Aggregate data meta-analysis with time-to-event outcomes

被引:449
作者
Williamson, PR [1 ]
Smith, CT
Hutton, JL
Marson, AG
机构
[1] Univ Liverpool, Dept Math Sci, Liverpool L69 3BX, Merseyside, England
[2] Univ Warwick, Dept Stat, Coventry, W Midlands, England
关键词
meta-analysis; time-to-event outcome; aggregate data; survival curve; number at risk;
D O I
10.1002/sim.1303
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
In a meta-analysis of randomized controlled trials with time-to-event outcomes, an aggregate data approach may be required for some or all included studies. Variation in the reporting of survival analyses in journals suggests that no single method for extracting the log(hazard ratio) estimate will suffice. Methods are described which improve upon a previously proposed method for estimating the log(HR) from survival curves. These methods extend to life-tables. In the situation where the treatment effect varies over time and the trials in the meta-analysis have different lengths of follow-up, heterogeneity may be evident. In order to assess whether the hazard ratio changes with time, several tests are proposed and compared. A cohort study comparing life expectancy of males and females with cerebral palsy and a systematic review of five trials comparing two anti-epileptic drugs, carbamazepine and sodium valproate, are used for illustration. Copyright (C) 2002 John Wiley Sons, Ltd.
引用
收藏
页码:3337 / 3351
页数:15
相关论文
共 27 条
  • [1] REVIEW OF SURVIVAL ANALYSES PUBLISHED IN CANCER JOURNALS
    ALTMAN, DG
    DESTAVOLA, BL
    LOVE, SB
    STEPNIEWSKA, KA
    [J]. BRITISH JOURNAL OF CANCER, 1995, 72 (02) : 511 - 518
  • [2] Armitage P., 2001, STAT METHODS MED RES, V4th
  • [3] Boutitie F, 1998, STAT MED, V17, P2883, DOI 10.1002/(SICI)1097-0258(19981230)17:24<2883::AID-SIM900>3.0.CO
  • [4] 2-L
  • [5] COOPER H, 1994, HDB RES SYNTHESIS, P285
  • [6] METAANALYSIS IN CLINICAL-TRIALS
    DERSIMONIAN, R
    LAIRD, N
    [J]. CONTROLLED CLINICAL TRIALS, 1986, 7 (03): : 177 - 188
  • [7] Randomised comparative monotherapy trial of phenobarbitone, phenytoin, carbamazepine, or sodium valproate for newly diagnosed childhood epilepsy
    deSilva, M
    MacArdle, B
    McGowan, M
    Hughes, E
    Stewart, J
    Neville, BGR
    Johnson, AL
    Reynolds, EH
    [J]. LANCET, 1996, 347 (9003) : 709 - 713
  • [8] A NOTE ON GRAPHICAL PRESENTATION OF ESTIMATED ODDS RATIOS FROM SEVERAL CLINICAL-TRIALS
    GALBRAITH, RF
    [J]. STATISTICS IN MEDICINE, 1988, 7 (08) : 889 - 894
  • [9] Hardy RJ, 1996, STAT MED, V15, P619, DOI 10.1002/(SICI)1097-0258(19960330)15:6<619::AID-SIM188>3.0.CO
  • [10] 2-A