Research area/discipline: Machine learning and Healthcare
Prerequisites: Programming in Python INF22306 (or similar), some knowledge on machine learning.
In the Netherlands, around 0.85% of the population has an intellectual disability (ID) according to the classical definition of having an IQ below 70. People with an ID often live in long-term care facilities and represent a large share of the health care use in the Netherlands. Care around people with an ID is complex and involves many caregivers. These caregivers all use some health information systems (HIS) to, for example, register their activities and to ensure reimbursement of care provided.
These HISs collect a lot of data about people with an ID, often on a daily basis. Your task is to see how this data can be used to improve the health of people with ID. You will use techniques such as text mining and natural language processing on pseudonymized data from care institutions.
- Familiarize yourself with the data and obtain relevant issues from practice
- Apply machine learning algorithms to the data in order to get answers for these issues
Required skills/knowledge (optional):
Programming (in Python)
- Knowledge on machine learning
- Knowledge on big data
Raja, U., Mitchell, T., Day, T., & Hardin, J. M. (2008). Text mining in healthcare. Applications and opportunities. J Healthc Inf Manag, 22(3), 52-6.
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. (2011). Natural language processing (almost) from scratch. Journal of machine learning research, 12(Aug), 2493-2537.
For more information:
For making an appointment to discuss the thesis topic, please send an email to: HJM (Joep) Tummers | Promovendus | Information Technology group (INF) | Wageningen University & Research (WUR) | firstname.lastname@example.org