院感和感控临床研究的干扰：实验设计与统计分析问题.pdfVIP

Journal of Hospital Infection 86 (2014) 77e82 Available online at Journal of Hospital Infection journal homepage: www.elsevier /journals/jhin Review Interventions to control nosocomial infections: study designs and statistical issues M. Wolkewitz a,*, A.G. Barnett b, M. Palomar Martinez c, U. Frank d, M. Schumacher a for the IMPLEMENT Study Group a Institute of Medical Biometry and Medical Informatics, University of Freiburg, Freiburg, Germany b Institute of Health and Biomedical Innovation and School of Public Health and Social Work, Queensland University of Technology, Queensland, Australia c Hospital Arnau de Vilanova, Lleida, Universitat Autonoma de Barcelona, Barcelona, Spain d Department of Infectiology, Heidelberg University Hospital, Heidelberg, Germany A R T I C L E I N F O S U M M A R Y Article history: There is a wide range of potential study designs for intervention studies to decrease Received 2 July 2013 nosocomial infections in hospitals. The analysis is complex due to competing events, Accepted 26 September 2013 clustering, multiple timescales and time-dependent period and intervention variables. Available online 18 October This review considers the popular preepost quasi-experimental design and compares it 2013 with randomized designs. Randomization can be done in several ways: randomization of the cluster [intensive care unit (ICU) or hospital] in a parallel design; randomization of the Keywords: sequence in a cross-over design; and randomization of th