Mining adverse drug reactions in social media with named entity recognition and semantic methods

Xiaoyi Chen; Myrtille Deldossi; Rim Aboukhamis; Carole Faviez; Badisse Dahamna; Pierre Karapetiantz; Armelle Guenegou-Arnoux; Yannick Girardeau; Sylvie Guillemin-Lanne; Agnès Lillo-Le-Louët; Nathalie Texier; Anita Burgun; Sandrine Katsahian

doi:10.3233/978-1-61499-830-3-322

Mining adverse drug reactions in social media with named entity recognition and semantic methods

Xiaoyi Chen
, Myrtille Deldossi
, Rim Aboukhamis
, Carole Faviez
, Badisse Dahamna
, Pierre Karapetiantz
, Armelle Guenegou-Arnoux
, Yannick Girardeau
, Sylvie Guillemin-Lanne
, Agnès Lillo-Le-Louët
, Nathalie Texier
, Anita Burgun
, Sandrine Katsahian

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

8 Scopus citations

Abstract

Suspected adverse drug reactions (ADR) reported by patients through social media can be a complementary source to current pharmacovigilance systems. However, the performance of text mining tools applied to social media text data to discover ADRs needs to be evaluated. In this paper, we introduce the approach developed to mine ADR from French social media. A protocol of evaluation is highlighted, which includes a detailed sample size determination and evaluation corpus constitution. Our text mining approach provided very encouraging preliminary results with F-measures of 0.94 and 0.81 for recognition of drugs and symptoms respectively, and with F-measure of 0.70 for ADR detection. Therefore, this approach is promising for downstream pharmacovigilance analysis.

Original language	English (US)
Title of host publication	MEDINFO 2017
Subtitle of host publication	Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics
Editors	Adi V. Gundlapalli, Jaulent Marie-Christine, Zhao Dongsheng
Publisher	IOS Press BV
Pages	322-326
Number of pages	5
ISBN (Electronic)	9781614998297
DOIs	https://doi.org/10.3233/978-1-61499-830-3-322
State	Published - 2017
Externally published	Yes
Event	16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017 - Hangzhou, China Duration: Aug 21 2017 → Aug 25 2017

Publication series

Name	Studies in Health Technology and Informatics
Volume	245
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Other

Other	16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017
Country/Territory	China
City	Hangzhou
Period	8/21/17 → 8/25/17

Bibliographical note

Publisher Copyright:
© 2017 International Medical Informatics Association (IMIA) and IOS Press.

Keywords

Data mining
Pharmacovigilance
Social media

Publisher link

10.3233/978-1-61499-830-3-322

Find It

Find It at U of M Libraries

Cite this

Chen, X., Deldossi, M., Aboukhamis, R., Faviez, C., Dahamna, B., Karapetiantz, P., Guenegou-Arnoux, A., Girardeau, Y., Guillemin-Lanne, S., Lillo-Le-Louët, A., Texier, N., Burgun, A., & Katsahian, S. (2017). Mining adverse drug reactions in social media with named entity recognition and semantic methods. In A. V. Gundlapalli, J. Marie-Christine, & Z. Dongsheng (Eds.), MEDINFO 2017: Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics (pp. 322-326). (Studies in Health Technology and Informatics; Vol. 245). IOS Press BV. https://doi.org/10.3233/978-1-61499-830-3-322

Mining adverse drug reactions in social media with named entity recognition and semantic methods. / Chen, Xiaoyi; Deldossi, Myrtille; Aboukhamis, Rim et al.
MEDINFO 2017: Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics. ed. / Adi V. Gundlapalli; Jaulent Marie-Christine; Zhao Dongsheng. IOS Press BV, 2017. p. 322-326 (Studies in Health Technology and Informatics; Vol. 245).

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

Chen, X, Deldossi, M, Aboukhamis, R, Faviez, C, Dahamna, B, Karapetiantz, P, Guenegou-Arnoux, A, Girardeau, Y, Guillemin-Lanne, S, Lillo-Le-Louët, A, Texier, N, Burgun, A & Katsahian, S 2017, Mining adverse drug reactions in social media with named entity recognition and semantic methods. in AV Gundlapalli, J Marie-Christine & Z Dongsheng (eds), MEDINFO 2017: Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics. Studies in Health Technology and Informatics, vol. 245, IOS Press BV, pp. 322-326, 16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017, Hangzhou, China, 8/21/17. https://doi.org/10.3233/978-1-61499-830-3-322

Chen X, Deldossi M, Aboukhamis R, Faviez C, Dahamna B, Karapetiantz P et al. Mining adverse drug reactions in social media with named entity recognition and semantic methods. In Gundlapalli AV, Marie-Christine J, Dongsheng Z, editors, MEDINFO 2017: Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics. IOS Press BV. 2017. p. 322-326. (Studies in Health Technology and Informatics). doi: 10.3233/978-1-61499-830-3-322

Chen, Xiaoyi ; Deldossi, Myrtille ; Aboukhamis, Rim et al. / Mining adverse drug reactions in social media with named entity recognition and semantic methods. MEDINFO 2017: Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics. editor / Adi V. Gundlapalli ; Jaulent Marie-Christine ; Zhao Dongsheng. IOS Press BV, 2017. pp. 322-326 (Studies in Health Technology and Informatics).

