Title :
Semi-automatic classification of clinical diagnoses with hybrid approach
Author :
Héja, Gergely ; Surján, György
Author_Institution :
Dept. of Meas. & Inf. Syst., Budapest Univ. of Technol. & Econ., Hungary
Abstract :
The authors present a hybrid approach to assist the laborious work of coding of medical reports. The system consists of four components: an n-gram based module, a modified vector-space module, a neural module, and an XML representation of the ICD coding system. It supports the coding of clinical diagnoses to ICD.
Keywords :
classification; learning (artificial intelligence); medical information systems; perceptrons; statistics; ICD coding system; XML representation; clinical diagnoses; hybrid approach; modified vector-space module; n-gram based module; neural module; semi-automatic classification; Blood; Computer errors; Electronic mail; Environmental economics; Humans; Information systems; Medical diagnostic imaging; Postal services; Statistical analysis; XML;
Conference_Titel :
Computer-Based Medical Systems, 2002. (CBMS 2002). Proceedings of the 15th IEEE Symposium on
Print_ISBN :
0-7695-1614-9
DOI :
10.1109/CBMS.2002.1011403
