Big Data & Machine Learning

Practical applications of big data technologies in medical informatics

ImpactHub - Atlantic room

18th November, 16:00-17:00

In this talk we will provide an overview of the current challenges in medical informatics and we will present in-depth details about the architecture of a system used by the USA government to tackle a particular problem in this field: extraction of drug-drug interactions from medical records and drug product labels. We will in particular focus on how natural language processing, machine learning and big data technologies are combined for such a project. We will also give a general introduction about medical informatics and present some key projects currently developed by the USA government and the FDA in the field.

Johann Stan

European Patent Office

Dr. Johann Stan received his MSc in Computer Science from INSA de Lyon in France and his PhD in Computer Science from Jean-Monnet University. Having spent several years as a research engineer in Bell Labs, he authored several patents and publications related to the leverage of content in online social networks for the improvement of user experience. He is the chair of the SDAIN workshop (Semantic and Dynamic Analysis of Information Networks), last year organized within the Asonam conference and steering committee member of the MISNC conference (The 2014 Multidisciplinary International Social Networks Conference) . He also serves as patent and big data expert for the European Young Innovators Forum and is the curator of TEDxTarguMures. Johann worked several years at the National Institutes of Health in Washington D.C., exploring machine learning techniques for drug-drug interaction extraction. Currently, he is patent examiner in information retrieval at the European Patent Office situated in The Hague and deals with applications from e.g. Google, Facebook and IBM.