Author/Editor		Babič, A
Title		Case studies in machine learning for medical knowledge extraction
Type		članek
Source		In: Machine learning and akademiska forskings projekt. SAIS'94 wokshop; 1994 Jun 6-7, Ronneby. Arrangoer: Nova CastAB-Soft center,
Publication year		1994
Volume		str. 1-21
Language		eng
Abstract		This paper explores and discusses several features of machine learning procedures, as used for knowledge extraction from medical data. In particular, two inductive learning systems, as well as Kohonen feature map, were applied to obtain knowledge, both of semantic and classification nature, enabling to differentiate among patients, observations and disease groups, what in turn was aimed to support clinical decisions. The study was done in two clinical sets of data with well defined patients groups. All medical variables included were prospectively chosen according to prior medical knowledge. Procedures used were analysed and compared for their theoretical and applicative performances, and in some cases they were assessed medical approprietness.
Descriptors		DECISION TREES DATA INTERPRETATION, STATISTICAL LEARNING ARTIFICIAL INTELLIGENCE ALGORITHMS DECISION MAKING, COMPUTER-ASSISTED