|
CALL FOR PAPERS Special Issue on Medical Data Streams Artificial Intelligence in Medicine An Elsevier Journal (JCR 2010 IF=1.568; 5-Year IF=1.891) |
|
AIM Many artificial intelligence researchers coming from different areas (data mining, machine learning, intelligent data analysis, pattern recognition, fuzzy logic, databases, etc.) design new approaches or adapt some of the traditional algorithms to data streams. In many medical applications different domain experts, e.g. physicians (would) benefit from the integration of the streaming medical data into decision support systems. The goal of this special issue is to gather researchers who deal with artificial intelligence for data processing, data management and knowledge discovery in clinical scenarios where data is produced as a continuous stream. IMPORTANT DATES Submission deadline: 18 Jun 2012 * Review notification: 18 Sept 2012 Revised submission: 18 Nov 2012 Second notification: 18 Dec 2012 Camera-ready submission: 18 Jan 2013 * earlier submissions are welcome; review process will start immediately after submission RATIONALE Artificial Intelligence in Medicine is facing a new challenge, created by the rapid growth in information science and technology in general and the complexity and volume of data in particular. Medical settings are using sensors and networks of health information systems to integrate data from patients, which requires storage, processing and management operators to enable further analysis and knowledge discovery. The main issue is that this data production often takes the form of high-speed continuous flows of data. Medical domains include several settings where data is produced in a streaming fashion, such as anatomical and physiological sensors, or incidence records and health information systems. New services appear allowing users to store and track information about their medical history, to connect to and stream data from medical devices. Medical data streams have become widespread and call for development of intelligent tools for making use of these data. Decision support, alerting services, ambient intelligence, assisted leaving and personalization services are just few examples of expected uses of actionable knowledge extracted from medical data streams. All of them are characterized by the high-speed at which huge amounts of data are produced, and often require fast and accurate information retrieval and analysis, that can effectively support clinical decisions. Dealing with continuous, and possibly infinite, flows of data require different approaches for data processing and management, and further machine learning and knowledge discovery. Particular issues to address include summarization of infinite data, incremental and decremental learning, resource-awareness, real-time monitoring of changes and recurrences, etc. This is an incremental task that requires incremental algorithms that integrate very large data bases in medical domains. Streaming artificial intelligence is increasingly important in the research community, as new algorithms are needed to process medical data in reasonable time. Furthermore, medical domains introduce extra peculiarities to the problem. For example, health information systems now deal with heterogeneous data sources, possibly distributed across health-care institutions. Moreover, this data integration requirement yields privacy-preserving issues. At the same time, it forces the system to take time, resources, and costs into consideration. Currently, generic techniques for intelligent analysis and learning from streaming data include also processing and management techniques which are widely spread in the applied computing research community. Also, in the medical domain, technological issues of data collection and storage, access, integration, information fusion, etc are also widely studied in the health informatics research community. However, adoption and development of tailored techniques for medical stream mining and clinical decision support is still to come. The goal of this special issue is to present cutting-edge research from experts in data stream processing interested in medical applications and medical domain experts interested in timely analysis of their data streams for clinical decision support. TOPICS Topics include but are not restricted to processing, managing and knowledge discovery for:
SPECIAL ISSUE GUEST EDITORS Pedro Pereira Rodrigues - LIAAD & Faculty of Medicine, University of Porto, Portugal Mykola Pechenizkiy - Eindhoven University of Technology, the Netherlands Mohamed Medhat Gaber - University of Portsmouth, United Kingdom Carolyn McGregor - University of Ontario Institute of Technology, Canada João Gama - LIAAd & Faculty of Economics, University of Porto, Portugal PAPER FORMATTING, SUBMISSION AND REVIEWING Authors should follow the guide to authors available at AIIM website to format their article. Please note that, for the initial submission, only PDF format of submissions is allowed. Papers to this special issue should be submitted by email to the guest editors at pprodrigues@med.up.pt and not via the online Elsevier Editorial System. Each paper submission will be peer-reviewed by at least three reviewers. The quest editors will screen the submissions for eligibility and quality. Special issue articles should report on significant previously unpublished work. We do invite authors to submit their revised and substantially extended workshop and conference papers. As a rule of thumb the journal paper submission should contain at least 30% of new previously unpublished material. Please indicate in your cover letter whether the journal paper submission is based on or extend substantially a previously published conference or workshop paper, in case of which a description of what is new must be clarified in the submission. All papers accepted to the special issue are subject to the final approval by the Editor-in-Chief of AIIM journal. It is planned that the articles will appear in one of the issues of the Artificial Intelligence in Medicine Journal, edited and published by Elsevier, in 2013. AIIM typically has 9 issues per year. |