PhD student, on the subject of machine learning within the Research Project Enabling Personalized Interventions
Job/Project DescriptionThis PhD research project is part of the NWO Project Enabling Personalized Interventions (EPI), a collaboration of the University …
- Science Park, Amsterdam, Noord-Holland
- Tijdelijk contract / Tijdelijke opdracht
- Uren per week:
- 40 uur
- € 2346 - € 3007 per maand
This PhD research project is part of the NWO Project Enabling Personalized Interventions (EPI), a collaboration of the University of Amsterdam, CWI, Philips, KPMG and a number of hospitals. EPI is a consortium of medical professionals, data scientists, ICT-infrastructure experts and machine learning researchers. EPI aims to empower patients and providers through self-management, shared management, and personalization across the full health spectrum. To do so, we will build a fuller picture of the person by linking traditional eHealth data sets from within the hospital with new sources of data throughout the care delivery chain. We will develop a platform based upon a secure and trustworthy distributed data infrastructure, combining data analytics, including machine learning, and health decision support algorithms to create new, actionable, and personalized insights for prevention, management, and intervention to providers and patients.
In traditional clinical trials, one tests new medications on a fixed sample of a particular population sub-group – more often than not, all subjects are young, male and healthy. But most actual patients are evidently from a very different population, so medications may not always work, or have unpredictable side effects and so on. Hence, we aim for online tools that allow the medical professional and the patient to make informed shared decisions, based on patient data so far, in order to dynamically modify the treatment. Such tools could be based on sequential hypothesis testing methods (such as those currently being developed at CWI), giving statistical performance guarantees, or related Bayesian methods; but there is also a role for reinforcement learning and other machine learning tools aiming at online decision making and learning with continuous feedback. To accelerate the dissemination of knowledge and expertise developed, in past research, algorithms were replicated and validated in the partner mental hubs. The challenge how these institutions can collaborate without sharing privacy-sensitive data is one of our research questions.
The project will be carried out partly at CWI’s Machine Learning Group, and partly at the Innovation Team of the Psychiatry Department of University Medical Center Utrecht (UMCU). There will furthermore be intensive collaboration with scientists from Philips Research, and later on in the project there may be collaborations with/projects at other hospitals.
As a candidate you should thus
- be familiar both with traditional statistical testing methodology and with modern machine learning tools
- be aware of the limitations of such approaches
- understand the math behind statistical methods (error guarantees, confidence intervals)
- be proficient in programming (e.g. in R, Python or Matlab)
- have the creativity to think of new methods or to adjust existing methods to deal with the practical problems at hand
Together with other data scientists from the UMCU innovation team and health care professionals you eventually want to understand the data and improve treatments. Thus, additionally,
- you can explain your work in nontechnical terms,
- in particular you have the communication skills to, and you like to, collaborate with professionals from a different background than yours.
A central challenge is to translate the newest theoretical insights to the real-world challenges of dealing with actual data of actual patients. We are thus looking for a candidate who can think independently, who likes to do pioneering work and is willing to take initiatives to build bridges.
You have a master in statistics, data science or artificial intelligence, with a strong mathematical background. You have experience with both machine learning and statistical data analysis techniques. You are interested both in developing new methods and algorithms, as well as in applying them in a medical setting. You have good communication skills, enabling you to interact with professionals from other fields than yours. Candidates are expected to have excellent grades, research talent (as proven by their Master’s thesis), an excellent command of English, together with good academic writing and presentation skills. For residents outside the EER-area, a TOEFL English language test may be required.
The terms of employment are in accordance with the Dutch Collective Labour Agreement for Research Centres ("CAO-onderzoeksinstellingen"). The initial labour agreement will be for a period of 18 months. After a positive evaluation, the agreement will extended by 30 months. The gross monthly salary, for a PhD student on a full time basis, is €2,346 during the first year and increases to €3,007 over the four year period.
Employees are also entitled to a holiday allowance of 8% of the gross annual salary and a year-end bonus of 8.33%. CWI offers attractive working conditions, including flexible scheduling and help with housing for expat employees.
Please visit our website for more information about our terms of employment: https://www.cwi.nl/jobs/terms-of-employment
Applications can be sent before 5 May, 2019 through the 'Apply' button. Applications should include: your CV, a brief motivation letter (max. 1 page), a list of your MSc courses with grades, master thesis (if already available) or otherwise the Bachelor thesis and a summary of the Master thesis, and the name, e-mail address and phone number of at least one scientist able and willing to provide references.
For more information about the vacancies, please contact Prof. Peter Grünwald, email email@example.com, with cc to Karin Hagoort, K.Hagoort@umcutrecht.nl.
Middels onderstaande knop kun je direct solliciteren op deze vacature.Reageer op deze vacature