Medical case-based retrieval of patient records using the radlex hierarchical lexicon

Assaf B. Spanier; Leo Joskowicz

doi:10.1007/978-3-319-24471-6_12

Medical case-based retrieval of patient records using the radlex hierarchical lexicon

Assaf B. Spanier^*
, Leo Joskowicz

^*Corresponding author for this work

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

We present a new method for the retrieval radiological cases from a database of clinical cases described by terms from the RadLex lexicon. The input is an database of cases and a query consisting of the patient volumetric scan, a user-defined region of interest in it, and a list of RadLex from the radiological report. The output is list of the most relevant cases from the database in decreasing order. Our method uses the RadLex terms and their hierarchical representation to define a similarity metric between terms based on their relative location in the hierarchy. For this purpose, we develop the Augmented RadLex Graph, a data structure that augments the RadLex hierarchy with links derived from the terms in the case reports, and a search algorithm that ranks case similarity based on the link distance between the terms in the graph. Our method was evaluated in the VISCERAL Retrieval Benchmark Challenge on 8 queries and a database of 1,813 cases. It ranked first in 6 out of the 8 cases tested.

Original language	English
Title of host publication	Multimodal Retrieval in the Medical Domain - 1st International Workshop, MRMD 2015, Revised Selected Papers
Editors	Henning Müller H., Oscar Alfonso Jimenez del Toro, Allan Hanbury, Georg Langs, Antonio Foncubierta Rodríguez
Publisher	Springer Verlag
Pages	129-138
Number of pages	10
ISBN (Print)	9783319244709
DOIs	https://doi.org/10.1007/978-3-319-24471-6_12
State	Published - 2015
Event	1st International Workshop on Multimodal Retrieval in the Medical Domain, MRMD 2015 held in connection with 37th European Conference on Information Retrieval, ECIR 2015 - Vienna, Austria Duration: 29 Mar 2015 → 29 Mar 2015

Publication series

Name	Lecture Notes in Computer Science
Volume	9059
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	1st International Workshop on Multimodal Retrieval in the Medical Domain, MRMD 2015 held in connection with 37th European Conference on Information Retrieval, ECIR 2015
Country/Territory	Austria
City	Vienna
Period	29/03/15 → 29/03/15

Bibliographical note

Publisher Copyright:
© Springer International Publishing Switzerland 2015.

Access to Document

10.1007/978-3-319-24471-6_12

Cite this

Spanier, A. B., & Joskowicz, L. (2015). Medical case-based retrieval of patient records using the radlex hierarchical lexicon. In H. Müller H., O. A. J. del Toro, A. Hanbury, G. Langs, & A. F. Rodríguez (Eds.), Multimodal Retrieval in the Medical Domain - 1st International Workshop, MRMD 2015, Revised Selected Papers (pp. 129-138). (Lecture Notes in Computer Science; Vol. 9059). Springer Verlag. https://doi.org/10.1007/978-3-319-24471-6_12

Spanier, Assaf B. ; Joskowicz, Leo. / Medical case-based retrieval of patient records using the radlex hierarchical lexicon. Multimodal Retrieval in the Medical Domain - 1st International Workshop, MRMD 2015, Revised Selected Papers. editor / Henning Müller H. ; Oscar Alfonso Jimenez del Toro ; Allan Hanbury ; Georg Langs ; Antonio Foncubierta Rodríguez. Springer Verlag, 2015. pp. 129-138 (Lecture Notes in Computer Science).

@inproceedings{2ac9ea69939247d59b56a6544b46b0c7,

title = "Medical case-based retrieval of patient records using the radlex hierarchical lexicon",

abstract = "We present a new method for the retrieval radiological cases from a database of clinical cases described by terms from the RadLex lexicon. The input is an database of cases and a query consisting of the patient volumetric scan, a user-defined region of interest in it, and a list of RadLex from the radiological report. The output is list of the most relevant cases from the database in decreasing order. Our method uses the RadLex terms and their hierarchical representation to define a similarity metric between terms based on their relative location in the hierarchy. For this purpose, we develop the Augmented RadLex Graph, a data structure that augments the RadLex hierarchy with links derived from the terms in the case reports, and a search algorithm that ranks case similarity based on the link distance between the terms in the graph. Our method was evaluated in the VISCERAL Retrieval Benchmark Challenge on 8 queries and a database of 1,813 cases. It ranked first in 6 out of the 8 cases tested.",

author = "Spanier, \{Assaf B.\} and Leo Joskowicz",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2015.; 1st International Workshop on Multimodal Retrieval in the Medical Domain, MRMD 2015 held in connection with 37th European Conference on Information Retrieval, ECIR 2015 ; Conference date: 29-03-2015 Through 29-03-2015",

