DateWednesday October 16, 2019 from 1:30 PM to 2:30 PM
BuildingGemini-South (GEM-Z) 1.03
OrganizerDragan Bosnacki & Pieter Van Gorp
The speaker of our second meeting of the new series will be Harm Buisman, a former BME student and currently a Clinical data scientist at IKNL, the Netherlands comprehensive cancer organization. The talk is on the Cancer surveillance project at IKNL and deals with extracting knowledge from cancer registry data.
Cancer surveillance: detecting suprising patterns from cancer registry data
Cancer is the leading cause of death in the Netherlands, with 47.000 people dying of cancer in 2017. With such numbers, even small improvements in prevention and care can have a big impact. The question is, where do we start?
For this we need data. Data on cancer is collected in registries. The Netherlands cancer registry (NCR) maintained by IKNL, the Netherlands comprehensive cancer organization, contains data on over 2.3 million cancer patients and is growing with over 100.000 patients a year. These data are used by many scientific & clinical research organizations such as universities, hospitals and IKNL itself to improve cancer care and contribute to prevention.
Traditionally research starts with a trigger from the field, e.g. a doctor notices a lot of patients working with asbestos develop lung cancer. This leads to a request for data from the NCR and the research question is answered using the data. But, why wait for a trigger from the field? Can't we let the data speak? This is the goal of the cancer surveillance project at IKNL. We want to extract surprising findings from the NCR as a trigger for further epidemiological research. In the talk we give an introduction to the cancer surveillance project and discuss processing geographical data, applying standardization to correct for bias and discuss how to extract surprising patterns.
The (Big) Data and Health Meetings meetings were founded in 2017, mainly as a forum for the people from the Biomedical Engineering Department interested in methods for data analysis, like machine learning, neural networks or different statistical techniques. However, the meetings have always been open for researchers from other TU/e departments as well as outside the university. Since late 2019 onward, the meeting series is also endorsed and supported by the Data Science Center Eindhoven (DSCE). In particular, alignment to the multi-disciplinary research programs of Health Analytics (http://tue.nl/ds/ha) and Quantified Self (http://tue.nl/ds/qs) and Health research within EAISI is facilitated.