Using compund codes for automatic classification of clinical diagnoses

Serguei V. Pakhomov, James D. Buntrock, Christopher Chute

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Classification of diagnoses (a.k.a. coding) is the central part of current concept based medical IR systems. Some classification systems contain over 30, 000 distinct codes which makes classifying clinical documents a time consuming labor intensive and error prone process. This paper presents a simple methodology for cleaning up and reusing existing manually coded diagnostic statements mainly extracted from clinical notes to build predictive models using a sparse feature implementation of a Naïve Bayes classifier. One of the problems addressed is that diagnostic statements often contain several diagnoses and are assigned several codes resulting in a 'many-to-many' mapping problem. We investigate one possible way of solving this problem by introducing compound (multiple code) categories. We present experimental results of classifying >16,000 randomly selected diagnostic strings into 19 top level categories. A small improvement (3%) with using compound categories over simple categories indicates that using multiple code categories is a promising solution, although clearly in need of further research and refinement.

Original languageEnglish (US)
Title of host publicationStudies in Health Technology and Informatics
Pages411-415
Number of pages5
Volume107
DOIs
StatePublished - 2004
Externally publishedYes

Fingerprint

Cleaning
Classifiers
Personnel
Research

Keywords

  • Automatic classification
  • clinical diagnoses
  • concept indexing

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Pakhomov, S. V., Buntrock, J. D., & Chute, C. (2004). Using compund codes for automatic classification of clinical diagnoses. In Studies in Health Technology and Informatics (Vol. 107, pp. 411-415) https://doi.org/10.3233/978-1-60750-949-3-411

Using compund codes for automatic classification of clinical diagnoses. / Pakhomov, Serguei V.; Buntrock, James D.; Chute, Christopher.

Studies in Health Technology and Informatics. Vol. 107 2004. p. 411-415.

Research output: Chapter in Book/Report/Conference proceedingChapter

Pakhomov, SV, Buntrock, JD & Chute, C 2004, Using compund codes for automatic classification of clinical diagnoses. in Studies in Health Technology and Informatics. vol. 107, pp. 411-415. https://doi.org/10.3233/978-1-60750-949-3-411
Pakhomov SV, Buntrock JD, Chute C. Using compund codes for automatic classification of clinical diagnoses. In Studies in Health Technology and Informatics. Vol. 107. 2004. p. 411-415 https://doi.org/10.3233/978-1-60750-949-3-411
Pakhomov, Serguei V. ; Buntrock, James D. ; Chute, Christopher. / Using compund codes for automatic classification of clinical diagnoses. Studies in Health Technology and Informatics. Vol. 107 2004. pp. 411-415
@inbook{ef093c4b4d9a424e8c5f9a6f822de843,
title = "Using compund codes for automatic classification of clinical diagnoses",
abstract = "Classification of diagnoses (a.k.a. coding) is the central part of current concept based medical IR systems. Some classification systems contain over 30, 000 distinct codes which makes classifying clinical documents a time consuming labor intensive and error prone process. This paper presents a simple methodology for cleaning up and reusing existing manually coded diagnostic statements mainly extracted from clinical notes to build predictive models using a sparse feature implementation of a Na{\"i}ve Bayes classifier. One of the problems addressed is that diagnostic statements often contain several diagnoses and are assigned several codes resulting in a 'many-to-many' mapping problem. We investigate one possible way of solving this problem by introducing compound (multiple code) categories. We present experimental results of classifying >16,000 randomly selected diagnostic strings into 19 top level categories. A small improvement (3{\%}) with using compound categories over simple categories indicates that using multiple code categories is a promising solution, although clearly in need of further research and refinement.",
keywords = "Automatic classification, clinical diagnoses, concept indexing",
author = "Pakhomov, {Serguei V.} and Buntrock, {James D.} and Christopher Chute",
year = "2004",
doi = "10.3233/978-1-60750-949-3-411",
language = "English (US)",
volume = "107",
pages = "411--415",
booktitle = "Studies in Health Technology and Informatics",

}

TY - CHAP

T1 - Using compund codes for automatic classification of clinical diagnoses

AU - Pakhomov, Serguei V.

AU - Buntrock, James D.

AU - Chute, Christopher

PY - 2004

Y1 - 2004

N2 - Classification of diagnoses (a.k.a. coding) is the central part of current concept based medical IR systems. Some classification systems contain over 30, 000 distinct codes which makes classifying clinical documents a time consuming labor intensive and error prone process. This paper presents a simple methodology for cleaning up and reusing existing manually coded diagnostic statements mainly extracted from clinical notes to build predictive models using a sparse feature implementation of a Naïve Bayes classifier. One of the problems addressed is that diagnostic statements often contain several diagnoses and are assigned several codes resulting in a 'many-to-many' mapping problem. We investigate one possible way of solving this problem by introducing compound (multiple code) categories. We present experimental results of classifying >16,000 randomly selected diagnostic strings into 19 top level categories. A small improvement (3%) with using compound categories over simple categories indicates that using multiple code categories is a promising solution, although clearly in need of further research and refinement.

AB - Classification of diagnoses (a.k.a. coding) is the central part of current concept based medical IR systems. Some classification systems contain over 30, 000 distinct codes which makes classifying clinical documents a time consuming labor intensive and error prone process. This paper presents a simple methodology for cleaning up and reusing existing manually coded diagnostic statements mainly extracted from clinical notes to build predictive models using a sparse feature implementation of a Naïve Bayes classifier. One of the problems addressed is that diagnostic statements often contain several diagnoses and are assigned several codes resulting in a 'many-to-many' mapping problem. We investigate one possible way of solving this problem by introducing compound (multiple code) categories. We present experimental results of classifying >16,000 randomly selected diagnostic strings into 19 top level categories. A small improvement (3%) with using compound categories over simple categories indicates that using multiple code categories is a promising solution, although clearly in need of further research and refinement.

KW - Automatic classification

KW - clinical diagnoses

KW - concept indexing

UR - http://www.scopus.com/inward/record.url?scp=77955512211&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955512211&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-949-3-411

DO - 10.3233/978-1-60750-949-3-411

M3 - Chapter

VL - 107

SP - 411

EP - 415

BT - Studies in Health Technology and Informatics

ER -