Mark Hoogendoorn appointed Professor of Quantitative Data Analytics
VU Amsterdam’s Executive Board has appointed Mark Hoogendoorn professor in the Computer Science department, where he will hold a chair in Quantitative Data Analytics.
09/17/2020 | 2:00 PM
Far from flawless
Although machine learning is in the news a lot these days, with great successes being reported, many practical applications remain far from flawless. Hoogendoorn: “We definitely still have a long way to go before we can truly be successful at applying machine learning in certain contexts. Think of the healthcare sector, for example, in which machine learning can be used to create models based on data collected from previous patients. Those models can then predict how a patient’s illness will progress, or which treatment option will have the greatest effect.” To do this properly, you need to be able to look under the bonnet of the models you create, so that you can see why they make certain predictions. In many cases, this is not yet possible, says Hoogendoorn. “Another factor is that for rare diseases, limited amounts of patient data are available. This means that the algorithms must be able to learn very efficiently. These are just a few examples of essential developments that need to happen in this field.”
More fundamental research needed
In order to facilitate these essential developments, more fundamental research into machine learning techniques is needed. “This will make it easier to apply machine learning in practice, and eventually benefit patients by helping doctors treat various conditions more effectively. A lot of this kind of interdisciplinary research is currently being done at VU Amsterdam, and I would like to contribute to it,” says Hoogendoorn.
Mark Hoogendoorn obtained his PhD from VU Amsterdam in 2007, after which he started working as a postdoctoral researcher at the University of Minnesota. He then returned to VU Amsterdam to work as an assistant professor. In 2015, he was a visiting scientist at the Massachusetts Institute for Technology. His research focuses on predictive modelling and personalization using AI techniques, mainly for applications within the health domain. He participated in and led a large number of research projects related to AI and healthcare, and served as a coordinator on the ICT4Depression FP7 project. He is currently a board member of the International Society for Research on Internet Interventions, in addition to chairing the organization’s Special Interest Group on Data Sharing and Standards. He also holds a position on the board of Amsterdam Medical Data Science.