PhD Candidate: Machine Learning for Identifying Predictive Factors of Cognitive Decline and...

Updated: about 1 month ago
Job Type: Temporary
Deadline: 11 Mar 2021

A PhD candidate to develop and apply machine learning and statistical techniques for identifying non-invasive markers for cognitive decline and multi-domain lifestyle intervention response within the crossover research project 'Maintaining Optimal Cognitive Function In Ageing' (MOCIA), funded by the Dutch Research Council (NWO) and coordinated by Radboud University. MOCIA focuses on identifying increased risk of cognitive decline and improving prevention through the development of a personalised lifestyle approach. MOCIA will design a predictive, preventive, personalised and participatory multi-domain lifestyle intervention for older adults at risk of cognitive decline. The programme brings together various disciplines, such as nutrition, lifestyle, behavioural science, clinical research, epidemiology, mathematics, biology, industrial design and technology to help achieve maintaining a healthy brain, good long and short-term memory, increased concentration and greater flexibility. MOCIA involves a public-private partnership with members from eight knowledge institutes and eight co-financing parties. In addition to Radboud University, it includes the Radboud university medical center, Wageningen University & Research, the University of Twente, Maastricht University, Amsterdam University Medical Center, University Medical Center Groningen and HAN University of Applied Sciences. The co-financing parties are Danone Nutricia Research, IMEC (OnePlanet Research Centre), DSM Nutritional Products, Salut (a VGZ spin-off), Hersenstichting, Reckitt Benckiser/Mead Johnson Nutrition, Alzheimer Nederland and Wageningen Food and Biobased Research. The project has a total budget of € 9.17 million, of which € 6.25 million is financed by NWO.

The data science group at iCIS is involved as leader of the work package 'Non-invasive markers for cognitive decline and intervention response'. The main objective of this work package is to identify non-invasive modifiable risk and protective factors and to design scoring tools to quantify risk of cognitive decline. We are looking for a candidate who is excited to perform collaborative research within such a large, multidisciplinary consortium. More particularly, you will develop and validate AI algorithms to unravel individual differences in cognitive decline and intervention response. You will combine non-invasive modifiable risk and protective factors in reliable scoring tools through predictive AI models to quantify risk of cognitive decline on a personal level and to analyse the effect on an intervention in relatively short periods. You will use the developed scoring tools to identify multi-modal non-invasive markers.


View or Apply

Similar Positions