当因子分层时，在RStudio中使用ggforest绘制Cox PH模型？

我试图找到一种方法，当模型变量之一需要分层时，从Cox-PH模型中绘制一个危险比森林图。对于非分层模型，

ggforest（）

函数非常出色。运行一些示例代码

library(survival)
library(survminer)

model <- coxph(Surv(time, status) ~ sex + rx + adhere,
               data = colon )
ggforest(model)

colon <- within(colon, {
  sex <- factor(sex, labels = c("female", "male"))
  differ <- factor(differ, labels = c("well", "moderate", "poor"))
  extent <- factor(extent, labels = c("submuc.", "muscle", "serosa", "contig."))
})
bigmodel <-
  coxph(Surv(time, status) ~ sex + rx + adhere + differ + extent + node4,
        data = colon )
ggforest(bigmodel)

库（生存）
图书馆（survminer）
模型我认为理想的森林地块只是跳过模型公式中的分层RX变量。如果是这样，我们可以简单地在其中插入一个If子句，忽略与数据中的列名不完全对应的公式部分（例如，“strata（rx）”不是列名）

方法1
如果您对R足够熟悉，可以修改函数，请运行
trace（ggforest，edit=TRUE）
并替换
您可以检查的所有术语：感谢您的快速回复。挑战在于，对于我正在使用的实际数据集，答案并不是一个真正的选项，其中分层变量是一种处理水平的方法，需要在模型中对其进行校正，但不需要进行解释，因此需要使用地层函数。看起来ggforest几乎是ggplot的包装器，所以我想知道是否有办法让它工作。不幸的是，我更像是一个生态学家，在我走的时候学会了r技巧，所以我不确定我所问的是否可行，正如你所说，
ggforest
是一个包装器，所以使用底层的ggplot进行编码肯定是可行的。这里的问题是熟悉分层模型和ggplot2的SO用户池可能不是很大。如果您能提供分层模型绘图的大致草图，您获得帮助的机会可能会增加。谢谢您的建议@Z.Lin，如果使用示例代码绘图，分层模型将与原始问题中的图像相似，但是由于分层的原因，数值略有不同，不包括rx治疗，这是分层的。这正是我所需要的，而且效果很好，非常感谢您的帮助！
stratamodel <- coxph(Surv(time, status) ~ sex + strata(rx) + adhere + differ + extent + node4,
                     data = colon )
ggforest(stratamodel)

allTerms <- lapply(seq_along(terms), function(i) {
  var <- names(terms)[i]
  if(var %in% colnames(data)) {
    if (terms[i] %in% c("factor", "character")) {
      adf <- as.data.frame(table(data[, var]))
      cbind(var = var, adf, pos = 1:nrow(adf))
    }
    else if (terms[i] == "numeric") {
      data.frame(var = var, Var1 = "", Freq = nrow(data), 
                 pos = 1)
    }
    else {
      vars = grep(paste0("^", var, "*."), coef$term, 
                  value = TRUE)
      data.frame(var = vars, Var1 = "", Freq = nrow(data), 
                 pos = seq_along(vars))
    }
  } else {
    message(var, "is not found in data columns, and will be skipped.")
  }
  
})

