Supervised text classification of medical triage reports

Kleverwal, J. (2015) Supervised text classification of medical triage reports.

[img]
Preview
PDF
796kB
Abstract:Topicus Zorg has developed a system to help triage officers at the emergency department perform a triage. This system uses keyword scanning for text classification; an entered description of medical symptoms is categorized in one or more presenting complaints. This way of classification has its limitations. Only keywords are recognized, which makes that some information is ignored. Also sometimes more than two presenting complaints are used as category for one text, although almost always one presenting complaint is sufficient. 10 characteristics of medical texts were found, only three of these characteristics were highly represented in the used data collection. These three characteristics are telegraphic style, shorthand text (e.g. abbreviations) and negation. Also some commonly used supervised text classification methods are reviewed; k Nearest Neighbors, Support Vector Machines and Naive Bayes. One text classification method is chosen (k Nearest Neighbors, kNN). Parameters focussing on query construction, number of nearest neighbors, scoring and ranking were defined. Some implementations of these parameters were chosen to be tested. The current triage system was then compared to the implementation of kNN and the parameters using an F-measure. A similar score is obtained for both systems, the triage system and the implementation of kNN using parameters.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science MSc (60300)
Link to this item:http://purl.utwente.nl/essays/66946
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page