dat.anand1999.RdResults from 34 trials examining the effectiveness of oral anticoagulants in patients with coronary artery disease.
dat.anand1999The data frame contains the following columns:
| study | character | author(s) or trial name |
| year | numeric | publication year |
| intensity | character | intensity of anticoagulation (low, medium, or high) |
| asp.t | numeric | concomitant use of aspirin in the treatment group (0 = no, 1 = yes) |
| asp.c | numeric | concomitant use of aspirin in the control group (0 = no, 1 = yes) |
| ai | numeric | number of deaths in the treatment group |
| n1i | numeric | number of patients in the treatment group |
| ci | numeric | number of deaths in the control group |
| n2i | numeric | number of patients in the control group |
The dataset includes the results from 34 randomized clinical trials that examined the effectiveness of oral anticoagulants in patients with coronary artery disease. The results given here are focused on the total mortality in the treatment versus control groups.
Strictly speaking, there are only 31 trials, since Breddin et al. (1980) and ATACS (1990) are multiarm trials.
According to a correction, dat.anand1999$ci[29] should be 1. But then dat.anand1999$ci[21] would also have to be 1 (if these data indeed refer to the same control group). This appears contradictory, so this correction was not made.
Anand, S. S., & Yusuf, S. (1999). Oral anticoagulant therapy in patients with coronary artery disease: A meta-analysis. Journal of the American Medical Association, 282(21), 2058–2067. https://doi.org/10.1001/jama.282.21.2058
medicine, cardiology, odds ratios, Mantel-Haenszel method
### copy data into 'dat' and examine data
dat <- dat.anand1999
dat
#> study year intensity asp.t asp.c ai n1i ci n2i
#> 1 MacMillan et al 1960 high 0 0 8 27 0 23
#> 2 Borchegrevink 1960 high 0 0 1 103 8 100
#> 3 Clausen et al 1961 high 0 0 15 93 13 99
#> 4 Harvald et al 1961 high 0 0 34 145 45 171
#> 5 Apenstrom and Korsan-Bengtsen 1964 high 0 0 39 118 50 113
#> 6 Conrad et al 1964 high 0 0 9 52 8 34
#> 7 Wasserman et al 1966 high 0 0 12 77 15 70
#> 8 Loeliger et al 1967 high 0 0 8 128 11 112
#> 9 Lovell et al 1967 high 0 0 33 178 39 172
#> 10 Seaman et al 1969 high 0 0 36 88 31 87
#> 11 Sorensen et al 1969 high 0 0 30 156 43 120
#> 12 Sixty Plus Reinfarction 1980 high 0 0 51 439 69 439
#> 13 WARIS 1990 high 0 0 94 607 123 607
#> 14 ASPECT 1994 high 0 0 170 1700 189 1704
#> 15 Meuwissen et al 1969 high 0 0 1 68 8 70
#> 16 Drapkin and Merskey 1974 high 0 0 111 745 166 782
#> 17 Breddin et al 1980 high 0 0 39 320 32 309
#> 18 Breddin et al 1980 high 0 1 39 320 27 317
#> 19 CABADAS 1993 high 0 1 3 307 8 309
#> 20 Eritsland et al 1996 high 0 1 5 319 9 291
#> 21 ATACS 1990 high 0 1 1 24 0 32
#> 22 McEnany et al 1982 moderate 0 1 1 68 1 71
#> 23 Kraska et al 1981 moderate 0 1 5 60 7 60
#> 24 EPSIM 1982 moderate 0 1 67 652 72 651
#> 25 COOP 1969 moderate 0 0 120 385 114 350
#> 26 MRC Anticoagulant 1964 moderate 0 0 29 195 40 188
#> 27 Williams et al 1986 moderate 0 0 1 51 4 51
#> 28 McEnany et al 1982 moderate 0 0 1 68 3 77
#> 29 ATACS 1990 high 1 1 0 37 0 32
#> 30 OASIS Pilot 2 1998 moderate 1 1 2 98 5 99
#> 31 ATACS-Main 1994 moderate 1 1 2 105 2 109
#> 32 OASIS Pilot 1998 low 1 1 2 155 3 154
#> 33 Post-CABG 1997 low 1 1 28 674 39 677
#> 34 CARS 1997 low 1 1 118 3382 102 3393
### load metafor package
library(metafor)
### High-Intensity OA vs Control
rma.mh(measure="OR", ai=ai, n1i=n1i, ci=ci, n2i=n2i, data=dat,
