Extracting Expert Knowledge from Medical Texts

In this paper we argue that researchers in Intelligent Data Analysis (IDA) in Medicine and Pharmacology should conside r textual databases as an additional source of knowledge. We desc rib three areas where medical knowledge extraction from textua l databases can be fruitful: finding new applications for existing drugs, evolution of medical knowledge in time, and drug risk assess ment. We evaluate two textual knowledge extraction methods, wher e an IDA approach shows to be robust and efficient compared to a com mon computational linguistic one.