Decision aid for depression treatment

Each year 5% of people in the Netherlands experience depression. Treatment outcomes differ widely from person to person, depending on age, severity, medical history and social context.

I-SHARED combines socio-demographic and clinical data into a personalised overview of possible treatments. The question: how do you bring that data together in a machine learning model that automatically generates a report both patient and clinician can use?

We contributed to the decision aid and delivered a microservice architecture for generating visualisations and reports. Using those reports, clinician and patient discuss the direction of treatment together.

How it works:

• The tool securely collects information about symptoms, earlier treatments and personal preferences
• That data is linked to the UMCG prediction model
• The result is a clear report with treatment options, tailored to the patient's situation

We also wrote an article about it: how I-SHARED brings control to the choice of depression treatment.

On 21 July 2025 the contribution appeared in the Journal of Participatory Medicine, under the title "Development of a Cocreated Decision Aid for Patients With Depression: Combining Data-Driven Prediction With Patients' and Clinicians' Needs and Perspectives: Mixed Methods Study".