2015
DOI: 10.1080/00224065.2015.11918141
|View full text |Cite
|
Sign up to set email alerts
|

The Monitoring and Improvement of Surgical-Outcome Quality

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
44
0

Year Published

2015
2015
2021
2021

Publication Types

Select...
8

Relationship

3
5

Authors

Journals

citations
Cited by 64 publications
(44 citation statements)
references
References 115 publications
0
44
0
Order By: Relevance
“…It is not reasonable for a VLAD to have horizontal control limits for signaling an improved or a deteriorated performance because the variance of the cumulative sum plotted increases with the sample size. Many authors recommended running the VLAD and some risk‐adjusted cumulative sum (RA‐CUSUM) control chart (such as Steiner et al) simultaneously, one for interpretation and the other for signaling . This approach requires a user to monitor both charts and alarm points matched.…”
Section: Introductionmentioning
confidence: 99%
“…It is not reasonable for a VLAD to have horizontal control limits for signaling an improved or a deteriorated performance because the variance of the cumulative sum plotted increases with the sample size. Many authors recommended running the VLAD and some risk‐adjusted cumulative sum (RA‐CUSUM) control chart (such as Steiner et al) simultaneously, one for interpretation and the other for signaling . This approach requires a user to monitor both charts and alarm points matched.…”
Section: Introductionmentioning
confidence: 99%
“…We postulate that at some time τ , the process changes, so that the parameters are bold-italicβ0=()β01,β01,β02,,β0p before the change, and bold-italicβ1=()β10,β11,β12,,β1p after the change. Most previous work on risk‐adjusted monitoring, such as Grigg and Farewell, Grigg and Spiegelhalter, Steiner et al , Zeng and Zhou and Woodall et al , assumes that the intercept β 0 is the only parameter that changes. This is equivalent to a constant change in the log‐odds for all patients, regardless of their initial condition as expressed in the predictor variables x i .…”
Section: Overviewmentioning
confidence: 99%
“…(2) Sort the N CUSUM statistics in ascending order C t, (1) , C t, (2) , C t, (3) , … , C t,(N) and take the N ′ = ⌈N ⋅ (1 − )⌉ largest CUSUM statistic C t,(N ′ ) as the approximated DPCL h t ( ).…”
Section: Dynamic Probability Control Limitsmentioning
confidence: 99%