In this project, UMC Utrecht and Utrecht University will partner with Parnassia Groep and Arkin to unravel the effects of treatment decisions in mood disorders. We will bring novel techniques for machine learning and data sharing from the academic environment together with expertise from data scientists and big datasets in mental healthcare to study complex research questions on a sufficiently large scale, in a privacy-preserving way.

This research project, in collaboration with Clear, aims to develop a personalized meal recommender system. Clear, a nutrition precision startup, possesses a unique dataset containing user demographics, logged meals, and postprandial glucose values. Existing data underscores the variability in individual responses to identical meals, emphasizing the need for personalized dietary recommendations. The project faces specific challenges, including predicting post-meal glucose values accurately, identifying similar meal responses among users and translating predictive outcomes into a practical recipe recommender system that would also take into account user preferences, allergies, and contextual information.

Read more

Anticipating a rise to half a million dementia cases among the elderly in the Netherlands by 2040, the demand for care is escalating while a shortage of professionals persists. To address this, a collaboration involving HvA, HAN, Tu/e and UU is developing an Intelligent Care Environment, utilizing sensor tech and AI for personalized care. The project aims to implement reinforcement learning techniques for Just-in-time adaptive interventions, potentially easing the workload on healthcare professionals and enhancing the quality of care for elderly dementia patients.

Read more 

Exposure to natural outdoor environments including green space is vital for people’s health. Remote sensing via satellites is most used to generate measures of green space, however this does not capture the street-level perspective that people experience.

We addressed this research challenge with an assemblage of IT methods to derive measures of greenery from street view services on the web which allows virtual navigation through urban spaces composed of geo-tagged street-level images. We developed methods to automatically compute objective and accurate measures of green space employing big street view data and deep learning.

Read more