RESEARCH FIELDLanguage sciences
RESEARCHER PROFILERecognised Researcher (R2)
APPLICATION DEADLINE01/06/2021 23:59 - Europe/Brussels
LOCATIONNetherlands › Tilburg
TYPE OF CONTRACTTemporary
HOURS PER WEEK40.0
The Department of Cognitive Science and Artificial Intelligence (CSAI) at Tilburg University, in collaboration with Tilburg School of Social and Behavioral Sciences (TSB) and the Elisabeth-Tweesteden Ziekenhuis (ETZ) is looking for a
Postdoctoral Researcher in Artificial Intelligence for a project on network analyses of cognitive tests for personalised diagnostics aimed at predicting Mild Cognitive Impairment and/or early Alzheimer’s disease.
The position in for a period of 2 years, between 0.8-1.0 fte (max. 38 hours per week) employment and starting from August 1st , 2021 (starting date flexible).
You contribute to research that is part of the WeCare program, focusing on AI contributions to personalized health care. In this project, we aim to develop personalized diagnostics of memory impairments, using adaptive online cognitive tests. Methods will draw on graph (neural) network analyses to uncover relationships between test items and demographic attributes, you will work towards generating flexible and personalized baselines/norms that will aid in creating sensitive and easy to use diagnostic tests, for use in primary care situations.
You perform scientific research at the intersection of AI and clinical neuropsychology:
- You are involved in creating graph models that feed into adaptive cognitive tests
- You work with clinical partners to benchmark AI-based model predictions against current clinical practice and evaluate predictive accuracy and stability
- You present the results of the study in clear, unambiguous reports.
- You play an active role in all activities of the research team and collaborate with team members.
- You publish results in scientific journals.
- You present results at (international) conferences.
Your professional environment
You will be part of the CSAI research group and collaborate closely with the Cognitive Neuropsychology department at TSB and the medical psychologists, geriatrists and neurologists at ETZ, through the WeCare programme. WeCare is the scientific collaboration programme of ETZ and TiU. WeCare aims to strengthen both parties in health (care) research to improve patient care. Our team consist of AI researchers, (neuro)psychologists and clinicians.
This project focuses on the application of AI techniques to generate individualized baselines for cognitive testing, using (among other memory tests) a Famous Faces Test which we are currently developing for use in an elderly population. We hope to use this test to detect early cognitive impairment and distinguish ‘normal’ cognitive aging from early signs of dementia. Alzheimer’s disease (AD) is the primary cause of dementia. Currently, over 270.000 people suffer from AD in the Netherlands alone and this number will double over the next decade (Alzheimer Stichting Fact Sheet, 2017). A string of failed clinical trials highlights the need to detect AD as early as possible rather than trying to treat after brain damage is irreversible (Scheltens et al., 2016; Sperling et al., 2014). Moreover, one pharmacological intervention (aducanumab) is currently awaiting final FDA approval (Sevigny et al., 2016), increasing the pressure on scientists and clinicians to work together to develop adequate and early diagnosis of patients who would benefit from such an intervention.
Early-stage symptoms of AD, such as memory decline, are often mistaken for normal aging, creating a barrier for patients to seek care. Furthermore, when individuals do seek help, usually through their GP, current standardized screening tests are often too general (e.g. the MOCA or MMSE which are screens for cognitive performance) and do not correct for individual characteristics, thereby losing sensitivity (Rentz et al., 2013; Nieuwenhuis-Mark, 2010). Consequently, patients are diagnosed much later than necessary or not at all. This is unfortunate (and costly), since the early detection of AD could significantly aid patients, carers and clinicians in organizing appropriate (future) care and increase the effectiveness of possible pharmacological and lifestyle interventions.
One of the hallmarks of AD is a steep decline in episodic memory, where recent memories are more affected that remote memories. The Famous Faces Test, a cognitive test in development by our team and a dedicated PhD student, is designed to be sensitive to this temporal gradient. In this project, we will use machine learning and network analysis tools to create a personalized model of memory performance based on demographics (e.g., age, gender, education) and health factors (e.g., physical activity, sleep), which have been shown to impact individual differences in cognitive abilities. These personalized predictions in turn allow the content of the memory tests to be tailored to the individual during the test (by adaptively presenting test items), to maximize its diagnostic sensitivity and thereby improve the early detection of potential cognitive decline in individual patients.
The central research questions are: Can predictions from machine learning models based on network analyses be used to generate personalized baseline for the early detection of dementia? Furthermore, is an online, adaptive test for detecting memory impairment as good as diagnoses generated in current clinical practice? If so, the online cognitive diagnostics platform could act as a low-cost longitudinal screening tool for the early detection of memory decline and follow up, to be deployed in primary care. This would be a proof-of-principle for such a successful precision medicine approach to the online detection of memory disorders, that could eventually be extended to other cognitive domains as well.
