Construction of Dominant Factor Presumption Model for Postoperative Hospital Days from Operation Records

Author

Yamashita, Takayoshi ; Wakata, Yoshifumi ; Nakashima, Norihiro ; Hamai, Satoshi ; Nakashima, Yuta ; Iwamoto, Yukihide ; Flanagan, Brendan ; Hirokawa, Sachio

Author_Institution

Med. Inf. Center, Kyushu Univ. Hosp., Fukuoka, Japan

fYear

2014

fDate

Aug. 31 2014-Sept. 4 2014

Firstpage

19

Lastpage

24

Abstract

The secondary use of clinical text data to improve the quality and the efficiency of medical care is gaining much attention. However, there are few previous researches that have given feedback to clinical situations. The present paper analyzes the words that appear in operation records to predict the postoperative length of stay. SVM (support vector machine) and feature selection are applied to predict if a stay is longer than the standard length of 25 days. It was confirmed that with less than 20 feature words we can predict if a stay is longer or not with almost the optimal prediction performance.

Keywords

data mining; feature selection; health care; hospitals; medical information systems; support vector machines; text analysis; SVM; clinical text data; dominant factor presumption model; feature selection; feature word analysis; medical care efficiency improvement; medical care quality improvement; operation records; optimal prediction performance; postoperative hospital days; postoperative length-of-stay prediction; support vector machine; Informatics; CI(Critical Indicator); Critical Path; Feature Selection; SVM(support vector machine); hip replacement arthroplasty surgery;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Applied Informatics (IIAIAAI), 2014 IIAI 3rd International Conference on

Conference_Location

Kitakyushu

Print_ISBN

978-1-4799-4174-2

Type

conf

DOI

10.1109/IIAI-AAI.2014.16

Filename

6913260