Keynotes

The 2015 International Workshop on Data Analytics for Evidence-based Healthcare

 

Professor Osmar Zaiane

Department of Computer Science, University of Alberta, Canada


Title

From Big Data Analytics in Healthcare to New Generic Data Mining Approaches


Abstract

More data may lead to more accurate analyses. Combining disparate information sources may bring up the value of the data. These are not new held opinions. The advent of the so-called Big Data phenomenon which has not spared the healthcare domain, has only brought more evidence to these notions and reinforced the conviction.

The views about Big Data have been articulated in many ways, but the concept boils downs to exponential and rapid growth of data, referred to as Volume and Velocity, but more importantly the necessity to integrate data from distributed, dissimilar and essentially poles apart data sources often belonging to different custodians. This is known as Variety. This is obviously not new or foreign to the healthcare domain where data has always been of different kinds, amasses at high speed and is dispersed. One recognized peculiarity of Big Data is that traditional data processing applications are inadequate and new techniques for data analysis/data science are required. The impact in the other direction is also conceivable.

In this talk, after briefly introducing Big Data and reporting on a real research application in medicine, I will outline some innovation in conventional data analysis for generic data mining derived directly from healthcare data science projects.


Biography

Osmar R. Zaïane is a Professor in Computing Science at the University of Alberta, Canada, and Scientific Director of the Alberta Innovates Centre for Machine Learning (AICML). Dr. Zaiane joined the University of Alberta in July of 1999. He obtained a Master's degree in Electronics at the University of Paris, France, in 1989 and a Master's degree in Computer Science at Laval University, Canada, in 1992. He obtained his Ph.D. from Simon Fraser University, Canada, in 1999 under the supervision of Dr. Jiawei Han. His Ph.D. thesis work focused on web mining and multimedia data mining. He has research interests in data analytics, namely novel data mining algorithms, web mining, text mining, image mining, social network analysis, data visualization and information retrieval with applications in Health Informatics, e-Learning and e-Business. He has published more than 200 papers in refereed international conferences and journals, and taught on all six continents. Osmar Zaiane was from 2009 to 2012 the Secretary-Treasurer of the ACM SIGKDD (ACM Special Interest Group on Data Mining) which runs the world’s premier data science, big data, and data mining association and conference. He is also on the steering committee of many data mining conferences such as IEEE International Conference on Data Mining, Advanced Data Mining and Applications, Data Science and Advanced Analytics. He was the Associate Editor then Editor-inChief of the ACM SIGKDD Explorations from 2003 to 2010. He is also Associate Editor of the Knowledge and Information Systems, An International Journal, by Springer, and of the journal Data Mining and Knowledge Discovery by Springer, as well as the International Journal of Internet Technology and Secured Transactions He was the General co-Chair of the IEEE International Conference on Data Mining ICDM 2011. Osmar Zaiane received the ICDM Outstanding Service Award in 2009 and the 2010 ACM SIGKDD Service Award.

 
 

Dr. Guy Tsafnat

Centre for Health Informatics (CHI), Macquarie University, Australia


Title

Evidence Mining Systems


Abstract

Evidence based medicine is the use of all available medicine to provide the best, safest and most cost effective care we know. But evidence based medicine is at a crisis point: the rate at which evidence is produced far exceeds our capacity to incorporate evidence into practice. Mining the evidence base for discovery, synthesis and summarisation is a challenging multi-disciplinary task with the potential to make evidence based medicine sustainable.

Efforts in evidence mining include process automation, data linkage, machine learning and text processing for appraisal and data extraction. Current research focuses on individual sub-tasks and often with a narrow set of technologies. However, it is clear that complex systems that integrate multiple technologies will be required solve the challenge of evidence mining.

The Evidence Agent Academy is an agent-based system in which systematic reviewers and clinicians can teach generic software agents how to answer specific clinical questions. The agents then utilise multiple tools to producing high-quality evidence summaries at the push of a button. While the Evidence Agent Academy is practical, more research is still needed to realise sustainable evidence based medicine.

Biography

Dr. Guy Tsafnat is a senior research fellow and head of the Computable Evidence Lab (CEL) at the Centre for Health Informatics, Macquarie University in Sydney. With a background in computer and information sciences and over 20 years experience in text processing, machine learning and artificial intelligence, Dr. Tsafnat's research focuses on applications in evidence based decision support systems. Modern evidence still primarily consists of clinical trials published as scientific papers. Effective evidence gathering, synthesis and dissemination thus poses significant challenges in text mining, computational reasoning, public health and medicine. The next generation of evidence will additionally come from new sources such as electronic health records, wearable devices, biosensors and systems biology. These will pose even more informatics and statistical challenges for in how we use such evidence to deliver safer, cheaper and more effective health services. Dr. Tsafnat is also CEO and co-founder of Spokade Pty Ltd, a health start-up dedicated to combating antibiotic resistance through specific monitoring of antibiotic resistance genes.

 

Sponsored by the Centre for Health Informatics (CHI), Australian Institute of Health Innovation (AIHI) and Department of Computing, Macquarie University, Australia