ACSW 2013 Health Informatics and Knowledge Management keynote speakers


Professor Riccardo Bellazzi

Professor Riccardo Bellazzi

Bio: Riccardo Bellazzi is the Professor of Biomedical Engineering and Director of Biomedical Informatics Research laboratories at the University of Pavia, Italy.His current research interests include intelligent data analysis, biomedical data mining, bioinformatics, information technology infrastructures to support biomedical research, and secondary use of clinical data. He is a Board Member of the International Medical Informatics Association, a Fellow of the American College of Medical Informatics, associate editor of BMC Biomedical Informatics and a member of the editorial board of Methods of Information in Medicine. The organisers of Australasian Computer Science Week are pleased to host his first visit to Australia to give the Health Informatics and Knowledge Management keynote presentation during ACSW, at the University of South Australia 29 January to 1 February 2013.


Allan H. Baird

Allan H. Baird

Topic: The new Royal Adelaide Hospital –The Age of the Digital Hospital Dawns in South Australia

Abstract: The South Australian Government developed the Health Care Plan 2007-2016 to meet the health challenges of an ageing population, increasing incidence of chronic diseases, international workforce shortages and ageing infrastructure. The plan included an outline of the most significant single investment in health care in South Australia’s history - the new Royal Adelaide Hospital. Efficient and effective application of the new Royal Adelaide Hospital Model of Care is reliant upon a robust ICT system which is fully integrated throughout the Facility and with primary and secondary health providers. The ICT element of the hospital is critical in ensuring that the return on the investment in such a new and complex facility will be achieved.

Bio: Allan Baird is a graduate of the SA Institute of Technology holding a B. Bus and Associate Diploma in Business (Industrial Engineering). He also holds a Master of Business (Research) from the former School of Information Systems, University of SA. Allan is a Fellow of the Australian Computer Society, and an Associate of the Institute of Industrial Engineers (Aust.) His current role isICT Consultant with the SA Department of Health and Ageingfor the new Royal Adelaide Hospital Project. Allan is also an Executive Consultant with Tasman Human Resource Consulting, specialising in Stakeholder Management. Prior to this Allan was the Industry Alliance Manager with the School of Computer and Information Science at the University of South Australia (UniSA). Before joining UniSA he held senior positions in Hewlett-Packard Corporation, Compaq Computer Corporation, and Digital Equipment Corporation in Australia, The People’s Republic of China, Singapore and the United States of America.


Jim Warren

Jim Warren

Topic: The Role of Electronic Medical Records in the Identification of Suboptimal Prescribing for Hypertension Management: An Opportunity in Unchanged Therapy

Abstract: A Participatory Action Research (PAR) approach was taken to identify electronic medical record (EMR) queries for hypertension management quality review in the context of a Pacific-led New Zealand general practice. In each PAR cycle, queries to identify patients with prescribing at variance from evidence-based practice were formulated and run, relevant patient notes were retrieved, and a quality audit of the medication decisions was carried out by a medical practitioner working in the practice. 764 enrolled and funded patients with current antihypertensive prescriptions were queried regarding adherence to national treatment guidelines. Queries based on drug classes indicated by specific comorbidities (e.g. hypertension complicated by diabetes) retrieved few cases, and with almost none having a compelling case for change in therapy upon review. A query on unchanged therapy while cardiovascular risk (CVR) and systolic blood pressure remained high, however, yielded 30 cases for review, and 10 of these were deemed as warranting further investigation. We conclude that a promising area for the use of EMR queries to improve long-term condition management is in identification of patients with persistently high risk of adverse outcomes and concurrent unchanged therapy during successive general practice visits.

Bio: Jim Warren is Chair in Health Informatics at the University of Auckland, holding a joint position in Computer Science and Population Health. He has over 20 years research experience in health IT, with a particular interest in systems to support both patients and providers in better management of long-term conditions. Prior to commencing with University of Auckland in 2005 he worked for the University of South Australia for 12 years. He has a Bachelor of Science in Computer Science and PhD in Information Systems from the University of Maryland. He is the recent past chair of Health Informatics New Zealand, the member organisation of IMIA for New Zealand. His research group, National Institute for Health Innovation, has been closely involved in support and evaluation of New Zealand’s national Health IT Plan.


Lua Perimal-Lewis

Lua Perimal-Lewis

Topic: Analysing homogenous patient journeys to assess quality of care for patients admitted outside of their ‘home-ward’

Abstract: This study is the first to explore the quality of care based on the outlier or the inlier status of patients for a large heterogeneous General Medicine (GM) service at a busy public hospital. The study compared the quality of care between ward outliers and ward inliers based on a homogenous group of patients using Two-step clustering method. Contrary to common perception, ward outliers had overall shorter Length of Stay (LOS) than ward inliers. The study also was unable to support the perception of shorter LOS in the outlier group being associated with higher in-hospital mortality. The study confirmed that overall the outliers received inferior quality of care as discharge summaries for the outliers were delayed and more outliers were re-admitted within 7 days of discharge in comparison to the inliers.

Bio: Lua Perimal-Lewis started her career in IT as Data Analyst with the Department of Education in 2000. Since then (2001 – 2010) she has worked as Information Analyst, Programmer, Software Quality Assurance Subject Matter Expert (SME) and Software Configuration Management SME for Electronic Data System Australia (EDS) and Hewlett-Packard Australia (HP). She completed Master of IT (Computing) at Flinders University in 2009, Graduate Diploma in the Management of Information Systems from IMIS, UK and B.Sc. (Hons) Computing from University of Greenwich, UK. She is currently a Ph.D. candidate with the School of Computer Science, Engineering and Mathematics at Flinders University undertaking research in the area of Inpatient Flow Process Mining, Modelling and Simulation for Hospital Management Decision Support.


Julie Harris

Topic: Next Generation Linkage Management System

Abstract: SA NT Datalink is a consortium of government departments, universities and other parties that are committed to providing high quality data linkage to support research. The Next Generation Linkage Management System has been developed using open source technologies to manage disparate source data files coming into the organisation, cleansing and standardisation, then the analysis of the data which will determine blocking parameters and linkage weights. The open source linkage engine called FEBRL (Freely Extensible Biomedical Record Linkage) is used to link the datasets using probabilistic methods. For storage of the linked records SA NT Datalink has employed a graph database which allows us to keep and reuse the rich comparison vectors.


Shima Ghassem Pour

Topic: Validating Synthetic Health Datasets for Longitudinal Clustering

Abstract: Clustering methods partition datasets into subgroups with some homogeneous properties, with information about the number and particular characteristics of each subgroup unknown a priori. The problem of predicting the number of clusters and quality of each cluster might be overcome by using cluster validation methods. This paper presents such an approach incorporating quantitative methods for comparison between original and synthetic versions of longitudinal health datasets. The use of the methods is demonstrated by using two different clustering algorithms, K-means and Latent Class Analysis, to perform clustering on synthetic data derived from the 45 and Up Study baseline data, from NSW in Australia.

Bio: Shima Ghassem Pour received her B.Eng. Computer Hardware Engineering from Sadjad University, Iran in 2007 and her Master of Engineering Management from University of Newcastle, Australia in 2009. She is a PHD student at University of Western Sydney and her research expands on data mining methods for longitudinal health data.