Authors:
Ghazar Chahbandarian
1
;
Nathalie Souf
1
;
Rémi Bastide
1
and
Jean-Christophe Steinbach
2
Affiliations:
1
University of Toulouse, France
;
2
Pays d’Autan Hospital, France
Keyword(s):
Electronic Medical Records, EMR, Context, Data Mining, Decision Tree, ICD, PMSI.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Business Analytics
;
Cloud Computing
;
Data Engineering
;
Data Mining
;
Databases and Information Systems Integration
;
Datamining
;
e-Health
;
Enterprise Information Systems
;
Health Information Systems
;
Information Systems Analysis and Specification
;
Knowledge Management
;
Ontologies and the Semantic Web
;
Platforms and Applications
;
Sensor Networks
;
Signal Processing
;
Society, e-Business and e-Government
;
Soft Computing
;
Web Information Systems and Technologies
Abstract:
In order to measure the medical activity, hospitals are required to manually encode information concerning a
patient’s stay using International Classification of Disease (ICD-10). This task is time consuming and requires
substantial training for the staff. We propose to help by speeding up and facilitating the tedious task of coding
patient information, specially while coding some secondary diagnostics that are not well described in the
medical resources such as discharge letter and medical records. Our approach consists of building a decision
tree out of big variety of inpatient stay information in particular, contextual information such as age, sex,
diagnostic count and other related information, next figure out missing secondary diagnostics. The results
are still preliminary, we identify some important information variables that can be interesting to verify while
coding certain secondary diagnostics.