Similarity index for sound-alikeness of drug names with pitch accents

Tomoyuki Nagata, Masaomi Kimura, Fumito Tsuchiya

研究成果: Conference contribution

3 引用 (Scopus)

抄録

Drug name similarity is one of major reasons of medical accidents. In order to prevent from the accidents, one of the best ways is to avoid approving drugs that has the names similar to that of existing drugs. It is well-known that there are two kinds of drug name similarity, look-alikeness and sound-alikeness. Nabeta et. al. proposed a look-alikeness similarity index,which excludes the sound-alikeness. Though, in Japan, oral prescription is basically prohibited, emergent situation can force a doctor to prescribe orally. In such a situation, medical accidents can occur. In this study, we proposed a sound-alikeness similarity index based on quantitative similarity of consonants. The consonant similarity was proposed based on The International Phonetic Alphabet (IPA). Overall drug name similarity is calculated based on Letter Sequence Kernel (LSK). The similarity calculation method takes account of the effect of plural pitch accents. We divided a drug name into some pieces at the position where a pitch accent changes, applied LSK to each of them, and combined them to obtain the value of the similarity index. The similarity index proposed in this study achieved relatively high correlation to the results of our experiment, r ≈ 0.8.

元の言語English
ホスト出版物のタイトルProcedia Computer Science
出版者Elsevier
ページ1519-1528
ページ数10
35
エディションC
DOI
出版物ステータスPublished - 2014
イベントInternational Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2014 - Gdynia, Poland
継続期間: 2014 9 152014 9 17

Other

OtherInternational Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2014
Poland
Gdynia
期間14/9/1514/9/17

Fingerprint

Accidents
Acoustic waves
Speech analysis
Experiments

ASJC Scopus subject areas

  • Computer Science(all)

これを引用

Nagata, T., Kimura, M., & Tsuchiya, F. (2014). Similarity index for sound-alikeness of drug names with pitch accents. : Procedia Computer Science (C 版, 巻 35, pp. 1519-1528). Elsevier. https://doi.org/10.1016/j.procs.2014.08.235

Similarity index for sound-alikeness of drug names with pitch accents. / Nagata, Tomoyuki; Kimura, Masaomi; Tsuchiya, Fumito.

Procedia Computer Science. 巻 35 C. 編 Elsevier, 2014. p. 1519-1528.

研究成果: Conference contribution

Nagata, T, Kimura, M & Tsuchiya, F 2014, Similarity index for sound-alikeness of drug names with pitch accents. : Procedia Computer Science. C Edn, 巻. 35, Elsevier, pp. 1519-1528, International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2014, Gdynia, Poland, 14/9/15. https://doi.org/10.1016/j.procs.2014.08.235
Nagata T, Kimura M, Tsuchiya F. Similarity index for sound-alikeness of drug names with pitch accents. : Procedia Computer Science. C 版 巻 35. Elsevier. 2014. p. 1519-1528 https://doi.org/10.1016/j.procs.2014.08.235
Nagata, Tomoyuki ; Kimura, Masaomi ; Tsuchiya, Fumito. / Similarity index for sound-alikeness of drug names with pitch accents. Procedia Computer Science. 巻 35 C. 版 Elsevier, 2014. pp. 1519-1528
@inproceedings{7377734424a84e09a7619626f87374ac,
title = "Similarity index for sound-alikeness of drug names with pitch accents",
abstract = "Drug name similarity is one of major reasons of medical accidents. In order to prevent from the accidents, one of the best ways is to avoid approving drugs that has the names similar to that of existing drugs. It is well-known that there are two kinds of drug name similarity, look-alikeness and sound-alikeness. Nabeta et. al. proposed a look-alikeness similarity index,which excludes the sound-alikeness. Though, in Japan, oral prescription is basically prohibited, emergent situation can force a doctor to prescribe orally. In such a situation, medical accidents can occur. In this study, we proposed a sound-alikeness similarity index based on quantitative similarity of consonants. The consonant similarity was proposed based on The International Phonetic Alphabet (IPA). Overall drug name similarity is calculated based on Letter Sequence Kernel (LSK). The similarity calculation method takes account of the effect of plural pitch accents. We divided a drug name into some pieces at the position where a pitch accent changes, applied LSK to each of them, and combined them to obtain the value of the similarity index. The similarity index proposed in this study achieved relatively high correlation to the results of our experiment, r ≈ 0.8.",
keywords = "Drug names, Medical Safety, Similarity Index",
author = "Tomoyuki Nagata and Masaomi Kimura and Fumito Tsuchiya",
year = "2014",
doi = "10.1016/j.procs.2014.08.235",
language = "English",
volume = "35",
pages = "1519--1528",
booktitle = "Procedia Computer Science",
publisher = "Elsevier",
edition = "C",

}

TY - GEN

T1 - Similarity index for sound-alikeness of drug names with pitch accents

AU - Nagata, Tomoyuki

AU - Kimura, Masaomi

AU - Tsuchiya, Fumito

PY - 2014

Y1 - 2014

N2 - Drug name similarity is one of major reasons of medical accidents. In order to prevent from the accidents, one of the best ways is to avoid approving drugs that has the names similar to that of existing drugs. It is well-known that there are two kinds of drug name similarity, look-alikeness and sound-alikeness. Nabeta et. al. proposed a look-alikeness similarity index,which excludes the sound-alikeness. Though, in Japan, oral prescription is basically prohibited, emergent situation can force a doctor to prescribe orally. In such a situation, medical accidents can occur. In this study, we proposed a sound-alikeness similarity index based on quantitative similarity of consonants. The consonant similarity was proposed based on The International Phonetic Alphabet (IPA). Overall drug name similarity is calculated based on Letter Sequence Kernel (LSK). The similarity calculation method takes account of the effect of plural pitch accents. We divided a drug name into some pieces at the position where a pitch accent changes, applied LSK to each of them, and combined them to obtain the value of the similarity index. The similarity index proposed in this study achieved relatively high correlation to the results of our experiment, r ≈ 0.8.

AB - Drug name similarity is one of major reasons of medical accidents. In order to prevent from the accidents, one of the best ways is to avoid approving drugs that has the names similar to that of existing drugs. It is well-known that there are two kinds of drug name similarity, look-alikeness and sound-alikeness. Nabeta et. al. proposed a look-alikeness similarity index,which excludes the sound-alikeness. Though, in Japan, oral prescription is basically prohibited, emergent situation can force a doctor to prescribe orally. In such a situation, medical accidents can occur. In this study, we proposed a sound-alikeness similarity index based on quantitative similarity of consonants. The consonant similarity was proposed based on The International Phonetic Alphabet (IPA). Overall drug name similarity is calculated based on Letter Sequence Kernel (LSK). The similarity calculation method takes account of the effect of plural pitch accents. We divided a drug name into some pieces at the position where a pitch accent changes, applied LSK to each of them, and combined them to obtain the value of the similarity index. The similarity index proposed in this study achieved relatively high correlation to the results of our experiment, r ≈ 0.8.

KW - Drug names

KW - Medical Safety

KW - Similarity Index

UR - http://www.scopus.com/inward/record.url?scp=84924155236&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924155236&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2014.08.235

DO - 10.1016/j.procs.2014.08.235

M3 - Conference contribution

AN - SCOPUS:84924155236

VL - 35

SP - 1519

EP - 1528

BT - Procedia Computer Science

PB - Elsevier

ER -