@inproceedings{a57d73600f804c45abe64e2ddd7f1785,

title = "Mining adverse drug reactions in social media with named entity recognition and semantic methods",

abstract = "Suspected adverse drug reactions (ADR) reported by patients through social media can be a complementary source to current pharmacovigilance systems. However, the performance of text mining tools applied to social media text data to discover ADRs needs to be evaluated. In this paper, we introduce the approach developed to mine ADR from French social media. A protocol of evaluation is highlighted, which includes a detailed sample size determination and evaluation corpus constitution. Our text mining approach provided very encouraging preliminary results with F-measures of 0.94 and 0.81 for recognition of drugs and symptoms respectively, and with F-measure of 0.70 for ADR detection. Therefore, this approach is promising for downstream pharmacovigilance analysis.",

keywords = "Data mining, Pharmacovigilance, Social media",

author = "Xiaoyi Chen and Myrtille Deldossi and Rim Aboukhamis and Carole Faviez and Badisse Dahamna and Pierre Karapetiantz and Armelle Guenegou-Arnoux and Yannick Girardeau and Sylvie Guillemin-Lanne and Agn{\`e}s Lillo-Le-Lou{\"e}t and Nathalie Texier and Anita Burgun and Sandrine Katsahian",

note = "Publisher Copyright: {\textcopyright} 2017 International Medical Informatics Association (IMIA) and IOS Press.; 16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017 ; Conference date: 21-08-2017 Through 25-08-2017",

year = "2017",

doi = "10.3233/978-1-61499-830-3-322",

language = "English (US)",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press BV",

pages = "322--326",

editor = "Gundlapalli, \{Adi V.\} and Jaulent Marie-Christine and Zhao Dongsheng",

booktitle = "MEDINFO 2017",

address = "Netherlands",

}

TY - GEN

T1 - Mining adverse drug reactions in social media with named entity recognition and semantic methods

AU - Chen, Xiaoyi

AU - Deldossi, Myrtille

AU - Aboukhamis, Rim

AU - Faviez, Carole

AU - Dahamna, Badisse

AU - Karapetiantz, Pierre

AU - Guenegou-Arnoux, Armelle

AU - Girardeau, Yannick

AU - Guillemin-Lanne, Sylvie

AU - Lillo-Le-Louët, Agnès

AU - Texier, Nathalie

AU - Burgun, Anita

AU - Katsahian, Sandrine

PY - 2017

Y1 - 2017

N2 - Suspected adverse drug reactions (ADR) reported by patients through social media can be a complementary source to current pharmacovigilance systems. However, the performance of text mining tools applied to social media text data to discover ADRs needs to be evaluated. In this paper, we introduce the approach developed to mine ADR from French social media. A protocol of evaluation is highlighted, which includes a detailed sample size determination and evaluation corpus constitution. Our text mining approach provided very encouraging preliminary results with F-measures of 0.94 and 0.81 for recognition of drugs and symptoms respectively, and with F-measure of 0.70 for ADR detection. Therefore, this approach is promising for downstream pharmacovigilance analysis.

AB - Suspected adverse drug reactions (ADR) reported by patients through social media can be a complementary source to current pharmacovigilance systems. However, the performance of text mining tools applied to social media text data to discover ADRs needs to be evaluated. In this paper, we introduce the approach developed to mine ADR from French social media. A protocol of evaluation is highlighted, which includes a detailed sample size determination and evaluation corpus constitution. Our text mining approach provided very encouraging preliminary results with F-measures of 0.94 and 0.81 for recognition of drugs and symptoms respectively, and with F-measure of 0.70 for ADR detection. Therefore, this approach is promising for downstream pharmacovigilance analysis.

KW - Data mining

KW - Pharmacovigilance

KW - Social media

UR - https://www.scopus.com/pages/publications/85040526550

UR - https://www.scopus.com/pages/publications/85040526550#tab=citedBy

U2 - 10.3233/978-1-61499-830-3-322

DO - 10.3233/978-1-61499-830-3-322

M3 - Conference contribution

C2 - 29295108

AN - SCOPUS:85040526550

T3 - Studies in Health Technology and Informatics

SP - 322

EP - 326

BT - MEDINFO 2017

A2 - Gundlapalli, Adi V.

A2 - Marie-Christine, Jaulent

A2 - Dongsheng, Zhao

PB - IOS Press BV

T2 - 16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017

Y2 - 21 August 2017 through 25 August 2017

ER -

Mining adverse drug reactions in social media with named entity recognition and semantic methods

Abstract

Publication series

Other

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this