Workshop on

Advances and Issues in Biomedical Data Mining (AIBDM’09)

in conjunction with Pacific-Asia Knowledge Discovery and Data Mining (PAKDD09)

27 April 2009 · Bangkok · Thailand

Papers due date extended to 19Jan09 (Mon) 5Jan09 (Mon)





Recent advances in measurement techniques and computer hardware have enabled the collection of huge amount of biomedical data. From patient records to digitized image archives to DNA microarrays, the complexities of these data made analyses difficult and time-consuming. A common characteristic among biomedical datasets are their high-dimensionality and small sample sizes. For example, a DNA microarray dataset might only have a hundred samples, but each sample can have 50,000 or more attributes. The so-called "curse of dimensionality" problem poses a great challenge to the data mining community because most existing algorithms only work well on data in large quantity, with a reasonable number of attributes or dimensions. At the same time, the mining of associations among attribute sets only works if they co-occur. Existing association rule mining algorithms are unable to detect the interactions among sets of attributes that lead to some desired effects.



The aims of this workshop are to explore difficulties and current attempts to resolve these two outstanding problems in mining biomedical data. Special attention will be devoted to dimensionality reduction and discovery of interacting items.


Recent years have witnessed considerable advances in both dimensionality reduction (DR) and interaction mining (IM) algorithms. In particular, the advantages of nonlinear DR methods over classical linear approaches in emerging domains like biomedical data have been demonstrated. Similarly, IM approaches in validating protein-protein interactions have been reported.


This workshop, held in conjunction with The 13th Pacific-Asia Conference on Knowledge Discovery and Data Mining, will contribute to the conference by assembling active researchers in biomedical data mining to share their experiences on addressing aspects of the above problems, and to propose and prepare useful reference datasets for algorithmic comparison.



Potential participants of this workshop are encouraged to submit technical papers on (but not limited to) the following topics:

         Dimensionality reduction

         Sampling and feature selection

         Interaction Mining

         Interestingness measurement in biomedical data mining

         Data mining with small biomedical dataset

         Knowledge discovery in Biomedical data

         Semantics in Biomedicine

         Health Data Integration

         Biomedical Data Privacy and Security

         Health geomatics

         Biomedical informatics

         Biomedical Imaging Techniques

         Adaptive Biomedical Data Mining

         New Machine Learning Techniques for Biomedical Data



Authors are strongly encouraged to use Springer’s manuscript submission guidelines (available at


Papers should be no longer than 10 pages inclusive of all references and figures. All papers must be submitted electronically in PDF format only. Please ensure that any special fonts used are included in the submitted documents. The workshop papers will be published as LNAI Post Proceedings. The submitted papers must not be published or under consideration to be published elsewhere. Each paper will undergo a double-blind review process by the Program Committee.


Negotiation is undergoing with journal publishers so that outstanding papers will be invited for the submission to a Special Issues in Biomedical Data Mining. Please pay attention to our website for further development on this matter.


- Submission Deadline: 22Dec08 (Mon)   19Jan (Mon) ** extended **

- Author Notification: 23Jan09 (Fri)

- Camera-Ready: 9Feb09 (Mon)

- Workshop Date: 27Apr09 (Mon)


Submission: please click here



Quality papers submitted to tracks will be selected for fast-track reviews and possible publications in the following supporting international journal:

         International Journal of Data Mining, Modelling and Management (IJDMMM) -


Organizing Committee

Junbin Gao, Charles Sturt University, Australia,

Paul Kwan, University of New England, Australia,

Josiah Poon, University of Sydney, Australia,

Simon Poon, University of Sydney, Australia,


Program Committee

Rafael Calvo, University of Sydney, Australia

Peter Christen, Australian National University, Australia

Dao-qing Dai, Sun Yat-Sen(Zhongshan) University, PRC

Kin Fun Li, University of Victoria, Canada

Steve Gunn, University of Southampton, UK

David Hansen, CSIRO, Australia

Irena Koprinska, University of Sydney, Australia

Ong Kok Leong, Deakin University, Australia

Wenyuan Li, University of Southern California, USA

Christine O'Keefe, CSIRO, Australia

Georg Peters, University of Applied Sciences Muenchen, Germany

Daming Shi, Nanyang Technological University, Singapore

Chunhua Weng, Columbia University, USA

Jun Zhang, Huazhong University of Science and Technology, PRC