在RMarkdown中，如何从模型输出中检索值并将它们放在格式化的LaTex中？

Question

作为一个例子，我正在运行几个生存模型，每个模型都有一组不同的协变量。

第一个模型

> coxph = coxph(Surv(time, event) ~ tr.ma, data = first.data, method = "breslow")
> summary(coxph)
Call:
coxph(formula = Surv(time, event) ~ tr.ma, data = first.data, 
    method = "breslow")

  n= 49, number of events= 46 
   (1 observation deleted due to missingness)

         coef exp(coef) se(coef)     z Pr(>|z|)  
tr.ma 0.09520   1.09988  0.03906 2.437   0.0148 *
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

      exp(coef) exp(-coef) lower .95 upper .95
tr.ma       1.1     0.9092     1.019     1.187

Concordance= 0.694  (se = 0.058 )
Rsquare= 0.109   (max possible= 0.997 )
Likelihood ratio test= 5.68  on 1 df,   p=0.01718
Wald test            = 5.94  on 1 df,   p=0.0148
Score (logrank) test = 5.93  on 1 df,   p=0.01485

第二个模型

> coxph = coxph(Surv(time, event) ~ tr.ma + contag_per, data = first.data, method = "breslow")
> summary(coxph)
Call:
coxph(formula = Surv(time, event) ~ tr.ma + contag_per, data = first.data, 
    method = "breslow")

  n= 49, number of events= 46 
   (1 observation deleted due to missingness)

               coef exp(coef) se(coef)      z Pr(>|z|)    
tr.ma       0.09801   1.10297  0.04231  2.317 0.020518 *  
contag_per -1.97309   0.13903  0.51683 -3.818 0.000135 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

           exp(coef) exp(-coef) lower .95 upper .95
tr.ma          1.103     0.9066   1.01521    1.1983
contag_per     0.139     7.1929   0.05049    0.3828

Concordance= 0.752  (se = 0.058 )
Rsquare= 0.348   (max possible= 0.997 )
Likelihood ratio test= 20.98  on 2 df,   p=2.78e-05
Wald test            = 19.33  on 2 df,   p=6.357e-05
Score (logrank) test = 20.73  on 2 df,   p=3.147e-05

问题

我希望从每个模型的输出中获取exp(coef), Pr(>|z|)并将它们收集到以LaTex格式化的表格中，以生成简明的报告。类似的东西：

Model   covariates   exp(coef)   p-value
----------------------------------------
1       tr.ma        1.099       0.0148
2       tr.ma        1.103       0.0205
        contag_per   0.139       0.00013
...

如果我可以实现自动化，那将是非常棒的，因为我有大约25个模型，并且必须手动检索并输入表中的数字将非常不方便且容易出错。感谢。