Presentation 2010-05-14
DPC coding using concept base specialized in medical field
Toshio UCHIYAMA, Kazuya OKAMOTO, Tadamasa TAKEMURA, Takayuki ADACHI, Naoto KUME, Tomohiro KURODA, Tadasu UCHIYAMA, Hiroyuki YOSHIHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The goal of our research is to achieve high classification accuracy for DPC(Diagnosis Procedure Combination)coding from diagnosis and treatment information using machine learning techniques. We use the approach of combining various classifiers, such as naive Bayes classifier and a classifier using a concept-base(a set of concept vectors for words). Therefore, we derive the concept-base specialized in medical field from discharge summaries and examine the capability of it through experiments of DPC coding. Discharge summaries are also used for inputs of classifiers. Experimental results of DPC coding using this concept-base show its usefulness and effectiveness of our approach. Our method of DPC coding achieves 76.0 percent accuracy in all 14 digits and 88.5 percent accuracy in first 6 digits.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) concept-base / document classification / combination of classifiers / DPC coding
Paper # IE2010-42,PRMU2010-30,MI2010-30
Date of Issue

Conference Information
Committee MI
Conference Date 2010/5/6(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Medical Imaging (MI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) DPC coding using concept base specialized in medical field
Sub Title (in English)
Keyword(1) concept-base
Keyword(2) document classification
Keyword(3) combination of classifiers
Keyword(4) DPC coding
1st Author's Name Toshio UCHIYAMA
1st Author's Affiliation NTT Cyber Solutions Laboratories, NTT CORPORATION()
2nd Author's Name Kazuya OKAMOTO
2nd Author's Affiliation Department of Medical Informatics, Kyoto University Hospital
3rd Author's Name Tadamasa TAKEMURA
3rd Author's Affiliation Department of Medical Informatics, Kyoto University Hospital
4th Author's Name Takayuki ADACHI
4th Author's Affiliation NTT Cyber Solutions Laboratories, NTT CORPORATION
5th Author's Name Naoto KUME
5th Author's Affiliation Department of Medical Informatics, Kyoto University Hospital
6th Author's Name Tomohiro KURODA
6th Author's Affiliation Department of Medical Informatics, Kyoto University Hospital
7th Author's Name Tadasu UCHIYAMA
7th Author's Affiliation NTT Cyber Solutions Laboratories, NTT CORPORATION
8th Author's Name Hiroyuki YOSHIHARA
8th Author's Affiliation Department of Medical Informatics, Kyoto University Hospital
Date 2010-05-14
Paper # IE2010-42,PRMU2010-30,MI2010-30
Volume (vol) vol.110
Number (no) 28
Page pp.pp.-
#Pages 6
Date of Issue