Combining string and phonetic similarity matching to identify misspelt names of drugs in medical records written in Portuguese

Hegler Tissot; Richard Dobson

doi:10.1186/s13326-019-0216-2

Combining string and phonetic similarity matching to identify misspelt names of drugs in medical records written in Portuguese

Hegler Tissot^*, Richard Dobson

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

8 Citations (Scopus)

Abstract

Background: There is an increasing amount of unstructured medical data that can be analysed for different purposes. However, information extraction from free text data may be particularly inefficient in the presence of spelling errors. Existing approaches use string similarity methods to search for valid words within a text, coupled with a supporting dictionary. However, they are not rich enough to encode both typing and phonetic misspellings. Results: Experimental results showed a joint string and language-dependent phonetic similarity is more accurate than traditional string distance metrics when identifying misspelt names of drugs in a set of medical records written in Portuguese. Conclusion: We present a hybrid approach to efficiently perform similarity match that overcomes the loss of information inherit from using either exact match search or string based similarity search methods.

Original language	English
Article number	17
Journal	Journal of biomedical semantics
Volume	10
DOIs	https://doi.org/10.1186/s13326-019-0216-2
Publication status	Published - 12 Nov 2019

Keywords

Misspelt names of drugs
Phonetic similarity
Similarity search

Access to Document

10.1186/s13326-019-0216-2

Cite this

@article{3b53f21292414d949a0a1fe26df670fc,

title = "Combining string and phonetic similarity matching to identify misspelt names of drugs in medical records written in Portuguese",

abstract = "Background: There is an increasing amount of unstructured medical data that can be analysed for different purposes. However, information extraction from free text data may be particularly inefficient in the presence of spelling errors. Existing approaches use string similarity methods to search for valid words within a text, coupled with a supporting dictionary. However, they are not rich enough to encode both typing and phonetic misspellings. Results: Experimental results showed a joint string and language-dependent phonetic similarity is more accurate than traditional string distance metrics when identifying misspelt names of drugs in a set of medical records written in Portuguese. Conclusion: We present a hybrid approach to efficiently perform similarity match that overcomes the loss of information inherit from using either exact match search or string based similarity search methods.",

keywords = "Misspelt names of drugs, Phonetic similarity, Similarity search",

author = "Hegler Tissot and Richard Dobson",

year = "2019",

month = nov,

day = "12",

doi = "10.1186/s13326-019-0216-2",

language = "English",

volume = "10",

journal = "Journal of biomedical semantics",

}

TY - JOUR

T1 - Combining string and phonetic similarity matching to identify misspelt names of drugs in medical records written in Portuguese

AU - Tissot, Hegler

AU - Dobson, Richard

PY - 2019/11/12

Y1 - 2019/11/12

N2 - Background: There is an increasing amount of unstructured medical data that can be analysed for different purposes. However, information extraction from free text data may be particularly inefficient in the presence of spelling errors. Existing approaches use string similarity methods to search for valid words within a text, coupled with a supporting dictionary. However, they are not rich enough to encode both typing and phonetic misspellings. Results: Experimental results showed a joint string and language-dependent phonetic similarity is more accurate than traditional string distance metrics when identifying misspelt names of drugs in a set of medical records written in Portuguese. Conclusion: We present a hybrid approach to efficiently perform similarity match that overcomes the loss of information inherit from using either exact match search or string based similarity search methods.

AB - Background: There is an increasing amount of unstructured medical data that can be analysed for different purposes. However, information extraction from free text data may be particularly inefficient in the presence of spelling errors. Existing approaches use string similarity methods to search for valid words within a text, coupled with a supporting dictionary. However, they are not rich enough to encode both typing and phonetic misspellings. Results: Experimental results showed a joint string and language-dependent phonetic similarity is more accurate than traditional string distance metrics when identifying misspelt names of drugs in a set of medical records written in Portuguese. Conclusion: We present a hybrid approach to efficiently perform similarity match that overcomes the loss of information inherit from using either exact match search or string based similarity search methods.

KW - Misspelt names of drugs

KW - Phonetic similarity

KW - Similarity search

UR - http://www.scopus.com/inward/record.url?scp=85074837199&partnerID=8YFLogxK

U2 - 10.1186/s13326-019-0216-2

DO - 10.1186/s13326-019-0216-2

M3 - Article

C2 - 31711534

AN - SCOPUS:85074837199

VL - 10

JO - Journal of biomedical semantics

JF - Journal of biomedical semantics

M1 - 17

ER -

Combining string and phonetic similarity matching to identify misspelt names of drugs in medical records written in Portuguese

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this