An information retrieval approach for text mining of medical records based on graph descriptor

Alexander Dudko, Tatiana Endrjukaite, Yasushi Kiyoki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper describes a new method of data retrieval from free text documents in medical domain. Proposed approach creates the document summary and highlights most important keywords in the text. To achieve this result we process the document natural language text and build a descriptor as an internal representation of the document. This descriptor is a graph with concepts, relations between them, and concept points as a metric of relevance. By means of points in the descriptor the approach performs ambiguity resolution, selects most relevant concepts to display in the summary, and votes for keywords highlighting in the text. Besides the direct representation of identified information in the summary, this work proposes a way to provide extended summary by using additional knowledge about relations between medications, procedures, diseases and anatomy. The described approach helps to speed up analysis and decision making processes by means of providing aggregated summary for a document and highlighting most meaningful parts of the document's text. Experiment results demonstrate that automatic summary generation and keywords highlighting can be successfully performed by the proposed approach to achieve meaningful and highly relevant results.

Original languageEnglish
Title of host publicationInformation Modelling and Knowledge Bases XXX
EditorsTatiana Endrjukaite, Hannu Jaakkola, Alexander Dudko, Yasushi Kiyoki, Bernhard Thalheim, Naofumi Yoshida
PublisherIOS Press
Pages334-352
Number of pages19
ISBN (Electronic)9781614999324
DOIs
Publication statusPublished - 2019 Jan 1

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume312
ISSN (Print)0922-6389

Fingerprint

Information retrieval
Decision making
Experiments

Keywords

  • ambiguity resolution
  • graph descriptor
  • information retrieval
  • summary generation
  • text mining

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Dudko, A., Endrjukaite, T., & Kiyoki, Y. (2019). An information retrieval approach for text mining of medical records based on graph descriptor. In T. Endrjukaite, H. Jaakkola, A. Dudko, Y. Kiyoki, B. Thalheim, & N. Yoshida (Eds.), Information Modelling and Knowledge Bases XXX (pp. 334-352). (Frontiers in Artificial Intelligence and Applications; Vol. 312). IOS Press. https://doi.org/10.3233/978-1-61499-933-1-334

An information retrieval approach for text mining of medical records based on graph descriptor. / Dudko, Alexander; Endrjukaite, Tatiana; Kiyoki, Yasushi.

Information Modelling and Knowledge Bases XXX. ed. / Tatiana Endrjukaite; Hannu Jaakkola; Alexander Dudko; Yasushi Kiyoki; Bernhard Thalheim; Naofumi Yoshida. IOS Press, 2019. p. 334-352 (Frontiers in Artificial Intelligence and Applications; Vol. 312).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dudko, A, Endrjukaite, T & Kiyoki, Y 2019, An information retrieval approach for text mining of medical records based on graph descriptor. in T Endrjukaite, H Jaakkola, A Dudko, Y Kiyoki, B Thalheim & N Yoshida (eds), Information Modelling and Knowledge Bases XXX. Frontiers in Artificial Intelligence and Applications, vol. 312, IOS Press, pp. 334-352. https://doi.org/10.3233/978-1-61499-933-1-334
Dudko A, Endrjukaite T, Kiyoki Y. An information retrieval approach for text mining of medical records based on graph descriptor. In Endrjukaite T, Jaakkola H, Dudko A, Kiyoki Y, Thalheim B, Yoshida N, editors, Information Modelling and Knowledge Bases XXX. IOS Press. 2019. p. 334-352. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-933-1-334
Dudko, Alexander ; Endrjukaite, Tatiana ; Kiyoki, Yasushi. / An information retrieval approach for text mining of medical records based on graph descriptor. Information Modelling and Knowledge Bases XXX. editor / Tatiana Endrjukaite ; Hannu Jaakkola ; Alexander Dudko ; Yasushi Kiyoki ; Bernhard Thalheim ; Naofumi Yoshida. IOS Press, 2019. pp. 334-352 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{89e102684fa745f49650bd1bc0b2083c,
title = "An information retrieval approach for text mining of medical records based on graph descriptor",
abstract = "This paper describes a new method of data retrieval from free text documents in medical domain. Proposed approach creates the document summary and highlights most important keywords in the text. To achieve this result we process the document natural language text and build a descriptor as an internal representation of the document. This descriptor is a graph with concepts, relations between them, and concept points as a metric of relevance. By means of points in the descriptor the approach performs ambiguity resolution, selects most relevant concepts to display in the summary, and votes for keywords highlighting in the text. Besides the direct representation of identified information in the summary, this work proposes a way to provide extended summary by using additional knowledge about relations between medications, procedures, diseases and anatomy. The described approach helps to speed up analysis and decision making processes by means of providing aggregated summary for a document and highlighting most meaningful parts of the document's text. Experiment results demonstrate that automatic summary generation and keywords highlighting can be successfully performed by the proposed approach to achieve meaningful and highly relevant results.",
keywords = "ambiguity resolution, graph descriptor, information retrieval, summary generation, text mining",
author = "Alexander Dudko and Tatiana Endrjukaite and Yasushi Kiyoki",
year = "2019",
month = "1",
day = "1",
doi = "10.3233/978-1-61499-933-1-334",
language = "English",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
pages = "334--352",
editor = "Tatiana Endrjukaite and Hannu Jaakkola and Alexander Dudko and Yasushi Kiyoki and Bernhard Thalheim and Naofumi Yoshida",
booktitle = "Information Modelling and Knowledge Bases XXX",

