Advanced clustering technique for medical data using semantic information

Kwangcheol Shin; Sang Yong Han; Alexander Gelbukh

doi:10.1007/978-3-540-24694-7_33

Advanced clustering technique for medical data using semantic information

Kwangcheol Shin, Sang Yong Han, Alexander Gelbukh

Centro de Investigación en Computación (CIC)

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

MEDLINE is a representative collection of medical documents supplied with original full-text natural-language abstracts as well as with representative keywords (called MeSH-terms) manually selected by the expert annotators from a pre-defined ontology and structured according to their relation to the document. We show how the structured manually assigned semantic descriptions can be combined with the original full-text abstracts to improve quality of clustering the documents into a small number of clusters. As a baseline, we compare our results with clustering using only abstracts or only MeSH-terms. Our experiments show 36% to 47% higher cluster coherence, as well as more refined keywords for the produced clusters.

Original language	English
Pages (from-to)	322-331
Number of pages	10
Journal	Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume	2972
DOIs	https://doi.org/10.1007/978-3-540-24694-7_33
State	Published - 2004
Event	Third Mexican International Conferenceon Artificial Intelligence - Mexico City, Mexico Duration: 26 Apr 2004 → 30 Apr 2004

Access to Document

10.1007/978-3-540-24694-7_33

Cite this

@article{58402baefd7c4eae8cf2d75cb00e7064,

title = "Advanced clustering technique for medical data using semantic information",

abstract = "MEDLINE is a representative collection of medical documents supplied with original full-text natural-language abstracts as well as with representative keywords (called MeSH-terms) manually selected by the expert annotators from a pre-defined ontology and structured according to their relation to the document. We show how the structured manually assigned semantic descriptions can be combined with the original full-text abstracts to improve quality of clustering the documents into a small number of clusters. As a baseline, we compare our results with clustering using only abstracts or only MeSH-terms. Our experiments show 36% to 47% higher cluster coherence, as well as more refined keywords for the produced clusters.",

author = "Kwangcheol Shin and Han, {Sang Yong} and Alexander Gelbukh",

year = "2004",

doi = "10.1007/978-3-540-24694-7_33",

language = "Ingl{\'e}s",

volume = "2972",

pages = "322--331",

journal = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

issn = "0302-9743",

publisher = "Springer Verlag",

note = "Third Mexican International Conferenceon Artificial Intelligence ; Conference date: 26-04-2004 Through 30-04-2004",

}

TY - JOUR

T1 - Advanced clustering technique for medical data using semantic information

AU - Shin, Kwangcheol

AU - Han, Sang Yong

AU - Gelbukh, Alexander

PY - 2004

Y1 - 2004

N2 - MEDLINE is a representative collection of medical documents supplied with original full-text natural-language abstracts as well as with representative keywords (called MeSH-terms) manually selected by the expert annotators from a pre-defined ontology and structured according to their relation to the document. We show how the structured manually assigned semantic descriptions can be combined with the original full-text abstracts to improve quality of clustering the documents into a small number of clusters. As a baseline, we compare our results with clustering using only abstracts or only MeSH-terms. Our experiments show 36% to 47% higher cluster coherence, as well as more refined keywords for the produced clusters.

AB - MEDLINE is a representative collection of medical documents supplied with original full-text natural-language abstracts as well as with representative keywords (called MeSH-terms) manually selected by the expert annotators from a pre-defined ontology and structured according to their relation to the document. We show how the structured manually assigned semantic descriptions can be combined with the original full-text abstracts to improve quality of clustering the documents into a small number of clusters. As a baseline, we compare our results with clustering using only abstracts or only MeSH-terms. Our experiments show 36% to 47% higher cluster coherence, as well as more refined keywords for the produced clusters.

UR - http://www.scopus.com/inward/record.url?scp=9444235094&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-24694-7_33

DO - 10.1007/978-3-540-24694-7_33

M3 - Artículo de la conferencia

AN - SCOPUS:9444235094

SN - 0302-9743

VL - 2972

SP - 322

EP - 331

JO - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

JF - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

T2 - Third Mexican International Conferenceon Artificial Intelligence

Y2 - 26 April 2004 through 30 April 2004

ER -

Advanced clustering technique for medical data using semantic information

Abstract

Access to Document

Other files and links

Fingerprint

Cite this