東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Use of text mining to predict patien...

Petrou, Christiana Savva.

FindBook

Google Book

Amazon

博客來

Use of text mining to predict patient compliance.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Use of text mining to predict patient compliance./
作者:	Petrou, Christiana Savva.
面頁冊數:	168 p.
附註:	Source: Dissertation Abstracts International, Volume: 69-03, Section: B, page: 1719.
Contained By:	Dissertation Abstracts International69-03B.
標題:	Health Sciences, Dentistry. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3308355
ISBN:	9780549549246

Use of text mining to predict patient compliance.
Petrou, Christiana Savva.

Use of text mining to predict patient compliance. - 168 p.

Source: Dissertation Abstracts International, Volume: 69-03, Section: B, page: 1719.

Thesis (Ph.D.)--University of Louisville, 2008.

The treatment needs, treatment schedules, clinic group, entry point, and socioeconomic status are all variables that affect patient compliance. This study can be extended to private dental practices for comparison purposes.

ISBN: 9780549549246Subjects--Topical Terms:

1019378
Health Sciences, Dentistry.

Use of text mining to predict patient compliance.
LDR:02414nam 2200289 a 45 001 963680
005 20110831
008 110831s2008 ||||||||||||||||| ||eng d
020 $a 9780549549246
035 $a (UMI)AAI3308355
035 $a AAI3308355
040 $a UMI $c UMI
100 1 $a Petrou, Christiana Savva. $3 1286742
245 1 0 $a Use of text mining to predict patient compliance.
300 $a 168 p.
500 $a Source: Dissertation Abstracts International, Volume: 69-03, Section: B, page: 1719.
502 $a Thesis (Ph.D.)--University of Louisville, 2008.
520 $a The treatment needs, treatment schedules, clinic group, entry point, and socioeconomic status are all variables that affect patient compliance. This study can be extended to private dental practices for comparison purposes.
520 $a The purpose of this study is to examine standards of care in the Dental School of the University of Louisville. The central theme is to consider issues of compliance on behalf of the patients and how to define it in an unbiased way. We will examine the relationship of visit intervals, treatment needs, and patient compliance.
520 $a With the use of SAS 9.1.3 software, data mining techniques such as clustering, kernel density, linear models and mixed models estimation will be used to define and analyze compliance. Statistical methods such as text mining were used to examine the severity of patient conditions. Confidence interval estimation and bootstrapping were explored to assist with the allocation of patients to compliance levels. Patients who were within the 95% confidence interval of the median for visit intervals at least 80% of the time were defined as fully compliant, with decreasing levels of compliance as the percentage decreases to 60%, 40%, 20% and 0%.
520 $a Approximately 82% of the patient population was classified as least compliant, and in the least compliant group, approximately 60% are in the two most severe condition categories with regards to their dental condition. The general trend indicates that patients with severe dental conditions tend not to be compliant, whereas patients that suffer from not so severe conditions tend to be more compliant.
590 $a School code: 0110.
650 4 $a Health Sciences, Dentistry. $3 1019378
650 4 $a Statistics. $3 517247
690 $a 0463
690 $a 0567
710 2 $a University of Louisville. $3 1017614
773 0 $t Dissertation Abstracts International $g 69-03B.
790 $a 0110
791 $a Ph.D.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3308355