特邀嘉宾:
Peter Bath, Professor of Health Informatics and Head of the Information School at the University of Sheffield, UK. He has been involved in funded research involving 23 grants from university, local, national and international funding bodies worth, in total, over £3 Million. He is Principal Investigator for £1.03 million multi-centre grant from the UK Economic and Social Research Council (ESRC) to explore how people in extreme circumstances share information in online environments, including social media, personal blogs and web forums (2014-2017). He has supervised 20 completed PhD students (including 3 visiting research students) and is supervisor of 10 current PhD students (7 full-time, 3 part-time). Peter has 222 refereed publications including 120 full articles in refereed journals in print, 105 publications in refereed conference proceedings/abstracts, 4 refereed book chapters. Professor Bath is the Editor of 11 Conference Proceedings and is Associate Editor of the Health Informatics Journal. According to Google Scholar, his work has been cited 4202 times (1917 since 2013). The h-index for his publications is 37 (23 since 2013) and the i10-index is 80 (60 since 2012). Professor Bath is Chair of the University of Sheffield Research Ethics Committee (UREC) (2015-present), having previously been Deputy Chair (2012-2015) and Faculty of Social Sciences representative (2007-2013).
Use of data mining methods to predict loneliness in older people
Many countries across the world are experiencing increased numbers and proportions of older people within their populations. Loneliness is an important problem for older people, as prolonged periods of loneliness can have adverse effects on physical and mental health and overall wellbeing. For example, loneliness has been shown to be associated with anxiety and depression as well as increased mortality among elderly people. The risk factors for loneliness are complex and multifactorial, and understanding the causes and effects of loneliness is important in developing interventions to reduce loneliness and improve health and well-being. This key-note talk will discuss research at the University of Sheffield which is utilising advanced data mining methods to develop a better understanding of the factors associated with loneliness in older people. The aim of this research is to develop a better understanding of the risk factors for loneliness and to develop models that will predict the occurrence of loneliness in later life.
Robert Moskovitch, Dr. Robert Moskovitch is a faculty at the department of Software and Information Systems Engineering at Ben Gurion University, in which he is heading the Complex Data Analytics Lab. He did his post doc fellowship at the department of Biomedical Informatics at Columbia University. He is a member of BGU’s Zlotowsky Center for Neuroscience, and BGU’s @Cyber security center. Prior to that, he headed several Research and Development projects in Information Security at Deutsche Telekom Innovation Laboratories. He is an Academic Editor at PLOS ONE, and has served on several journal editorial boards, as well as on program committees of several conferences, such as ACM KDD and IEEE ICHI and workshops in Information Security and Biomedical Informatics, as well as edited recently special issues at JASIST and JBI. He published more than seventy peer reviewed papers in leading journals and conferences, such as IEEE ICDM, Data Mining and Knowledge Discovery, KAIS, JAMIA, JBI and more, several of which had won best-paper awards. His lab focuses mainly on the development of Temporal Data Analytics methods, and their applications to the biomedical domain, but not exclusively. Dr. Moskovitch’s lab is funded by Microsoft, IBM, Amdocs, and governmental agencies, and collaborates with scientists from university medical centers, such as Columbia, Mount Sinai, Peking University, IIT New Delhi, Maccabi Healthcare Services and more. He is the Analytics Program Chair of IEEE International Conference of Healthcare Informatics 2018 (NYC).
Title: Analysis of Heterogeneous Multivariate Time Stamped Data
Analysis of heterogeneous multivariate time stamped data is one of the most challenging topics in data science in general, and in healthcare analytics specifically. Time stamped data can be sampled in a fixed frequency, commonly when measured by electronic means, but also in a non fixed frequency, often when made manually - a typical situation in biomedical data, whether fast data such as in ICU, or slow such as generally in EHR. Additionally, raw temporal data can represent durations of a continuous or nominal value represented by time intervals. In this talk the idea of transforming time point series into meaningful symbolic time intervals, using a process often called Temporal Abstraction, will be presented to bring all the temporal variables, having various representations, into a uniform representation. Then, KarmaLego, a fast time intervals mining method for the discovery of non-ambiguous Time Intervals Related Patterns (TIRPs) represented by Allen's temporal relations, will be presented. TIRPs can be used for several purposes: temporal knowledge discovery, and classification of multivariate temporal data, using the KarmaLegoS framework, in which TIRPs are used as classification features. To increase the classification accuracy a novel supervised Temporal Discretization for Classification (TD4C) method will be introduced, including an evaluation on three real life datasets from the biomedical domain. Finally, results of the use of TIRPs for outcomes prediction in patient data, such as clinical procedures or conditions, will be demonstrated on Columbia University Medical Center EHR data.
Huafang Gao, Ph.D. Professor, Director of Human Genetic Resource Center of National Research Institute for Health and Family Planning, Executive director of National Center for Human Genetic Resources. Vice-chairman of clinical data and biological sample bank Committee of Chinese Research Hospital Association, Vice-chairman of health management Committee of China Medicine Education Association. Prof. Gao has more than ten years experience in in vitro diagnostic reagents research and industry. He has developed a series of products for molecular diagnostics. Some of the products have been approved by CFDA and have been widely applied in clinical.
Title: Precision Medicine Powered by Human Genetic Resources
A national service network for health screening in young women (Pregnancy Risk Assessment Monitoring Network) has been set up by National Research Institute for Health and Family Planning, there are more than ten million young women take part in the screening each year. National Center for Human Genetic Resources (NCHG) will be built and put into operation this year. A ten million scale national biobank will begin to collect a large number of biological samples from research hospitals. So a national level big data center is taking shape in NCHG. The big data will be useful for precision medicine and medical AI research.