This postdoc position will be jointly supervised by dr. Marijn van Wingerden, AI-researcher (CSAI) and dr. Ruth Mark (TSB) and supported by a wider academic team including prof. Yvonne Brehmer (TSB). Collaborators include: prof. Eric Postma (CSAI) (AI) and dr. Gerwin Roks (Neurology, ETZ). Support in clinical translation will be provided by dr. Hetty Scholten (ETZ).
The junior researcher will be employed at the CSAI department, Tilburg School of Digital Sciences and Humanities. We offer:
- A 0.8-1.0 fte agreement for up to two years (including a 3-month probationary period), with a tentative starting date of August 1st, 2021 (a different starting date can be negotiated)
- The position will be ranked in the Dutch university job ranking system (UFO) as researcher (“onderzoeker 4”). The starting gross salary for a full-time appointment for a researcher is (minimally) € 2.790 in scale 10 up to (maximally) € 3.353 gross per month. Rating based on experience.
- Researchers from outside the Netherlands may qualify for a tax-free allowance equal to 30% of their taxable salary (the 30% tax regulation). The University will apply for such an allowance on their behalf.
- A broad package of attractive fringe benefits including an annual holiday allowance and an end-of-year bonus of 8.3%; travel compensation, optional system of additional terms of employment with among others an extensive bike plan.
- The collective labor agreement of the Dutch Universities applies.
Applications should include a cover letter in English, a Curriculum Vitae (including two references), and a half-page statement about the candidate’s contribution to Artificial Intelligence or Health Analytics. The deadline for applying is June 1st, 2021.
If you are interested in applying for the position, please use http://www.tilburguniversity.edu/about-tilburg-university/working-at/wp/.
For more information on this position, please contact dr. Marijn van Wingerden E.J.M.vanWingerden@tilburguniversity.edu.
Alzheimer Stichting Fact Sheet (2017).
Nieuwenhuis-Mark, R. E. (2010). The death knoll for the MMSE: Has it outlived its purpose? J. Geriatr. Psychiatry Neurol. 23, 151–157. doi:10.1177/0891988710363714.
Rentz, D. M., Parra Rodriguez, M. A., Amariglio, R., Stern, Y., Sperling, R., and Ferris, S. (2013). Promising developments in neuropsychological approaches for the detection of preclinical Alzheimer’s disease: A selective review. Alzheimer’s Res. Ther. 5. doi:10.1186/alzrt222.
Scheltens, P., Blennow, K., Breteler, M. M. B., de Strooper, B., Frisoni, G. B., Salloway, S., and Van der Flier, W. M. (2016). Alzheimer’s disease. Lancet 388, 505–517. doi:10.1016/S0140-6736(15)01124-1.
Sevigny, J., Chiao, P., Bussière, T., Weinreb, P. H., Williams, L., Maier, M., Dunstan, R., Salloway, S., Chen, T., Ling, Y., et al. (2016). The antibody aducanumab reduces Aβ plaques in Alzheimer’s disease. Nature 537, 50–56. doi:10.1038/nature19323.
Sperling, R. A., Rentz, D. M., Johnson, K. A., Karlawish, J., Donohue, M., Salmon, D. P., and Aisen, P. (2014). The A4 Study: Stopping AD Before Symptoms Begin? Sci. Transl. Med. 6, 228fs13-228fs13. doi:10.1126/scitranslmed.3007941.
Web site for additional job details
- You have a PhD in a relevant area such as Artificial Intelligence, Data Science, Computer Science, Medical Informatics, Computational Cognitive Science, Computational Cognitive Neuroscience, or a related discipline. Applicants with a (research) Master’s degree and proven applicable experience are also invited to apply
- You have experience with some or all of: (deep) network modelling, graph neural networks, psychological modelling, collaborative filtering and/or clustering using (variational) autoencoders.
- You have interest in and/or experience with health analytics.
- You possess strong programming skills in Python including Tensorflow/Keras or similar platforms for deep learning and familiarity with R.
- You have excellent analytical skills and are highly rigorous in your analyses.
- You have good technical understanding of advanced statistics and quantitative methods.
- You are a fast learner, autonomous and creative.
- You are highly motivated, work hard and show dedication.
- You possess good communication skills and are able to work with different people.
- You are fluent in English, both spoken and written.
EURAXESS offer ID: 634900
Posting organisation offer ID: 300210
The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.
Please contact firstname.lastname@example.org if you wish to download all jobs in XML.