A New Semantic Similarity Scheme for more Accurate Identification in Medical Data

Colin Wilcox; Soufiene Djahel; Vasilios Giagos; Kristopher Welsh; Nicholas Costen

doi:10.1109/ISC257844.2023.10293563

A New Semantic Similarity Scheme for more Accurate Identification in Medical Data

Colin Wilcox, Soufiene Djahel, Vasilios Giagos, Kristopher Welsh, Nicholas Costen

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

2 Citations (Scopus)

Abstract

This paper aims to design a new measure of similarity between personal textual information retrieved from historic medical records to correct errors introduced due to poor encoding and data omission. The key motivation underlying our proposed layered algorithm, named Semantic Similarity scheme (SSIM), is to create a consistent, complete and accurate data set that may then be used as a basis for the identification and authentication of individuals in a medical context. Such consistent data may provide a basis for use as part of an access control system without compromising medical ethics or security. The obtained evaluation results, using four sample data sets from the UK, USA, Canada and Australia, highlight promising benefits compared to other similarity measures including Jaccard index, Sorensen-Dice and Cosine Similarity - especially when nicknames, abbreviations and synonyms are used to determine similarity.

Original language	English
Title of host publication	Proceedings of 2023 IEEE International Smart Cities Conference
Subtitle of host publication	(ISC2 2023)
Publisher	IEEE
Number of pages	7
ISBN (Electronic)	9798350397758, 9798350397741
ISBN (Print)	9798350397765
DOIs	https://doi.org/10.1109/ISC257844.2023.10293563
Publication status	Published - 31 Oct 2023
Event	9th IEEE International Smart Cities Conference - University Politehnica of Bucharest, Bucharest, Romania Duration: 24 Sep 2023 → 27 Sep 2023 Conference number: 9 https://attend.ieee.org/isc2-2023/

Publication series

Name	Proceedings of the IEEE International Smart Cities Conference
Publisher	IEEE
ISSN (Print)	2687-8852
ISSN (Electronic)	2687-8860

Conference

Conference	9th IEEE International Smart Cities Conference
Abbreviated title	ISC2 2023
Country/Territory	Romania
City	Bucharest
Period	24/09/23 → 27/09/23
Internet address	https://attend.ieee.org/isc2-2023/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ISC257844.2023.10293563Licence: Unspecified

AAMAccepted author manuscript, 221 KBLicence: Unspecified

Cite this

@inproceedings{21aac61f069d4b9b9a0bf5976a626328,

title = "A New Semantic Similarity Scheme for more Accurate Identification in Medical Data",

abstract = "This paper aims to design a new measure of similarity between personal textual information retrieved from historic medical records to correct errors introduced due to poor encoding and data omission. The key motivation underlying our proposed layered algorithm, named Semantic Similarity scheme (SSIM), is to create a consistent, complete and accurate data set that may then be used as a basis for the identification and authentication of individuals in a medical context. Such consistent data may provide a basis for use as part of an access control system without compromising medical ethics or security. The obtained evaluation results, using four sample data sets from the UK, USA, Canada and Australia, highlight promising benefits compared to other similarity measures including Jaccard index, Sorensen-Dice and Cosine Similarity - especially when nicknames, abbreviations and synonyms are used to determine similarity.",

keywords = "Text Similarity, Semantic Similarity, Medical Data, Medical Records",

author = "Colin Wilcox and Soufiene Djahel and Vasilios Giagos and Kristopher Welsh and Nicholas Costen",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 9th IEEE International Smart Cities Conference, ISC2 2023 ; Conference date: 24-09-2023 Through 27-09-2023",

year = "2023",

month = oct,

day = "31",

doi = "10.1109/ISC257844.2023.10293563",

language = "English",

isbn = "9798350397765",

series = "Proceedings of the IEEE International Smart Cities Conference",

publisher = "IEEE",

booktitle = "Proceedings of 2023 IEEE International Smart Cities Conference",

address = "United States",

url = "https://attend.ieee.org/isc2-2023/",

}

Wilcox, C, Djahel, S, Giagos, V, Welsh, K & Costen, N 2023, A New Semantic Similarity Scheme for more Accurate Identification in Medical Data. in Proceedings of 2023 IEEE International Smart Cities Conference: (ISC2 2023)., 10293563, Proceedings of the IEEE International Smart Cities Conference, IEEE, 9th IEEE International Smart Cities Conference, Bucharest, Romania, 24/09/23. https://doi.org/10.1109/ISC257844.2023.10293563

A New Semantic Similarity Scheme for more Accurate Identification in Medical Data. / Wilcox, Colin; Djahel, Soufiene; Giagos, Vasilios et al.

Proceedings of 2023 IEEE International Smart Cities Conference: (ISC2 2023). IEEE, 2023. 10293563 (Proceedings of the IEEE International Smart Cities Conference).

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

TY - GEN

T1 - A New Semantic Similarity Scheme for more Accurate Identification in Medical Data

AU - Wilcox, Colin

AU - Djahel, Soufiene

AU - Giagos, Vasilios

AU - Welsh, Kristopher

AU - Costen, Nicholas

N1 - Conference code: 9

PY - 2023/10/31

Y1 - 2023/10/31

N2 - This paper aims to design a new measure of similarity between personal textual information retrieved from historic medical records to correct errors introduced due to poor encoding and data omission. The key motivation underlying our proposed layered algorithm, named Semantic Similarity scheme (SSIM), is to create a consistent, complete and accurate data set that may then be used as a basis for the identification and authentication of individuals in a medical context. Such consistent data may provide a basis for use as part of an access control system without compromising medical ethics or security. The obtained evaluation results, using four sample data sets from the UK, USA, Canada and Australia, highlight promising benefits compared to other similarity measures including Jaccard index, Sorensen-Dice and Cosine Similarity - especially when nicknames, abbreviations and synonyms are used to determine similarity.

AB - This paper aims to design a new measure of similarity between personal textual information retrieved from historic medical records to correct errors introduced due to poor encoding and data omission. The key motivation underlying our proposed layered algorithm, named Semantic Similarity scheme (SSIM), is to create a consistent, complete and accurate data set that may then be used as a basis for the identification and authentication of individuals in a medical context. Such consistent data may provide a basis for use as part of an access control system without compromising medical ethics or security. The obtained evaluation results, using four sample data sets from the UK, USA, Canada and Australia, highlight promising benefits compared to other similarity measures including Jaccard index, Sorensen-Dice and Cosine Similarity - especially when nicknames, abbreviations and synonyms are used to determine similarity.

KW - Text Similarity

KW - Semantic Similarity

KW - Medical Data

KW - Medical Records

UR - http://www.scopus.com/inward/record.url?scp=85178353726&partnerID=8YFLogxK

U2 - 10.1109/ISC257844.2023.10293563

DO - 10.1109/ISC257844.2023.10293563

M3 - Conference contribution

SN - 9798350397765

T3 - Proceedings of the IEEE International Smart Cities Conference

BT - Proceedings of 2023 IEEE International Smart Cities Conference

PB - IEEE

T2 - 9th IEEE International Smart Cities Conference

Y2 - 24 September 2023 through 27 September 2023

ER -

A New Semantic Similarity Scheme for more Accurate Identification in Medical Data

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Cite this