deft_do: Implement deft method

In metawho: Meta-Analytical Implementation to Identify Who Benefits Most from Treatments

Description

'deft' method is a meta-analytical approach to pool conclusion from multiple studies. More details please see references.

Usage

deft_do(prepare, group_level, method = "FE")

Arguments

prepare	a result data.frame from deft_prepare function or a data.frame contains at least 'trial', 'subgroup', 'yi' and 'sei' these four columns.
group_level	level of subgroup, should be a character vector with length 2 and the reference should put in the first. For example, if you have 'Male' and 'Female' groups and want compare 'Female' with 'Male', then should set c('Male', 'Female').
method	character string specifying whether a fixed- or a random/mixed-effects model should be fitted. A fixed-effects model (with or without moderators) is fitted when using method="FE". Random/mixed-effects models are fitted by setting method equal to one of the following: "DL", "HE", "SJ", "ML", "REML", "EB", "HS", or "GENQ". Default is "REML". See ‘Details’.

Details

About model fit, please see metafor::rma().

Value

a list which class is 'deft'.

Author(s)

Shixiang Wang [e-mail]

References

Fisher, David J., et al. "Meta-analytical methods to identify who benefits most from treatments: daft, deluded, or deft approach?." bmj 356 (2017): j573.

Wang, Shixiang, et al. "The predictive power of tumor mutational burden in lung cancer immunotherapy response is influenced by patients' sex." International journal of cancer (2019).

Examples

data("wang2019")
deft_do(wang2019, group_level = c("Male", "Female"))

Example output

Loading required package: metafor
Loading required package: Matrix
Loading 'metafor' package (version 2.4-0). For an overview 
and introduction to the package please type: help(metafor).
$all
$all$data
                 entry         trial subgroup   hr ci.lb ci.ub  ni   conf_q
1      Rizvi 2015-Male    Rizvi 2015     Male 0.30  0.09  1.00  16 1.959964
2    Rizvi 2015-Female    Rizvi 2015   Female 0.11  0.02  0.56  18 1.959964
3      Rizvi 2018-Male    Rizvi 2018     Male 1.25  0.82  1.90 118 1.959964
4    Rizvi 2018-Female    Rizvi 2018   Female 0.63  0.42  0.95 122 1.959964
5   Hellmann 2018-Male Hellmann 2018     Male 0.90  0.41  1.99  37 1.959964
6 Hellmann 2018-Female Hellmann 2018   Female 0.28  0.12  0.67  38 1.959964
          yi       sei
1 -1.2039728 0.6142831
2 -2.2072749 0.8500678
3  0.2231436 0.2143674
4 -0.4620355 0.2082200
5 -0.1053605 0.4030005
6 -1.2729657 0.4387290

$all$model

Fixed-Effects Model (k = 6)

I^2 (total heterogeneity / total variability):   73.53%
H^2 (total variability / sampling variability):  3.78

Test for Heterogeneity:
Q(df = 5) = 18.8865, p-val = 0.0020

Model Results:

estimate      se     zval    pval    ci.lb    ci.ub 
 -0.3207  0.1289  -2.4883  0.0128  -0.5733  -0.0681  * 

---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1



$subgroup
$subgroup$data
          trial        hr     ci.lb     ci.ub  ni   conf_q        yi       sei
1    Rizvi 2015 0.3666667 0.0469397 2.8641945  34 1.959964 -1.003302 1.0487893
2    Rizvi 2018 0.5040000 0.2805772 0.9053338 240 1.959964 -0.685179 0.2988460
3 Hellmann 2018 0.3111111 0.0967900 1.0000013  75 1.959964 -1.167605 0.5957285

$subgroup$model

Fixed-Effects Model (k = 3)

I^2 (total heterogeneity / total variability):   0.00%
H^2 (total variability / sampling variability):  0.28

Test for Heterogeneity:
Q(df = 2) = 0.5657, p-val = 0.7536

Model Results:

estimate      se     zval    pval    ci.lb    ci.ub 
 -0.7956  0.2589  -3.0737  0.0021  -1.3030  -0.2883  ** 

---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1



attr(,"class")
[1] "deft"

metawho documentation built on Dec. 6, 2019, 5:09 p.m.