Universiti Teknologi Malaysia Institutional Repository

Information extraction from handwritten medical record and assining ICD-10 codes

Salim, Naomie and Foudeh, Pouya (2010) Information extraction from handwritten medical record and assining ICD-10 codes. In: ICCS 10 - 8th International Conference on Conceptual Structures, 26-30 July 2010, Kuching,Sarawak.

Full text not available from this repository.

Abstract

Medical diagnoses for clinical patients are recorded by a physician at the time of admission and discharge from hospital as well as death. Nowadays this information is documented in patient file not only in form of ordinary reports but also in ICD-10 codes to reach more accurate interpretation and use them in statistical surveys. ICD code assignment is a tedious, laborious and highly expensive procedure. Many health care organizations pursue the goal of developing automated procedures. This paper is going to introduce a new method that have machine learned from files with ordinary diagnosis and ICD- 10 codes and then will be able to find ICD-10 codes for patients who are not assigned and double checking codes of the others as well. Results of this system will be in form of probabilistic data.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:diagnosis coding, medical records, ICD-10 codes, information extraction, probabilistic data
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System (Formerly known)
ID Code:24040
Deposited By: Liza Porijo
Deposited On:28 Sep 2012 05:36
Last Modified:28 Sep 2012 05:36

Repository Staff Only: item control page