Version 2 Universidade Nacional da Irlanda em Galway -- Ciência sem Fronteiras PhD Project Template Use one form per project Please complete & submit to international@nuigalway.ie as soon as possible, and by 27/11/2012 In your email, begin the subject line with [SWB] (be sure to use square brackets) to ensure that your email is filed correctly. Emails will be automatically filed PI name & contact details: School: Dr Michael Madden: michael.madden@nuigwalway.ie +353 91 493797 Information Technology, College of Engineering & Informatics Has project been agreed with head (or nominee) of proposed registration school? Yes Research Centre / group affiliation: Machine Learning & Data Mining Research Group Research group / centre website: http://datamining.it.nuigalway.ie/ PI website / link to CV: http://datamining.it.nuigalway.ie/ Brief summary of PI research / research group / centre activity (2 or 3 lines max): We focus on advances in techniques for machine learning and data mining, motivated by solving important practical applications. We work on classification algorithms, kernel methods, reinforcement learning, probabilistic inference, and data stream mining. Title & brief description of PhD project (suitable for publication on web): Personalised Intensive Care Medicine Using Probabilistic Model-Based Data Analytics Much of what we know about the human body is described formally as sets of mathematical equations. While these provide a succinct and accurate description of the general behaviour of the system being modelled, they are not attuned to individuals. Every patient in an Intensive Care Unit has different medical problems, so for example their response to drugs may be quite different from the normal response. Therefore, for medical models to be useful in understanding how individual patients will be respond, model parameters must be “individualised”. In the ICU, we can use real-time data from bed-side monitors and lab results to tune models to individual patients, but some results are infrequent and there can be errors in data (for example if leads are disconnected or monitors need recalibration). We have developed a methodology for automatically mapping systems of equations to a Dynamic Bayesian Network (DBN) representation. Our framework re-estimates model parameters efficiently and continuously, based on accumulated evidence. It provides principled handling of data and Version 2 Universidade Nacional da Irlanda em Galway -- Ciência sem Fronteiras model uncertainty, and facilitates integration of multiple time-series. It makes a clear distinction between true and measured values, to account for data uncertainty. In this project, the goal is to build on our existing work in order to create new knowledge-intensive data analysis methods that can improve the provision of modern evidence-based medicine. This will involve interdisciplinary research collaborations with mathematicians and end-user clinical experts. With our clinical collaborators and Ethics approval, we will curate a new dataset of anonymised patient records. This will be used to research and develop new data mining methods in which domain knowledge will be central, and to evaluate their ability to improve physicians’ understanding of critical care data. The result will be a new approach whereby clinical knowledge, even though incomplete and approximate, can be encoded automatically, refined with data from the population level to patient level, and used to generate actionable and meaningful information to support decision-making. Unique selling points of PhD project in NUI Galway: The National University of Ireland Galway, founded in 1845, has a distinguished record in scholarship and research. The University enjoys a close relationship with Galway city, which is shaped by artistic communities, active student life, innovative industry and leading edge research. The University’s Structured PhD programme enables researchers to take advanced technical courses as well as to develop their research skills in the early stages of their PhD work. In the Machine Learning & Data Mining Group, we have long-standing interdisciplinary collaborations with colleagues in Mathematics, Applied Mathematics, and Intensive Care Medicine. Our group also has strong links with research groups in other universities internationally, such as the University of California Berkeley (including Stuart Russell, who has co-authored with us on our earlier work on this topic), the University of California Irvine and the University of Helsinki, Finland. Name & contact details for project queries, if different from PI named above: As above. Please indicate the graduates of which disciplines that should apply: Computer Science, Software Engineering, Mathematics, or similar disciplines. Ciência sem Fronteiras / Science Without Borders Priority Area: Please indicate the specific programme priority area under which the proposed PhD project fits- choose only one (tick box): Engineering and other technological areas Pure and Natural Sciences (e.g. mathematics, physics, chemistry)/Physical Sciences (Mathematics, Physics, Chemistry, Biology and Geosciences) Health and Biomedical Sciences / Clinical, Pré-clinical and Health Sciences Version 2 Universidade Nacional da Irlanda em Galway -- Ciência sem Fronteiras Information and Communication Technologies (ICTs), Computing Aerospace Pharmaceuticals Sustainable Agricultural Production Oil, Gas and Coal Renewable Energy Minerals, Minerals Technology Biotechnology Nanotechnology and New Materials Technologies for Prevention and Mitigation of Natural Disasters Bioprospecting and Biodiversity Marine Sciences Creative Industry New technologies in constructive engineering Please indicate which of the following applies to this project (referring to Science Without Borders arrangements): Suitable only as a Full PhD (Y/N): _ ____ Available to candidates seeking a Sandwich PhD arrangement (Y/N): _____ Suitable for either/Don’t know: