Classification and feature extraction for text-based drug incident report

Takanori Yamashita; Naoki Nakashima; Sachio Hirokawa

doi:10.1145/3194480.3194499

Classification and feature extraction for text-based drug incident report

Takanori Yamashita, Naoki Nakashima, Sachio Hirokawa

Medical Information Center

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

1 Citation (Scopus)

Abstract

Medical institutions have been constructed incident report system, then accumulating incident data. Incident data compose text-based data and some structured attributes. We considered based on the analysis result with clustering for drug incident report. Firstly, we generated a network of documents and words from the text-based data. Secondly, Louvain method was applied to the network and 11 clusters were generated. We confirmed the contents of each cluster from feature words extracted by TF-IDF. Then, we compare clusters of text-based data with structured attributes and grasp the trend of the incident. This proposed method showed the possibility of clinical support toward reduction incident from text-based data.

Original language	English
Title of host publication	Proceedings of 2018 6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018
Publisher	Association for Computing Machinery
Pages	145-149
Number of pages	5
ISBN (Electronic)	9781450363488
DOIs	https://doi.org/10.1145/3194480.3194499
Publication status	Published - Mar 12 2018
Event	6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018 - Chengdu, China Duration: Mar 12 2018 → Mar 14 2018

Publication series

Name	ACM International Conference Proceeding Series

Other

Other	6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018
Country	China
City	Chengdu
Period	3/12/18 → 3/14/18

All Science Journal Classification (ASJC) codes

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3194480.3194499

Fingerprint Dive into the research topics of 'Classification and feature extraction for text-based drug incident report'. Together they form a unique fingerprint.

Cite this

Yamashita, T., Nakashima, N., & Hirokawa, S. (2018). Classification and feature extraction for text-based drug incident report. In Proceedings of 2018 6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018 (pp. 145-149). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3194480.3194499

Classification and feature extraction for text-based drug incident report. / Yamashita, Takanori ; Nakashima, Naoki; Hirokawa, Sachio.

Proceedings of 2018 6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018. Association for Computing Machinery, 2018. p. 145-149 (ACM International Conference Proceeding Series).

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

Yamashita, T , Nakashima, N & Hirokawa, S 2018, Classification and feature extraction for text-based drug incident report. in Proceedings of 2018 6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 145-149, 6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018, Chengdu, China, 3/12/18. https://doi.org/10.1145/3194480.3194499

@inproceedings{1a8625aac1604d7cba386a12716d860b,

title = "Classification and feature extraction for text-based drug incident report",

abstract = "Medical institutions have been constructed incident report system, then accumulating incident data. Incident data compose text-based data and some structured attributes. We considered based on the analysis result with clustering for drug incident report. Firstly, we generated a network of documents and words from the text-based data. Secondly, Louvain method was applied to the network and 11 clusters were generated. We confirmed the contents of each cluster from feature words extracted by TF-IDF. Then, we compare clusters of text-based data with structured attributes and grasp the trend of the incident. This proposed method showed the possibility of clinical support toward reduction incident from text-based data.",

author = "Takanori Yamashita and Naoki Nakashima and Sachio Hirokawa",

note = "Funding Information: This research is partially supported by JSPS KAKENHI Grand Number 15H02778. Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018 ; Conference date: 12-03-2018 Through 14-03-2018",

year = "2018",

month = mar,

day = "12",

doi = "10.1145/3194480.3194499",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "145--149",

booktitle = "Proceedings of 2018 6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018",

}

TY - GEN

T1 - Classification and feature extraction for text-based drug incident report

AU - Yamashita, Takanori

AU - Nakashima, Naoki

AU - Hirokawa, Sachio

PY - 2018/3/12

Y1 - 2018/3/12

N2 - Medical institutions have been constructed incident report system, then accumulating incident data. Incident data compose text-based data and some structured attributes. We considered based on the analysis result with clustering for drug incident report. Firstly, we generated a network of documents and words from the text-based data. Secondly, Louvain method was applied to the network and 11 clusters were generated. We confirmed the contents of each cluster from feature words extracted by TF-IDF. Then, we compare clusters of text-based data with structured attributes and grasp the trend of the incident. This proposed method showed the possibility of clinical support toward reduction incident from text-based data.

AB - Medical institutions have been constructed incident report system, then accumulating incident data. Incident data compose text-based data and some structured attributes. We considered based on the analysis result with clustering for drug incident report. Firstly, we generated a network of documents and words from the text-based data. Secondly, Louvain method was applied to the network and 11 clusters were generated. We confirmed the contents of each cluster from feature words extracted by TF-IDF. Then, we compare clusters of text-based data with structured attributes and grasp the trend of the incident. This proposed method showed the possibility of clinical support toward reduction incident from text-based data.

UR - http://www.scopus.com/inward/record.url?scp=85047157293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047157293&partnerID=8YFLogxK

U2 - 10.1145/3194480.3194499

DO - 10.1145/3194480.3194499

M3 - Conference contribution

AN - SCOPUS:85047157293

T3 - ACM International Conference Proceeding Series

SP - 145

EP - 149

BT - Proceedings of 2018 6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018

PB - Association for Computing Machinery

T2 - 6th International Conference on Bioinformatics and Computational Biology, ICBCB 2018

Y2 - 12 March 2018 through 14 March 2018

ER -

Classification and feature extraction for text-based drug incident report

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this