IDS believes that a strong, vibrant, and rewarding academic environment is essential for excellent Data Science research. The mission of the Institute of Data Science is to foster an interfaculty environment for collaborative innovation in the development and application of data science technologies
As data scientists, IDS leverages it's expertise to find, retrieve, manage, clean, integrate, prepare, visualise, interpret, and build models from data while consciously navigating hardware, software and bandwidth constraints along with social, legal and ethical issues. While using these interdisciplinary skills, IDS must also work with others to maximise it's productivity and the impact of it's work.
In Data Science, we build on theories and techniques from many fields including:
- information science
- computer science
- data management
- data mining
- machine learning
- data quality assessment
Michel Dumontier talks about the strategic aim of the Institute of Data Science:
- Coordinate, strengthen and promote Data Science activities at Maastricht University
- Spearhead new interfaculty initiatives targeting Data Science research, education, infrastructure and valorisation
Core research themes
Accelerating scientific discovery
Accelerating scientific discovery through the development of powerful Artificial Intelligence (AI) platforms coupled with FAIR data and services to systematically unlock knowledge about the world we live in
Most aspects of scientific inquiry remain entirely dependent on human expertise and effort. However, no one person can keep track of the vast amounts of data, tools, and knowledge being generated each and every day. Moreover, with recent reports claiming rates of non-reproducibility of 64% in psychological studies and up to 89% in pharmacological studies, there is an urgent need to find effective approaches to conduct scientific investigations that take into account and make sense of the vast amounts of data in a more reliable manner.
Recent developments in data-driven systems show that machines can effectively ingest complex information and outperform humans in many tasks. Topics include, but are not limited to:
- summarising what is known about a topic and contextualising new findings for an individual
- incentive-friendly platforms for sharing digital research objects (e.g. data, software, publications) that are maximally FAIR – Findable, Accessible, Interoperable, Reusable
- uncovering evidence that supports or potentially disputes a scientific assertion
- designing, prioritising and orchestrating experiments to fill in knowledge gaps
- tracking scientific progress, the evolution of scientific disciplines, and scientific impact
- adaptive, data-driven learning to maximise the accuracy and completeness of any human endeavour
Improving clinical care and well-being
Improving clinical care and well-being through the creation of intelligent systems that bring the science of medicine back into the practice of medicine
Despite ritualistic and time-consuming chronicling of patient encounters in electronic health care systems worldwide, these on their own cannot translate into improved patient outcomes. Meanwhile, new technology is filling the gap to monitor and advise patient health on a per second basis, but often has uncertain health benefits. Once again, vast amounts of data are becoming readily available, but we lack the infrastructure, methodology and understanding of the social, legal and ethical aspects of health information systems to take maximum advantage of these developments.
Our goal in this research theme is to exploit emerging sources of health-relevant data to improve clinical care and wellbeing. Topics include, but are not limited to:
- using distributed data in a privacy-preserving manner to identify environmental determinants of health at the level of an individual
- platforms to undertake systematic comparative effectiveness research using millions of patients worldwide
- methods for continuous and personalised diagnosis, prognosis and treatment
- methods to improve the quality of the physician-patient interaction (e.g. constructing a brief but accurate patient summary from the patient’s social networking data)
- methods to aid care workers in finding and working with people who need help at the time they need it
Empowering communities to characterise, implement and monitor data-driven solutions that optimise their investments to maximise their quality of life
It wasn’t that long ago that the tools for multivariate analysis, data mining and machine learning had limited utility and could only be used by specialists. Today, data science is more accessible and easier to use than ever – open source frameworks are freely available, compute-hungry analyses can be readily executed on cloud infrastructure, and enormous online communities are sharing their recipes and their accomplishments.
Indeed, people from all walks of life are applying data science out of curiosity and to create altogether new applications to meet a societal need. We believe that data science can be the bridge that brings youth and community leaders together to better understand the problems that they face and craft solutions to make life better for them and their neighbours.
In this research theme, we will focus on bringing data science to a region, nestled in the heart of Western Europe, which is making investments to overcome serious economic challenges and must strive to include youth as part of a strategy for economic and social prosperity.
Topics of interest include, but are not limited to:
- digital infrastructure to enable collaboration on policy making
- infrastructure for data sharing while strengthening privacy controls and cybersecurity for citizens and industry
- data-driven methods to foster job creation and reduce social inequality
- identification and removal of barriers to digital innovation and commercialisation for young data scientists and entrepreneurs