Friday November 12, 2010
A one-day colloquium in Washington, DC
in conjunction with the 2010 Annual Symposium of the American Medical informatics Association
Kirk T. Phillips and Stephen Swift (chairs)

Organized in collaboration with Intelligent Data Analysis and Data Mining Working Group of the International Medical Informatics Association, and Knowledge Discovery & Data Mining Working Group of the American Medical Informatics Association

• Submission: August 1, 2010
• Notification: September 1, 2010
• Camera-ready: October 1, 2009

GENERAL INFORMATION

The IDAMAP series is devoted to computational methods for data analysis in medicine, biology and pharmacology that present results of analysis in the form communicable to domain experts and that somehow exploit knowledge of the problem domain. Such knowledge may be available at different stages of the data-analysis and model-building process. Typical methods include data visualization, data exploration, machine learning, and data mining.

Gathering in an informal setting, colloquium participants will have the opportunity to meet and discuss selected technical topics in an atmosphere which fosters the active exchange of ideas among researchers and practitioners. The colloquium is intended to be a genuinely interactive event and not a mini-conference, thus ample time will be allotted for general discussion. A student challenge on data integration will be organized. Author of the best solution will be invited to present the work at the workshop.

TOPICS

In the colloquium, the attention will be given to methodological issues of intelligent data analysis and on specific applications in biomedicine and pharmacology. In terms of methodology, topics include, but are not limited to:

• data mining and machine learning techniques for supervised and unsupervised learning problems,
• exploiting domain knowledge in learning and data analysis,
• data visualization and exploration,
• analysis of large data sets and relational data mining,
• knowledge management and its integration with intelligent data analysis techniques, and
• integration of intelligent data analysis techniques within biomedical information systems.

A paper submitted to the colloquium is expected to show a selected methodology can help to solve relevant problems in medicine, and would typically address the following issues:

• What is the medical or clinical problem addressed?
• Was any prior knowledge available? How was this used in the data analysis or interpretation of results?
• How is/can the newly discovered knowledge put into use?

Contributions that discuss particular applications of intelligent data analysis techniques are invited, and can for example cover analysis of medical and health-care data, data coming from clinical bioinformatics data bases (like microarray data and DNA sequence analysis), analysis of pharmacological data, drug design, drug testing, and outcomes analysis.

PROBLEM OWNERS

In addition to regular scientific contributions, we welcome descriptions of problems or data sets that could potentially benefit from an analysis through Intelligent Data Analysis or Data Mining. Problem descriptions must be submitted as abstracts and will be presented at the workshop. They must briefly introduce the problem and provide an overview of the main objectives of the analysis. After the presentations, ample time will be reserved for discussion.

DATA ANALYSIS TOOLS

We also invite developers of data analysis tools to send an abstract with the description of their tool, and give a demonstration during a special demo session on data analysis tools at the colloquium. The abstract should describe the underlying methodology of the tool and sketch the potential for application in the field of intelligent data analysis in biomedicine. Preferably, abstracts on data analysis tools should also briefly describe a case study where the tool was used.

PROGRAM

The scientific program of the colloquium will consist of presentations of accepted scientific papers, an invited presentation, and demonstrations of data analysis tools and problem descriptions. Ample time will be allotted for informal discussion among the participants.

SUBMISSION OF PAPERS

IDAMAP invites submissions of either short papers (2 pages, up to 1500 words, leading to a short presentation at the meeting) or full papers (up to 6 pages/4500 words, leading to a long presentation at the meeting). Data analysis tools and description of problems should be submitted as abstracts (1 page, up to 750 words). Papers should be written in English. Authors should send an electronic submission in PDF format to both chairs Stephen Swift ([email protected]), Kirk T. Phillips ([email protected]); please use "IDAMAP SUBMISSION YOUR_NAME" as a subject, where YOUR_NAME is the surname of the first author.

The submissions should be received no later than August 1, 2010. Manuscripts should be formatted two columns to a page, on A4 paper size, and with a 10-point times font for the text. A PDF-document is available with detailed instructions. We have prepared a set of LaTeX macros and a Microsoft Word template. Alternatively to preferred PDF, submissions using Post Script or MS Word format are also welcome.

Submissions will be reviewed by at least two people of the program committee. Authors will be notified of acceptance/rejection by September 1, 2010. Accepted papers will appear in colloquium notes that will be distributed among registered participants.

JOURNAL PUBLICATION

Selected papers by contributors to IDAMAP 2010 will be invited to submit a revised and expanded version of their paper for publication in Schattauer's Methods of Information in Medicine journal. Publication is scheduled for late 2010/early 2011.

REGISTRATION

Details on payment and registration will be posted shortly on the AMIA and IDAMAP 2010 pages.