Combined bias suppression in single-arm therapy studies

被引:20
作者
Hamre, Harald J. [1 ]
Glockmann, Anja [1 ]
Kienle, Gunver S. [1 ]
Kiene, Helmut [1 ]
机构
[1] Inst Appl Epistemol & Med Methodol, D-79111 Freiburg, Germany
关键词
bias suppression; patient dropouts; prospective studies; regression to the mean; research design; spontaneous remission;
D O I
10.1111/j.1365-2753.2007.00903.x
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Rationale, aims and objectives For therapy evaluation studies, control groups are sometimes not feasible. In single-arm studies, various bias factors apart from the test therapy can affect clinical outcomes. The objective of this analysis was to improve the methods to minimize bias in single-arm studies. Method We present a procedure for combined suppression of several bias factors, using two methods: sample restriction to patients unaffected by bias, and score adjustment. The procedure was used for a secondary analysis of disease score (doctors' global rating, 0-10) in a cohort of patients receiving anthroposophic therapies for chronic diseases. Four bias factors were suppressed stepwise: attrition bias (by replacing missing values with the baseline value carried forward), bias from natural recovery (by sample restriction to patients with disease duration of >= 12 months), regression to the mean due to symptom-driven self-selection (by replacing baseline scores with scores three months before enrolment) and bias from adjunctive therapies (by sample restriction to patients not using adjunctive therapies). Results In the cohort analysed, these four bias factors could together explain a maximum of 37% of the 0- to 6-month improvement of disease score. Conclusion Combined bias suppression, using sample restriction and score adjustment, is a transparent procedure to minimize bias in single-arm therapy studies. Further applicability of the procedure should be tested in future studies.
引用
收藏
页码:923 / 929
页数:7
相关论文
共 41 条
[1]  
[Anonymous], COCHRANE DATABASE SY, DOI DOI 10.1002/14651858.CD003974.PUB2
[2]  
[Anonymous], 2002, Experimental and quasi-experimental designs for generalized causal inference
[3]   Regression to the mean: what it is and how to deal with it [J].
Barnett, AG ;
van der Pols, JC ;
Dobson, AJ .
INTERNATIONAL JOURNAL OF EPIDEMIOLOGY, 2005, 34 (01) :215-220
[5]   THE PHENOMENON OF REGRESSION TO THE MEAN AND CLINICAL INVESTIGATION OF BLOOD CHOLESTEROL LOWERING DRUGS [J].
BOISSEL, JP ;
DUPERAT, B ;
LEIZOROVICZ, A .
EUROPEAN JOURNAL OF CLINICAL PHARMACOLOGY, 1980, 17 (03) :227-230
[6]  
Borkovec TD, 2001, J CLIN PSYCHIAT, V62, P37
[7]   Methods in health service research - Handling uncertainty in economic evaluations of healthcare interventions [J].
Briggs, AH ;
Gray, AM .
BRITISH MEDICAL JOURNAL, 1999, 319 (7210) :635-638
[8]   A more flexible regression-to-the-mean model with possible stratification [J].
Chen, SD ;
Cox, C ;
Cui, L .
BIOMETRICS, 1998, 54 (03) :939-947
[9]   Treatment of refractory status epilepticus with pentobarbital, propofol, or midazolam: A systematic review [J].
Claassen, J ;
Hirsch, LJ ;
Emerson, RG ;
Mayer, SA .
EPILEPSIA, 2002, 43 (02) :146-153
[10]  
CORYELL W, 1994, ARCH GEN PSYCHIAT, V51, P405