Title
A frame-based representation of ICD-10.
Abstract
Physicians are required to code information concerning a patient's stay in order to measure the medical activity in hospitals. They use the International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10). Coding is usually performed manually and computerized tools may be useful in speeding up and facilitating the tedious task of coding patient information. The aim of this work is to build a surface semantic model of ICD-10 in order to ameliorate a coding help system.This work was focused on chapter XI of the ICD-10, Diseases of the Digestive System. Each term from both analytical and alphabetical indexes about this chapter were submitted to a morphological analysis in order to extract the medical concepts within. After a statistical analysis of these concepts and the way they connect themselves, a semantic model based on a "semantic frame" approach was built.Although this model could represent a reasonable amount of medical knowledge within chapter XI of the ICD-10 in a quite satisfactory way, it shows lack of efficiency for some other chapters.Difficulties have to be overcome when modelling a classification meant for manual utilisation, and a lot of work still has to be done to obtain an effective coding help system using the ICD-10.
Year
Venue
Field
2003
MIE
Data mining,Frame based,Natural language processing,Artificial intelligence,Medicine,ICD-10
DocType
Volume
ISSN
Conference
95
0926-9630
Citations 
PageRank 
References 
0
0.34
0
Authors
5
Name
Order
Citations
PageRank
Paul Fabry143.97
Robert H. Baud233360.59
Patrick Ruch311916.27
Pierre Le Beux4457.14
C Lovis58519.90