Extraction of determinants of postoperative length of stay from operation records

研究成果: 著書/レポートタイプへの貢献会議での発言

抄録

Secondary use of clinical text data are gaining much attention in improving the quality and the efficiency of medical treatment. Although there is some case studies of medical-examination text data, there are not many examples fed back to the medical-examination spot. The present paper analyses the operation records of total hip arthroplasty. We extracted feature words that characterize the two peaks which appeared in distribution of postoperative hospital days using SVM (support vector machine) and FS (feature selection). The models gained by optimal FS attained 60% accuracy as prediction performance. We applied logistic regression analysis to estimate postoperative length of stay from the extracted feature words. Most words were not statistically significant except two words.

元の言語英語
ホスト出版物のタイトルProceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014
出版者IEEE Computer Society
ページ822-827
ページ数6
ISBN(印刷物)9781479945658
DOI
出版物ステータス出版済み - 1 1 2014
イベント2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014 - Ottawa, ON, カナダ
継続期間: 5 8 20145 9 2014

出版物シリーズ

名前Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014

その他

その他2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014
カナダ
Ottawa, ON
期間5/8/145/9/14

Fingerprint

Feature extraction
Arthroplasty
Regression analysis
Support vector machines
Logistics

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

これを引用

Yamashita, T., Wakata, Y., Nakashima, N., Hirokawa, S., Hamai, S., Nakashima, Y., & Iwamoto, Y. (2014). Extraction of determinants of postoperative length of stay from operation records. : Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014 (pp. 822-827). [6845748] (Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014). IEEE Computer Society. https://doi.org/10.1109/IWECA.2014.6845748

Extraction of determinants of postoperative length of stay from operation records. / Yamashita, Takanori; Wakata, Yoshifumi; Nakashima, Naoki; Hirokawa, Sachio; Hamai, Satoshi; Nakashima, Yasuharu; Iwamoto, Yukihide.

Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014. IEEE Computer Society, 2014. p. 822-827 6845748 (Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014).

研究成果: 著書/レポートタイプへの貢献会議での発言

Yamashita, T, Wakata, Y, Nakashima, N, Hirokawa, S, Hamai, S, Nakashima, Y & Iwamoto, Y 2014, Extraction of determinants of postoperative length of stay from operation records. : Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014., 6845748, Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014, IEEE Computer Society, pp. 822-827, 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014, Ottawa, ON, カナダ, 5/8/14. https://doi.org/10.1109/IWECA.2014.6845748
Yamashita T, Wakata Y, Nakashima N, Hirokawa S, Hamai S, Nakashima Y その他. Extraction of determinants of postoperative length of stay from operation records. : Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014. IEEE Computer Society. 2014. p. 822-827. 6845748. (Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014). https://doi.org/10.1109/IWECA.2014.6845748
Yamashita, Takanori ; Wakata, Yoshifumi ; Nakashima, Naoki ; Hirokawa, Sachio ; Hamai, Satoshi ; Nakashima, Yasuharu ; Iwamoto, Yukihide. / Extraction of determinants of postoperative length of stay from operation records. Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014. IEEE Computer Society, 2014. pp. 822-827 (Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014).
@inproceedings{acbe9386e6424ed0941b761bbe3d4075,
title = "Extraction of determinants of postoperative length of stay from operation records",
abstract = "Secondary use of clinical text data are gaining much attention in improving the quality and the efficiency of medical treatment. Although there is some case studies of medical-examination text data, there are not many examples fed back to the medical-examination spot. The present paper analyses the operation records of total hip arthroplasty. We extracted feature words that characterize the two peaks which appeared in distribution of postoperative hospital days using SVM (support vector machine) and FS (feature selection). The models gained by optimal FS attained 60{\%} accuracy as prediction performance. We applied logistic regression analysis to estimate postoperative length of stay from the extracted feature words. Most words were not statistically significant except two words.",
author = "Takanori Yamashita and Yoshifumi Wakata and Naoki Nakashima and Sachio Hirokawa and Satoshi Hamai and Yasuharu Nakashima and Yukihide Iwamoto",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/IWECA.2014.6845748",
language = "English",
isbn = "9781479945658",
series = "Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014",
publisher = "IEEE Computer Society",
pages = "822--827",
booktitle = "Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014",
address = "United States",

}

TY - GEN

T1 - Extraction of determinants of postoperative length of stay from operation records

AU - Yamashita, Takanori

AU - Wakata, Yoshifumi

AU - Nakashima, Naoki

AU - Hirokawa, Sachio

AU - Hamai, Satoshi

AU - Nakashima, Yasuharu

AU - Iwamoto, Yukihide

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Secondary use of clinical text data are gaining much attention in improving the quality and the efficiency of medical treatment. Although there is some case studies of medical-examination text data, there are not many examples fed back to the medical-examination spot. The present paper analyses the operation records of total hip arthroplasty. We extracted feature words that characterize the two peaks which appeared in distribution of postoperative hospital days using SVM (support vector machine) and FS (feature selection). The models gained by optimal FS attained 60% accuracy as prediction performance. We applied logistic regression analysis to estimate postoperative length of stay from the extracted feature words. Most words were not statistically significant except two words.

AB - Secondary use of clinical text data are gaining much attention in improving the quality and the efficiency of medical treatment. Although there is some case studies of medical-examination text data, there are not many examples fed back to the medical-examination spot. The present paper analyses the operation records of total hip arthroplasty. We extracted feature words that characterize the two peaks which appeared in distribution of postoperative hospital days using SVM (support vector machine) and FS (feature selection). The models gained by optimal FS attained 60% accuracy as prediction performance. We applied logistic regression analysis to estimate postoperative length of stay from the extracted feature words. Most words were not statistically significant except two words.

UR - http://www.scopus.com/inward/record.url?scp=84904553421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904553421&partnerID=8YFLogxK

U2 - 10.1109/IWECA.2014.6845748

DO - 10.1109/IWECA.2014.6845748

M3 - Conference contribution

AN - SCOPUS:84904553421

SN - 9781479945658

T3 - Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014

SP - 822

EP - 827

BT - Proceedings - 2014 IEEE Workshop on Electronics, Computer and Applications, IWECA 2014

PB - IEEE Computer Society

ER -