A Unified Multilingual and Multimedia Data Mining Approach for Cancer Knowledge Discovery

The functions of automatically identify relationships between cancer diseases and external factors from medical records for supporting cancer diagnosis would be a valuable contribution in public health fields. Unfortunately, so far little attention has been paid on providing effective solutions to such a problem domain. In this work, we propose a framework to automating the extraction of relationships between cancer diseases and potential factors from clinical records and medical literature. We describe a platform framework integrating cancer microarray and developed data mining techniques of multimedia and multilingual, covering clustering of multimedia as well as multilingual classifiers to carry out the system development. In the implementation, we extracted the associated genes of cancers by clustering microarray data, and then exploited the resulting gene clusters to classify cancer related documents. The experimental results show that the platform is capable of extracting the potential patterns to enhancing more effective solutions for cancer diseases.