Comparison of ICD 10 and AIS with the Development of a Method for Automated Conversion

Most of the current scores and outcome prediction calculations in traumatology are based on the Abbreviated Injury Scale (AIS). However, this is not routinely used for documentation and coding of injuries in many countries, including Germany. Instead of the AIS, the International Classification of D...

Full description

Saved in:
Bibliographic Details
Published in:Zeitschrift fur Orthopadie und Unfallchirurgie Vol. 153; no. 6; p. 607
Main Authors: Hartensuer, R, Nikolov, B, Franz, D, Weimann, A, Raschke, M, Juhra, C
Format: Journal Article
Language:German
Published: Germany 01-12-2015
Subjects:
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most of the current scores and outcome prediction calculations in traumatology are based on the Abbreviated Injury Scale (AIS). However, this is not routinely used for documentation and coding of injuries in many countries, including Germany. Instead of the AIS, the International Classification of Diseases (ICD) is used. While the ICD functions as the basis for automated calculating of the diagnosis-related groups (DRG), no possibility of simple conversion of the 10th version of the ICD into AIS is available so far. The aim of this work is to develop and apply a methodology for simple conversion from ICD 10 to current AIS. The developed mapping procedure was based on a 1 : n relationship between trauma codes of ICD-10-GM and the codes of the AIS2005. Calculated ISS from the conversion codes were then compared with the actual ISS coding available from the clinical trauma documentation. It can be shown that, despite the considerable differences in the structure and systematic of both classification systems, an automated translation is technically possible. The preliminary result of the mapping suggests, however, that despite the technical feasibility of a reliable conversion and comparability of ICD 10 and AIS in the required quality is still questionable. An automated conversion is still possible and quality would possibly improve by inclusion of additional information.
ISSN:1864-6743
DOI:10.1055/s-0035-1546217