Nosocomial Infection, Length of Stay, and Time-Dependent Bias

被引：73

作者：

Beyersmann, Jan ^{[1
,2
]}

Kneib, Thomas ^{[3
]}

Schumacher, Martin ^{[2
]}

Gastmeier, Petra ^{[4
]}

机构：

[1] Univ Freiburg, Freiburg Ctr Data Anal & Modelling, D-79104 Freiburg, Germany

[2] Univ Med Ctr Freiburg, Inst Med Biometry & Med Informat, Munich, Germany

[3] Univ Munich, Dept Stat, Munich, Germany

[4] Charite Univ Med Berlin, Inst Hyg & Environm Med, D-13353 Berlin, Germany

来源：

INFECTION CONTROL AND HOSPITAL EPIDEMIOLOGY | 2009年 / 30卷 / 03期

关键词：

MULTISTATE MODELS; IMPACT;

D O I：

10.1086/596020

中图分类号：

R1 [预防医学、卫生学];

学科分类号：

1004 ; 120402 ;

摘要：

Nosocomial pneumonia and its impact on length of stay are major healthcare concerns. From an epidemiological perspective, nosocomial pneumonia is a time-dependent event. Any statistical analysis that does not explicitly model this time dependency will be biased. The bias is not redeemed by adjusting for baseline information.

引用

页码：273 / 276

页数：4

共 10 条

[1]

[Anonymous], MODELING SURVIVAL DA

[2]

[Anonymous], METHODOLOGICALLY FOC

[3] Use of multistate models to assess prolongation of intensive care unit stay due to nosocomial infection [J].

Beyersmann, J. ;

Gastmeier, P. ;

Grundmann, H. ;

Baerwolff, S. ;

Geffers, C. ;

Behnke, M. ;

Rueden, H. ;

Schumacher, M. .

INFECTION CONTROL AND HOSPITAL EPIDEMIOLOGY, 2006, 27 (05) :493-499

[4] The impact of time-dependent bias in proportional hazards modelling [J].

Beyersmann, Jan ;

Wolkewitz, Martin ;

Schumacher, Martin .

STATISTICS IN MEDICINE, 2008, 27 (30) :6439-6454

[5] An easy mathematical proof showed that time-dependent bias inevitably leads to biased effect estimation [J].

Beyersmann, Jan ;

Gastmeier, Petra ;

Wolkewitz, Martin ;

Schumacher, Martin .

JOURNAL OF CLINICAL EPIDEMIOLOGY, 2008, 61 (12) :1216-1221

[6] Bayesian semiparametric multi-state models [J].

Kneib, Thomas ;

Hennerfeind, Andrea .

STATISTICAL MODELLING, 2008, 8 (02) :169-198

[7] A simulation-based evaluation of methods to estimate the impact of an adverse event on hospital length of stay [J].

Samore, Matthew H. ;

Shen, Shuying ;

Greene, Tom ;

Stoddard, Greg ;

Sauer, Brian ;

Shinogle, Judith ;

Nebeker, Jonathan ;

Harbarth, Stephan .

MEDICAL CARE, 2007, 45 (10) :S108-S115

[8] Immortal time bias in pharmacoepidemiology [J].

Suissa, Samy .

AMERICAN JOURNAL OF EPIDEMIOLOGY, 2008, 167 (04) :492-499

[9] Time-dependent bias was common in survival analyses published in leading clinical journals [J].

van Walraven, C ;

Davis, D ;

Forster, AJ ;

Wells, GA .

JOURNAL OF CLINICAL EPIDEMIOLOGY, 2004, 57 (07) :672-682

[10] Risk factors for the development of nosocomial pneumonia and mortality on intensive care units:: application of competing risks models [J].

Wolkewitz, Martin ;

Vonberg, Ralf Peter ;

Grundmann, Hajo ;

Beyersmann, Jan ;

Gastmeier, Petra ;

Barwolff, Sina ;

Geffers, Christine ;

Behnke, Michael ;

Ruden, Henning ;

Schumacher, Martin .

CRITICAL CARE, 2008, 12 (02)

← 1 →