}

TY - GEN

T1 - An information retrieval approach for text mining of medical records based on graph descriptor

AU - Dudko, Alexander

AU - Endrjukaite, Tatiana

AU - Kiyoki, Yasushi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This paper describes a new method of data retrieval from free text documents in medical domain. Proposed approach creates the document summary and highlights most important keywords in the text. To achieve this result we process the document natural language text and build a descriptor as an internal representation of the document. This descriptor is a graph with concepts, relations between them, and concept points as a metric of relevance. By means of points in the descriptor the approach performs ambiguity resolution, selects most relevant concepts to display in the summary, and votes for keywords highlighting in the text. Besides the direct representation of identified information in the summary, this work proposes a way to provide extended summary by using additional knowledge about relations between medications, procedures, diseases and anatomy. The described approach helps to speed up analysis and decision making processes by means of providing aggregated summary for a document and highlighting most meaningful parts of the document's text. Experiment results demonstrate that automatic summary generation and keywords highlighting can be successfully performed by the proposed approach to achieve meaningful and highly relevant results.

AB - This paper describes a new method of data retrieval from free text documents in medical domain. Proposed approach creates the document summary and highlights most important keywords in the text. To achieve this result we process the document natural language text and build a descriptor as an internal representation of the document. This descriptor is a graph with concepts, relations between them, and concept points as a metric of relevance. By means of points in the descriptor the approach performs ambiguity resolution, selects most relevant concepts to display in the summary, and votes for keywords highlighting in the text. Besides the direct representation of identified information in the summary, this work proposes a way to provide extended summary by using additional knowledge about relations between medications, procedures, diseases and anatomy. The described approach helps to speed up analysis and decision making processes by means of providing aggregated summary for a document and highlighting most meaningful parts of the document's text. Experiment results demonstrate that automatic summary generation and keywords highlighting can be successfully performed by the proposed approach to achieve meaningful and highly relevant results.

KW - ambiguity resolution

KW - graph descriptor

KW - information retrieval

KW - summary generation

KW - text mining

UR - http://www.scopus.com/inward/record.url?scp=85059572767&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059572767&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-933-1-334

DO - 10.3233/978-1-61499-933-1-334

M3 - Conference contribution

T3 - Frontiers in Artificial Intelligence and Applications

SP - 334

EP - 352

BT - Information Modelling and Knowledge Bases XXX

A2 - Endrjukaite, Tatiana

A2 - Jaakkola, Hannu

A2 - Dudko, Alexander

A2 - Kiyoki, Yasushi

A2 - Thalheim, Bernhard

A2 - Yoshida, Naofumi

PB - IOS Press

ER -