Invited speakers

Data Science Against Disease: Perspectives on Research Networks, eHealth and Medical Product Discovery, Development and Regulation

Eric D. PerakslisEric Perakslis

Executive Director of the Center for Biomedical Informatics and the Countway Library of Medicine at Harvard Medical School, USA

Speech abstract

As we rapidly progress through an era where data is no longer merely an aspect of science but is rapidly becoming the science, it is essential to maintain thought, perspective and focus on the challenges opportunities that continue to stimulate, enable and defy technological advance.

In biomedicine, the ability to generate and analyze data has never been greater but the biopharmaceutical industry remains target rich and medicine poor. Advances in genomics, genetics and other high-content biological data remain years from widespread population impact but the mysteries of complex biological processes that underlie difficult diseases are slowly being revealed. Pharmaceutical companies, technology innovators and academics are all working together to pool data into prolific research networks that hope to bring answers. Patient and advocacy groups are assembling registries and data warehouses in order to support the specific research they need. Electronic medical record use is now ubiquitous but are patients safer? Have these technologies lowered the costs of quality healthcare delivery? The answers are complex as so many of these transformations are still very much in process. Human potential, human expectations, economics and sociological barriers are more likely to limit scientific, medical and technological advances than are aspects of the technologies themselves. Successful technology-enabled transformation must include strategic focus, solid leadership and management, thoughtful execution and proactive risk management.

This talk will focus on the advances and challenges that technological progression is having across healthcare delivery, medical product development and technology and medical regulation.


Eric is the Executive Director of the Center for Biomedical Informatics and the Countway Library of Medicine at Harvard Medical School. Eric was most recently the Chief Information Officer and Chief Scientist (Informatics) at the U.S. Food and Drug Administration. In this role, Eric authored the first IT Strategic Plan for FDA and was responsible for modernizing and enhancing the IT capabilities as well as the in silico scientific capabilities at FDA. Prior to FDA, Eric was Senior Vice President of R&D Information Technology at Johnson & Johnson Pharmaceuticals R&D and was a member of the Corporate Office of Science and Technology.

Eric serves on the editorial board of Cancer Today magazine and serves on the editorial board and as the Associate Editor for Novel Communications for the DIA flagship publication, the Journal of and Therapeutic Innovation and Regulatory Science.

Eric has a PhD in chemical and biochemical engineering from Drexel University and also holds B.S.Che and M.S. degrees in chemical engineering. Eric’s current research interests are enterprise knowledge management, patient stratification, healthcare IT and translational informatics with the specific focus on precompetitive data sharing, risk-based analytics and open source systems globalization.

Here, There and Everywhere – Towards Healthcare Process Support in a Complex and Mobile World

Manfred ReichertManfred Reichert's picture

Director of the Institute of Databases and Information Systems, University of Ulm, Germany

Speech abstract

Healthcare organizations are facing the challenge of delivering high quality services to their patients at affordable costs. These challenges become even more prominent with the growth in the aging population with chronic diseases and the rise of healthcare costs. High degree of specialization of medical disciplines, huge amounts of medical knowledge and patient data to be consulted in order to provide evidence-based re­commendations, and the need for personalized healthcare are prevalent trends in this information-intensive domain. The emerging situation necessitates computer-based, mobile support of healthcare process management as well as clinical decision-making.

Business process management (BPM) technology provides a key to implement these changes. Though patient-centered process support and m-health become increasingly crucial in healthcare, BPM technology has not been broadly used in healthcare environments yet. One reason for this drawback has been the rigidity introduced by traditional process-centric healthcare information systems. In particular, the latter will be not accepted by medical staff if their use in exceptional situations is more cumbersome and time-consuming than just handling the exception with a phone call to the right person.  This keynote presentation reflects on recent developments from the BPM domain, which aim at a high degree of process support, flexibility, traceability, and mobility. These key features will be illustrated along existing BPM frameworks. Altogether, emerging BPM methods, concepts and technologies will contribute to further enhance IT support for healthcare processes.


Manfred Reichert holds a PhD in Computer Science and a Diploma in Mathematics. Since 2008 he has been appointed as full professor at the University of Ulm, where he is director of the Institute of Databases and Information Systems. Before, he was associate professor at the University of Twente in the Netherlands and a member of the management board of the Centre for Telematics and Information Technology (CTIT), which is one of the largest academic ICT research institutes in Europe. At CTIT he was coordinator of the strategic research initiative on e-health.

Manfred’s research interests include business process management (e.g., process flexibility, process lifecycle management, and object-centric processes), service-oriented computing (e.g., service interoperability, mobile services, and service evolution) and e-health.

Manfred has been PC Co-chair of the BPM’08, CoopIS’11, EMISA’13 and EDOC’13 conferences, and General Chair of the BPM’09 and EDOC’14 conferences. Recently, he co-authored a Springer book on process flexibility and obtained the BPM Test of Time Award at the BPM 2013 conference.

Automated Segmentation of White Matter Lesions using Global Neighbourhood Given Contrast Feature-based Random Forest and Markov Random Field

Ramamohanarao KotagiriRamamohanarao Kotagiri

Professor of Computer Science and Software Engineering, The University of Melbourne, Australia

Speech abstract
Recent studies show that, cerebral White Matter Lesion (WML) is related to cerebrovascular diseases, cardiovascular diseases, dementia and psychiatric disorders. Manual segmentation of WML is not appropriate for long term longitudinal studies because it is time consuming and it shows high intra- and inter-rater variability. In this paper, a fully automated segmentation method is utilized to segment WML from brain Magnetic Resonance Imaging (MRI). The segmentation method uses a combination of global neighbourhood given contrast feature-based Random Forest (RF) classifier and Markov Random Field (MRF) to segment WML. To remove false positive lesions we use a rule based morphological postprocessing operation. Quantitative evaluation of the proposed method was performed on 24 subjects of ENVIS-ion study. The segmentation results were validated against the manual segmentation, performed by an experienced radiologist and were compared to a recenlty published WML segmentation method. The results show a dice similarity index of 0.75 for high lesion load, 0.71 for medium lesion load and 0.60 for low lesion load.

Ramamohanarao (Rao) Kotagiri received the PhD degree from Monash University. He was awarded the Alexander von Humboldt Fellowship in 1983. He has been at the University of Melbourne since 1980 and was appointed as a Professor in computer science in 1989. He has held several senior positions including Head of Computer Science and Software Engineering, Head of the School of Electrical Engineering and Computer Science at the University of Melbourne and Research Director for the Cooperative Research Centre for Intelligent Decision Systems. He served on the editorial boards of the Computer Journal. At present, he is on the editorial boards of Universal Computer Science, and Data Mining, IEEE Transactions on Knowledge and Data Engineering and VLDB (Very Large Data Bases) Journal. Dr. Kotagiri was the program cochair for VLDB, PAKDD, DASFAA, and DOOD conferences. He is a steering committee member of IEEE ICDM, PAKDD, and DASFAA. He received a Distinguished Contribution Award for Data Mining. He is a fellow of the Institute of Engineers Australia, the Australian Academy Technological Sciences and Engineering, and the Australian Academy of Science. He was awarded a Distinguished Contribution Award in 2009 by the Computing Research and Education Association of Australasia.

ICHI 2014 © 2014