Empirical evaluation of three machine learning method for automatic classification of neoplastic diagnoses

Diagnoses are a valuable source of information for evaluating a health system. However, they are not used extensively by information systems because diagnoses are normally written in natural language. This work empirically evaluates three machine learning methods to automatically assign codes from t...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jara,José Luis, Chacón,Max, Zelaya,Gonzalo
Lenguaje:English
Publicado: Universidad de Tarapacá. 2011
Materias:
Acceso en línea:http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-33052011000300006
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:scielo:S0718-33052011000300006
record_format dspace
spelling oai:scielo:S0718-330520110003000062012-03-14Empirical evaluation of three machine learning method for automatic classification of neoplastic diagnosesJara,José LuisChacón,MaxZelaya,Gonzalo Clinical coding controlled vocabulary international classification of diseases machine learning natural language processing Diagnoses are a valuable source of information for evaluating a health system. However, they are not used extensively by information systems because diagnoses are normally written in natural language. This work empirically evaluates three machine learning methods to automatically assign codes from the International Classification of Diseases (10th Revision) to 3,335 distinct diagnoses of neoplasms obtained from UMLS®. This evaluation is conducted on three different types of preprocessing. The results are encouraging: a well-known rule induction method and maximum entropy models achieve 90% accuracy in a balanced cross-validation experiment.info:eu-repo/semantics/openAccessUniversidad de Tarapacá.Ingeniare. Revista chilena de ingeniería v.19 n.3 20112011-12-01text/htmlhttp://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-33052011000300006en10.4067/S0718-33052011000300006
institution Scielo Chile
collection Scielo Chile
language English
topic Clinical coding
controlled vocabulary
international classification of diseases
machine learning
natural language processing
spellingShingle Clinical coding
controlled vocabulary
international classification of diseases
machine learning
natural language processing
Jara,José Luis
Chacón,Max
Zelaya,Gonzalo
Empirical evaluation of three machine learning method for automatic classification of neoplastic diagnoses
description Diagnoses are a valuable source of information for evaluating a health system. However, they are not used extensively by information systems because diagnoses are normally written in natural language. This work empirically evaluates three machine learning methods to automatically assign codes from the International Classification of Diseases (10th Revision) to 3,335 distinct diagnoses of neoplasms obtained from UMLS®. This evaluation is conducted on three different types of preprocessing. The results are encouraging: a well-known rule induction method and maximum entropy models achieve 90% accuracy in a balanced cross-validation experiment.
author Jara,José Luis
Chacón,Max
Zelaya,Gonzalo
author_facet Jara,José Luis
Chacón,Max
Zelaya,Gonzalo
author_sort Jara,José Luis
title Empirical evaluation of three machine learning method for automatic classification of neoplastic diagnoses
title_short Empirical evaluation of three machine learning method for automatic classification of neoplastic diagnoses
title_full Empirical evaluation of three machine learning method for automatic classification of neoplastic diagnoses
title_fullStr Empirical evaluation of three machine learning method for automatic classification of neoplastic diagnoses
title_full_unstemmed Empirical evaluation of three machine learning method for automatic classification of neoplastic diagnoses
title_sort empirical evaluation of three machine learning method for automatic classification of neoplastic diagnoses
publisher Universidad de Tarapacá.
publishDate 2011
url http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-33052011000300006
work_keys_str_mv AT jarajoseluis empiricalevaluationofthreemachinelearningmethodforautomaticclassificationofneoplasticdiagnoses
AT chaconmax empiricalevaluationofthreemachinelearningmethodforautomaticclassificationofneoplasticdiagnoses
AT zelayagonzalo empiricalevaluationofthreemachinelearningmethodforautomaticclassificationofneoplasticdiagnoses
_version_ 1714203393240596480