Abstract: Electronic health records (EHR) contain information about individuals' visits to healthcare services. In this talk, I will give an overview of current trends in using deep learning to analyse electronic health records. I will then focus on our recent work where in collaboration with the Finnish Institute for Health and Welfare we analysed the EHR data from 1.3 million individuals, aged 65 or more, in order to predict their need for healthcare services in the coming years. Predictions from similar models are used to allocate funding to different regions in Finland.

Bio: Pekka Marttinen is an assistant professor in machine learning in the department of computer science at Aalto University. His research focuses on probabilistic machine learning, inspired by applications in health and genomics. He contributes to teaching in the machine learning and bioinformatics Master’s programs. He received his Ph.D. in Statistics at the University of Helsinki in 2008, and has been employed at Aalto since 2009, interleaved by periods as a visitor at the Center for Communicable Disease Dynamics at Harvard and the Sanger Institute in Cambridge.

Speaker: Professor Pekka Marttinen

Affiliation: Department of Computer Science, Aalto University

Place of Seminar: ZOOM

More information will be updated shortly