different phenotype features of the structural covariance network will increase ASEA prediction in the three follow up datasets, and 2) specific phenotype-tailored ASEA-feature (e.g., nonexercise type, time, place, context) combinations will provide resilience and thus predict improved depression ratings in the two questionnaire follow ups at months 6 and 12.

Then, the objectives of this research conducted under MASE project context will be: a) use artificial intelligence to identify where and when nonexercise activity helps people with certain brain properties, and b) develop and design a smartphone app that delivers ASEA ((real-life physical activity-subjective energy association), interventions and provides suggestions when and where to engage in which short nonexercise activity to maximize participation rates.

Title of the project to be incorporated:

- MASE, Neurobiological And Digital Phenotyping Towards Digital Mental Health Interventions In Depression

PI and/or project manager:

Amaia Méndez Zorrilla and Begoña García-Zapirain   

Endowment of the contract:

25.973,10 €/year.  2 years (extendable to 3 years)

Funding Entity:

• MASE. COFUND 2 2023. Eranet Neuron, Call 2023. PCI2024-153469.