Title: An interface for medical diagnosis support: from the viewpoint of chance discovery

Authors: Akinori Abe, Norihiro Hagita, Michiko Furutani, Yoshiyuki Furutani, Rumiko Matsuoka

Addresses: International Research and Educational Institute for Integrated Medical Science (IREIIMS), Tokyo Women's Medical University, 8-1 Kawada-cho, Shinjuku-ku, Tokyo 162-8666, Japan; ATR Knowledge Science Laboratories, 2-2-2, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan. ' International Research and Educational Institute for Integrated Medical Science (IREIIMS), Tokyo Women's Medical University, 8-1 Kawada-cho, Shinjuku-ku, Tokyo 162-8666, Japan; ATR Intelligent Robotics and Communication Laboratories, 2-2-2, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan. ' International Research and Educational Institute for Integrated Medical Science (IREIIMS), Tokyo Women's Medical University, 8-1 Kawada-cho, Shinjuku-ku, Tokyo 162-8666, Japan. ' International Research and Educational Institute for Integrated Medical Science (IREIIMS), Tokyo Women's Medical University, 8-1 Kawada-cho, Shinjuku-ku, Tokyo 162-8666, Japan. ' International Research and Educational Institute for Integrated Medical Science (IREIIMS), Tokyo Women's Medical University, 8-1 Kawada-cho, Shinjuku-ku, Tokyo 162-8666, Japan

Abstract: In this paper, we propose a web-based interactive interface to show medical data analysis results by C4.5, where the physicians can easily confirm or correct medical data and analysed results. It can estimate health levels of medical data where health levels are not labelled, which can be referred to for medical diagnosis support. It demonstrates the possibilities of the chance discovery process, which enables the discovery of hidden or rare but very important relationships (chances) in a medical diagnosis support. We discovered models which are important for determining health levels but cannot be extracted during a machine learning process.

Keywords: interactive interface; medical diagnosis support; data mining; chance discovery; web-based interface; medical data analysis; hidden relationships; rare relationships; health levels; healthcare.

DOI: 10.1504/IJAIP.2010.030540

International Journal of Advanced Intelligence Paradigms, 2010 Vol.2 No.2/3, pp.283 - 302

Published online: 21 Dec 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article