東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Misspecification issues in risk adju...

Li, Yue.

Linked to FindBook

Google Book

Amazon

博客來

Misspecification issues in risk adjustment and constructing outcome-based quality indicators.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Misspecification issues in risk adjustment and constructing outcome-based quality indicators./
Author:	Li, Yue.
Description:	153 p.
Notes:	Source: Dissertation Abstracts International, Volume: 66-11, Section: B, page: 5884.
Contained By:	Dissertation Abstracts International66-11B.
Subject:	Health Sciences, Health Care Management. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3193659
ISBN:	9780542436758

Misspecification issues in risk adjustment and constructing outcome-based quality indicators.
Li, Yue.

Misspecification issues in risk adjustment and constructing outcome-based quality indicators. - 153 p.

Source: Dissertation Abstracts International, Volume: 66-11, Section: B, page: 5884.

Thesis (Ph.D.)--University of Rochester, 2005.

Background. Using health outcome measures for quality assessment is widespread. Quality of care is comparable between health providers after adjusting for their differences in patient mix. However, existing risk-adjustment methods do not fully account for the interaction and correlation between quality and patient risks in determining patient outcomes. This project proposes to examine this deficiency and its implications for better risk-adjustment methods.

ISBN: 9780542436758Subjects--Topical Terms:

1017922
Health Sciences, Health Care Management.

Misspecification issues in risk adjustment and constructing outcome-based quality indicators.
LDR:03515nmm 2200337 4500 001 1825240
005 20061206115500.5
008 130610s2005 eng d
020 $a 9780542436758
035 $a (UnM)AAI3193659
035 $a AAI3193659
040 $a UnM $c UnM
100 1 $a Li, Yue. $3 1900255
245 1 0 $a Misspecification issues in risk adjustment and constructing outcome-based quality indicators.
300 $a 153 p.
500 $a Source: Dissertation Abstracts International, Volume: 66-11, Section: B, page: 5884.
500 $a Supervisor: Andrew Dick.
502 $a Thesis (Ph.D.)--University of Rochester, 2005.
520 $a Background. Using health outcome measures for quality assessment is widespread. Quality of care is comparable between health providers after adjusting for their differences in patient mix. However, existing risk-adjustment methods do not fully account for the interaction and correlation between quality and patient risks in determining patient outcomes. This project proposes to examine this deficiency and its implications for better risk-adjustment methods.
520 $a Theory. We developed a theoretical framework of the 'health production process' (HPP) in which quality care, patient risks and other factors together determine the level of health outcome in varied functional forms. We further pointed out that current risk-adjustment methods based on classical regressions (e.g., logistic regression) and observed-to-expected outcomes comparisons suffer misspecification problems.
520 $a This study aimed to test two main hypotheses: (1) misspecified risk-adjustment introduces significant error in outcome-based quality measurement; and (2) the misspecification error interacts with errors from other sources in risk adjustment.
520 $a Methods. To quantify the effect of misspecification errors, we first performed a case study on the New York State cardiac surgery reporting system (CSRS). Risk-adjusted mortality rate was estimated and compared by different specifications based on patients undergoing isolated coronary artery bypass graft surgeries in 2002. We then conducted Monte Carlo simulations to further explore how the misspecification error varied for different HPPs (e.g., additive versus multiplicative), and for various sample sizes and levels of completeness of risk information.
520 $a Results. Misspecified risk-adjustment generates errors in outcome comparisons both independently and in a way that is modified by exogenous sources of uncertainty. Proper data collection, use of multiplicative risk-adjustment model as appropriate, and constructing consistent quality indicator with the model help get around this issue.
520 $a Implications. The effectiveness of outcome measures relies on the accuracy of the quality information they convey. The misspecification issue is generic to risk adjustment and, yet, has been ignored by previous work. Appreciation and correction of the inherently flawed method will advance the state of the art of quality assessment. The potential of better quality measurement will improve the efficacy and effectiveness of quality report cards in terms of evaluating quality and directing quality improvement efforts.
590 $a School code: 0188.
650 4 $a Health Sciences, Health Care Management. $3 1017922
650 4 $a Health Sciences, Public Health. $3 1017659
690 $a 0769
690 $a 0573
710 2 0 $a University of Rochester. $3 515736
773 0 $t Dissertation Abstracts International $g 66-11B.
790 1 0 $a Dick, Andrew, $e advisor
790 $a 0188
791 $a Ph.D.
792 $a 2005
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3193659