Performance characteristics of profiling methods and the impact of inadequate case-mix adjustment

Yanjun Chen, Damla Şentürk, Jason P. Estes, Luis F. Campos, Connie M. Rhee, Lorien Dalrymple, Kamyar Kalantar-Zadeh, Danh V. Nguyen

Research output: Contribution to journalArticle

Abstract

Profiling or evaluation of health care providers involves the application of statistical models to compare each provider’s performance with respect to a patient outcome, such as unplanned 30-day hospital readmission, adjusted for patient case-mix characteristics. The nationally adopted method is based on random effects (RE) hierarchical logistic regression models. Although RE models are sensible for modeling hierarchical data, novel high dimensional fixed effects (FE) models have been proposed which may be well-suited for the objective of identifying sub-standard performance. However, there are limited comparative studies. Thus, we examine their relative performance, including the impact of inadequate case-mix adjustment.

Original languageEnglish (US)
JournalCommunications in Statistics: Simulation and Computation
DOIs
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint

Profiling
Adjustment
Fixed Effects Model
Hierarchical Data
Logistic Regression Model
Random Effects Model
Random Effects
Healthcare
Statistical Model
Comparative Study
High-dimensional
Health care
Logistics
Evaluation
Modeling

Keywords

  • Fixed effects
  • Hierarchical logistic regression
  • Profiling analysis
  • Random effects

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation

Cite this

Performance characteristics of profiling methods and the impact of inadequate case-mix adjustment. / Chen, Yanjun; Şentürk, Damla; Estes, Jason P.; Campos, Luis F.; Rhee, Connie M.; Dalrymple, Lorien; Kalantar-Zadeh, Kamyar; Nguyen, Danh V.

In: Communications in Statistics: Simulation and Computation, 01.01.2019.

Research output: Contribution to journalArticle

Chen, Yanjun ; Şentürk, Damla ; Estes, Jason P. ; Campos, Luis F. ; Rhee, Connie M. ; Dalrymple, Lorien ; Kalantar-Zadeh, Kamyar ; Nguyen, Danh V. / Performance characteristics of profiling methods and the impact of inadequate case-mix adjustment. In: Communications in Statistics: Simulation and Computation. 2019.
@article{d0a74d4b6781417cb5f06dcfd9e6b6c0,
title = "Performance characteristics of profiling methods and the impact of inadequate case-mix adjustment",
abstract = "Profiling or evaluation of health care providers involves the application of statistical models to compare each provider’s performance with respect to a patient outcome, such as unplanned 30-day hospital readmission, adjusted for patient case-mix characteristics. The nationally adopted method is based on random effects (RE) hierarchical logistic regression models. Although RE models are sensible for modeling hierarchical data, novel high dimensional fixed effects (FE) models have been proposed which may be well-suited for the objective of identifying sub-standard performance. However, there are limited comparative studies. Thus, we examine their relative performance, including the impact of inadequate case-mix adjustment.",
keywords = "Fixed effects, Hierarchical logistic regression, Profiling analysis, Random effects",
author = "Yanjun Chen and Damla Şent{\"u}rk and Estes, {Jason P.} and Campos, {Luis F.} and Rhee, {Connie M.} and Lorien Dalrymple and Kamyar Kalantar-Zadeh and Nguyen, {Danh V.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1080/03610918.2019.1595649",
language = "English (US)",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",

}

TY - JOUR

T1 - Performance characteristics of profiling methods and the impact of inadequate case-mix adjustment

AU - Chen, Yanjun

AU - Şentürk, Damla

AU - Estes, Jason P.

AU - Campos, Luis F.

AU - Rhee, Connie M.

AU - Dalrymple, Lorien

AU - Kalantar-Zadeh, Kamyar

AU - Nguyen, Danh V.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Profiling or evaluation of health care providers involves the application of statistical models to compare each provider’s performance with respect to a patient outcome, such as unplanned 30-day hospital readmission, adjusted for patient case-mix characteristics. The nationally adopted method is based on random effects (RE) hierarchical logistic regression models. Although RE models are sensible for modeling hierarchical data, novel high dimensional fixed effects (FE) models have been proposed which may be well-suited for the objective of identifying sub-standard performance. However, there are limited comparative studies. Thus, we examine their relative performance, including the impact of inadequate case-mix adjustment.

AB - Profiling or evaluation of health care providers involves the application of statistical models to compare each provider’s performance with respect to a patient outcome, such as unplanned 30-day hospital readmission, adjusted for patient case-mix characteristics. The nationally adopted method is based on random effects (RE) hierarchical logistic regression models. Although RE models are sensible for modeling hierarchical data, novel high dimensional fixed effects (FE) models have been proposed which may be well-suited for the objective of identifying sub-standard performance. However, there are limited comparative studies. Thus, we examine their relative performance, including the impact of inadequate case-mix adjustment.

KW - Fixed effects

KW - Hierarchical logistic regression

KW - Profiling analysis

KW - Random effects

UR - http://www.scopus.com/inward/record.url?scp=85063566545&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063566545&partnerID=8YFLogxK

U2 - 10.1080/03610918.2019.1595649

DO - 10.1080/03610918.2019.1595649

M3 - Article

AN - SCOPUS:85063566545

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

ER -