NATURAL LANGUAGE PROCESSING FOR PERSONALISED HEALTH COMMUNICATION
The position is part of the project “Helping cancer patients to choose the best treatment: Data-driven shared decision making on cancer treatment for individual patients”, funded by NWO-ENW DATA2PERSON. The position is in the Department of Communication and Cognition (DCC) of the Tilburg School of Humanities and Digital Sciences (TSHD), and is a collaboration with the Tilburg School of Social and Behavioral Sciences (TSB) and The Netherlands Comprehensive Cancer Organization (IKNL).
When someone is first diagnosed with cancer, patient and doctor jointly need to decide which treatment to opt for from the range of possible treatments. Decision tools have been developed to support this difficult process, but, unfortunately, these tend to be generic and population-based, focus exclusively on long-term survival and lack personalised explanations. Moreover, they are not easily understandable and accessible for patients, and are difficult to maintain and keep up to date. As a result their usefulness is limited.
In this project, we will address these issues by developing an application that can generate multimodal personalised descriptions (text and graphics) of treatment options based on data of millions of Dutch cancer patients. Our team will include two new PhDs. One PhD (hosted by TSB) will develop new statistical models, determining the advantages and disadvantages of the relevant treatment options for individual patients. Based on the person and tumor characteristics, these models not only include predictions for (long term) survival, but also factors like side-effects of treatment and quality of life after treatment.
The other PhD (hosted by TSHD, and for which we are currently hiring) will develop a data-to-text system which automatically generates personalised explanations of the outcomes, using non-technical language and visualisations. This system is enhanced with personalised explanations of uncertainties and risks associated with different treatments.
End users (doctors and patients) are involved in all stages of the project, from the beginning, to gauge their wishes and needs, to the end, to evaluate the systems that were developed. We aim to show that our data-driven, personalised approach makes patients more knowledgeable about different treatment options and empowers them during shared decision making about treatments.
You will design, implement and evaluate a software system that is capable of explaining personalised health statistics related to treatment options. Based on state-of-the-art techniques for this, from Natural Language Generation (NLG), Natural Language Processing (NLP) and Artificial Intelligence (AI), you will study how to explain individualised treatment information to patients via automatically generated textual and visual reports, for which a demonstration system will be developed and evaluated with doctors and patients. You will collaborate with communication researchers from TSHD, statisticians from TSB, and data scientists and epidemiologists at IKNL (where you are expected to also spend one day per week). Your findings will be reported in publications, which form the basis of your PhD thesis.
For the position we seek a candidate with a (research) master in a relevant area, including, but not limited to: computational linguistics, natural language processing, artificial intelligence, computational health informatics, (health) data science, medical informatics, computer science or computational communication science.
You are a motivated researcher who is comfortable with working in a multidisciplinary research team, has strong statistical and programming/scripting skills, and an excellent command of English. Knowledge of Dutch is an advantage, but not strictly necessary. Importantly, you are passionate about health care and are motivated to empower patients using digital tools.
For more information on the position, please contact prof.dr. Emiel Krahmer (E.J.Krahmer at uvt.nl<mailto:E.J.Krahmer at uvt.nl>). A longer description of the project is available upon request.
What we offer
Tilburg University is rated among the top Dutch employers and offers very good fringe benefits (it is one of the best non-profit employers in the Netherlands), such as an options model for terms and conditions of employment and excellent reimbursement of moving expenses. The collective labor agreement of Tilburg University applies.
The selected candidate will start with a contract for one year, concluded by an evaluation. Upon a positive outcome of the first-year evaluation, the candidate will be offered an employment contract for the remaining three years. It is also possible to work 80% instead of fulltime.
The candidate will be hosted at TSHD (Tilburg) and is expected to work one day a week at IKNL (Eindhoven).
Researchers from outside the Netherlands may qualify for a tax-free allowance equal to 30% of their taxable salary. The university will apply for such an allowance on their behalf. The Faculty will provide assistance in finding suitable accommodation. The PhD candidates will be ranked in the Dutch university job ranking system (UFO) as a PhD-student (promovendus) with a starting fulltime salary of €2,266 gross per month in the first year (€31,600 on yearly basis), up to € 2.897 the fourth year. The selected candidate is expected to have written a PhD thesis, which may be based on articles, by the end of the contract.
Applications should include: - Cover letter, - Curriculum Vitae, - Copy of the university marks (grade list), - Names of two references.
Applications should be sent before the application deadline of August 15, 2018. Interviews are expected to be held in the last week of August.
The only way to apply is online by following this link: http://www.tilburguniversity.edu/about-tilburg-university/working-at/wp/
Tilburg University Language Production group<http://tulp.uvt.nl/> Department of Communication and Cognition Tilburg School of Humanities and Digital Sciences
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 8759 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20180710/1b72a891/attachment.txt>