year = "2015",

doi = "10.1007/978-3-319-24471-6\_12",

language = "אנגלית",

isbn = "9783319244709",

series = "Lecture Notes in Computer Science",

publisher = "Springer Verlag",

pages = "129--138",

editor = "\{M{\"u}ller H.\}, Henning and \{del Toro\}, \{Oscar Alfonso Jimenez\} and Allan Hanbury and Georg Langs and Rodr{\'i}guez, \{Antonio Foncubierta\}",

booktitle = "Multimodal Retrieval in the Medical Domain - 1st International Workshop, MRMD 2015, Revised Selected Papers",

address = "גרמניה",

}

Spanier, AB & Joskowicz, L 2015, Medical case-based retrieval of patient records using the radlex hierarchical lexicon. in H Müller H., OAJ del Toro, A Hanbury, G Langs & AF Rodríguez (eds), Multimodal Retrieval in the Medical Domain - 1st International Workshop, MRMD 2015, Revised Selected Papers. Lecture Notes in Computer Science, vol. 9059, Springer Verlag, pp. 129-138, 1st International Workshop on Multimodal Retrieval in the Medical Domain, MRMD 2015 held in connection with 37th European Conference on Information Retrieval, ECIR 2015, Vienna, Austria, 29/03/15. https://doi.org/10.1007/978-3-319-24471-6_12

Medical case-based retrieval of patient records using the radlex hierarchical lexicon. / Spanier, Assaf B.; Joskowicz, Leo.
Multimodal Retrieval in the Medical Domain - 1st International Workshop, MRMD 2015, Revised Selected Papers. ed. / Henning Müller H.; Oscar Alfonso Jimenez del Toro; Allan Hanbury; Georg Langs; Antonio Foncubierta Rodríguez. Springer Verlag, 2015. p. 129-138 (Lecture Notes in Computer Science; Vol. 9059).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Medical case-based retrieval of patient records using the radlex hierarchical lexicon

AU - Spanier, Assaf B.

AU - Joskowicz, Leo

N1 - Publisher Copyright: © Springer International Publishing Switzerland 2015.

PY - 2015

Y1 - 2015

N2 - We present a new method for the retrieval radiological cases from a database of clinical cases described by terms from the RadLex lexicon. The input is an database of cases and a query consisting of the patient volumetric scan, a user-defined region of interest in it, and a list of RadLex from the radiological report. The output is list of the most relevant cases from the database in decreasing order. Our method uses the RadLex terms and their hierarchical representation to define a similarity metric between terms based on their relative location in the hierarchy. For this purpose, we develop the Augmented RadLex Graph, a data structure that augments the RadLex hierarchy with links derived from the terms in the case reports, and a search algorithm that ranks case similarity based on the link distance between the terms in the graph. Our method was evaluated in the VISCERAL Retrieval Benchmark Challenge on 8 queries and a database of 1,813 cases. It ranked first in 6 out of the 8 cases tested.

AB - We present a new method for the retrieval radiological cases from a database of clinical cases described by terms from the RadLex lexicon. The input is an database of cases and a query consisting of the patient volumetric scan, a user-defined region of interest in it, and a list of RadLex from the radiological report. The output is list of the most relevant cases from the database in decreasing order. Our method uses the RadLex terms and their hierarchical representation to define a similarity metric between terms based on their relative location in the hierarchy. For this purpose, we develop the Augmented RadLex Graph, a data structure that augments the RadLex hierarchy with links derived from the terms in the case reports, and a search algorithm that ranks case similarity based on the link distance between the terms in the graph. Our method was evaluated in the VISCERAL Retrieval Benchmark Challenge on 8 queries and a database of 1,813 cases. It ranked first in 6 out of the 8 cases tested.

UR - https://www.scopus.com/pages/publications/84952761553

U2 - 10.1007/978-3-319-24471-6_12

DO - 10.1007/978-3-319-24471-6_12

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84952761553

SN - 9783319244709

T3 - Lecture Notes in Computer Science

SP - 129

EP - 138

BT - Multimodal Retrieval in the Medical Domain - 1st International Workshop, MRMD 2015, Revised Selected Papers

A2 - Müller H., Henning

A2 - del Toro, Oscar Alfonso Jimenez

A2 - Hanbury, Allan

A2 - Langs, Georg

A2 - Rodríguez, Antonio Foncubierta

PB - Springer Verlag

T2 - 1st International Workshop on Multimodal Retrieval in the Medical Domain, MRMD 2015 held in connection with 37th European Conference on Information Retrieval, ECIR 2015

Y2 - 29 March 2015 through 29 March 2015

ER -

Spanier AB, Joskowicz L. Medical case-based retrieval of patient records using the radlex hierarchical lexicon. In Müller H. H, del Toro OAJ, Hanbury A, Langs G, Rodríguez AF, editors, Multimodal Retrieval in the Medical Domain - 1st International Workshop, MRMD 2015, Revised Selected Papers. Springer Verlag. 2015. p. 129-138. (Lecture Notes in Computer Science). doi: 10.1007/978-3-319-24471-6_12

Medical case-based retrieval of patient records using the radlex hierarchical lexicon

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this