subset=(intensity=="high" & asp.t==0 & asp.c==0), digits=2)
#>
#> Equal-Effects Model (k = 17)
#>
#> I^2 (total heterogeneity / total variability): 41.89%
#> H^2 (total variability / sampling variability): 1.72
#>
#> Test for Heterogeneity:
#> Q(df = 16) = 27.54, p-val = 0.04
#>
#> Model Results (log scale):
#>
#> estimate se zval pval ci.lb ci.ub
#> -0.26 0.06 -4.65 <.01 -0.37 -0.15
#>
#> Model Results (OR scale):
#>
#> estimate ci.lb ci.ub
#> 0.77 0.69 0.86
#>
#> Cochran-Mantel-Haenszel Test: CMH = 21.49, df = 1, p-val < 0.01
#> Tarone's Test for Heterogeneity: X^2 = 34.88, df = 16, p-val < 0.01
#>
### High- or Moderate-Intensity OA vs Aspirin
rma.mh(measure="OR", ai=ai, n1i=n1i, ci=ci, n2i=n2i, data=dat,
subset=(intensity %in% c("high","moderate") & asp.t==0 & asp.c==1), digits=2)
#>
#> Equal-Effects Model (k = 7)
#>
#> I^2 (total heterogeneity / total variability): 16.57%
#> H^2 (total variability / sampling variability): 1.20
#>
#> Test for Heterogeneity:
#> Q(df = 6) = 7.19, p-val = 0.30
#>
#> Model Results (log scale):
#>
#> estimate se zval pval ci.lb ci.ub
#> -0.03 0.13 -0.26 0.80 -0.30 0.23
#>
#> Model Results (OR scale):
#>
#> estimate ci.lb ci.ub
#> 0.97 0.74 1.26
#>
#> Cochran-Mantel-Haenszel Test: CMH = 0.04, df = 1, p-val = 0.85
#> Tarone's Test for Heterogeneity: X^2 = 8.05, df = 6, p-val = 0.23
#>
### Moderate-Intensity OA vs Control
rma.mh(measure="OR", ai=ai, n1i=n1i, ci=ci, n2i=n2i, data=dat,
subset=(intensity=="moderate" & asp.t==0 & asp.c==0), digits=2)
#>
#> Equal-Effects Model (k = 4)
#>
#> I^2 (total heterogeneity / total variability): 5.55%
#> H^2 (total variability / sampling variability): 1.06
#>
#> Test for Heterogeneity:
#> Q(df = 3) = 3.18, p-val = 0.37
#>
#> Model Results (log scale):
#>
#> estimate se zval pval ci.lb ci.ub
#> -0.20 0.13 -1.48 0.14 -0.46 0.06
#>
#> Model Results (OR scale):
#>
#> estimate ci.lb ci.ub
#> 0.82 0.63 1.07
#>
#> Cochran-Mantel-Haenszel Test: CMH = 1.99, df = 1, p-val = 0.16
#> Tarone's Test for Heterogeneity: X^2 = 3.35, df = 3, p-val = 0.34
#>
### High- or Moderate-Intensity OA and Aspirin vs Aspirin
rma.mh(measure="OR", ai=ai, n1i=n1i, ci=ci, n2i=n2i, data=dat,
subset=(intensity %in% c("high","moderate") & asp.t==1 & asp.c==1), digits=2)
#> Warning: Some yi/vi values are NA.
#>
#> Equal-Effects Model (k = 3)
#>
#> I^2 (total heterogeneity / total variability): 0.00%
#> H^2 (total variability / sampling variability): 0.55
#>
#> Test for Heterogeneity:
#> Q(df = 1) = 0.55, p-val = 0.46
#>
#> Model Results (log scale):
#>
#> estimate se zval pval ci.lb ci.ub
#> -0.55 0.63 -0.87 0.38 -1.80 0.69
#>
#> Model Results (OR scale):
#>
#> estimate ci.lb ci.ub
#> 0.57 0.17 1.99
#>
#> Cochran-Mantel-Haenszel Test: CMH = 0.33, df = 1, p-val = 0.56
#> Tarone's Test for Heterogeneity: X^2 = 0.56, df = 1, p-val = 0.45
#>
### Low-Intensity OA and Aspirin vs Aspirin
rma.mh(measure="OR", ai=ai, n1i=n1i, ci=ci, n2i=n2i, data=dat,
subset=(intensity=="low" & asp.t==1 & asp.c==1), digits=2)
#>
#> Equal-Effects Model (k = 3)
#>
#> I^2 (total heterogeneity / total variability): 37.85%
#> H^2 (total variability / sampling variability): 1.61
#>
#> Test for Heterogeneity:
#> Q(df = 2) = 3.22, p-val = 0.20
#>
#> Model Results (log scale):
#>
#> estimate se zval pval ci.lb ci.ub
#> 0.03 0.12 0.27 0.79 -0.20 0.27
#>
#> Model Results (OR scale):
#>
#> estimate ci.lb ci.ub
#> 1.03 0.82 1.30
#>
#> Cochran-Mantel-Haenszel Test: CMH = 0.04, df = 1, p-val = 0.84
#> Tarone's Test for Heterogeneity: X^2 = 3.25, df = 2, p-val = 0.20
#>