ggforest(stratamodel) # this should work after the modification

ggforest2 <- function (model, data = NULL, main = "Hazard ratio", 
                       cpositions = c(0.02, 0.22, 0.4), fontsize = 0.7, 
                       refLabel = "reference", noDigits = 2) {
  conf.high <- conf.low <- estimate <- NULL
  stopifnot(class(model) == "coxph")
  data <- survminer:::.get_data(model, data = data)
  terms <- attr(model$terms, "dataClasses")[-1]
  coef <- as.data.frame(broom::tidy(model))
  gmodel <- broom::glance(model)
  allTerms <- lapply(seq_along(terms), function(i) {
    var <- names(terms)[i]
    if(var %in% colnames(data)) {
      if (terms[i] %in% c("factor", "character")) {
        adf <- as.data.frame(table(data[, var]))
        cbind(var = var, adf, pos = 1:nrow(adf))
      }
      else if (terms[i] == "numeric") {
        data.frame(var = var, Var1 = "", Freq = nrow(data), 
                   pos = 1)
      }
      else {
        vars = grep(paste0("^", var, "*."), coef$term, 
                    value = TRUE)
        data.frame(var = vars, Var1 = "", Freq = nrow(data), 
                   pos = seq_along(vars))
      }
    } else {
      message(var, "is not found in data columns, and will be skipped.")
    }    
  })
  allTermsDF <- do.call(rbind, allTerms)
  colnames(allTermsDF) <- c("var", "level", "N", 
                            "pos")
  inds <- apply(allTermsDF[, 1:2], 1, paste0, collapse = "")
  rownames(coef) <- gsub(coef$term, pattern = "`", replacement = "")
  toShow <- cbind(allTermsDF, coef[inds, ])[, c("var", "level", "N", "p.value", 
                                                "estimate", "conf.low", 
                                                "conf.high", "pos")]
  toShowExp <- toShow[, 5:7]
  toShowExp[is.na(toShowExp)] <- 0
  toShowExp <- format(exp(toShowExp), digits = noDigits)
  toShowExpClean <- data.frame(toShow, pvalue = signif(toShow[, 4], noDigits + 1), 
                               toShowExp)
  toShowExpClean$stars <- paste0(round(toShowExpClean$p.value, noDigits + 1), " ", 
                                 ifelse(toShowExpClean$p.value < 0.05, "*", ""), 
                                 ifelse(toShowExpClean$p.value < 0.01, "*", ""), 
                                 ifelse(toShowExpClean$p.value < 0.001, "*", ""))
  toShowExpClean$ci <- paste0("(", toShowExpClean[, "conf.low.1"], 
                              " - ", toShowExpClean[, "conf.high.1"], ")")
  toShowExpClean$estimate.1[is.na(toShowExpClean$estimate)] = refLabel
  toShowExpClean$stars[which(toShowExpClean$p.value < 0.001)] = "<0.001 ***"
  toShowExpClean$stars[is.na(toShowExpClean$estimate)] = ""
  toShowExpClean$ci[is.na(toShowExpClean$estimate)] = ""
  toShowExpClean$estimate[is.na(toShowExpClean$estimate)] = 0
  toShowExpClean$var = as.character(toShowExpClean$var)
  toShowExpClean$var[duplicated(toShowExpClean$var)] = ""
  toShowExpClean$N <- paste0("(N=", toShowExpClean$N, ")")
  toShowExpClean <- toShowExpClean[nrow(toShowExpClean):1, ]
  rangeb <- range(toShowExpClean$conf.low, toShowExpClean$conf.high, 
                  na.rm = TRUE)
  breaks <- axisTicks(rangeb/2, log = TRUE, nint = 7)
  rangeplot <- rangeb
  rangeplot[1] <- rangeplot[1] - diff(rangeb)
  rangeplot[2] <- rangeplot[2] + 0.15 * diff(rangeb)
  width <- diff(rangeplot)
  y_variable <- rangeplot[1] + cpositions[1] * width
  y_nlevel <- rangeplot[1] + cpositions[2] * width
  y_cistring <- rangeplot[1] + cpositions[3] * width
  y_stars <- rangeb[2]
  x_annotate <- seq_len(nrow(toShowExpClean))
  annot_size_mm <- fontsize * 
    as.numeric(grid::convertX(unit(theme_get()$text$size, "pt"), "mm"))
  p <- ggplot(toShowExpClean, 
              aes(seq_along(var), exp(estimate))) + 
    geom_rect(aes(xmin = seq_along(var) - 0.5, 
                  xmax = seq_along(var) + 0.5, 
                  ymin = exp(rangeplot[1]), 
                  ymax = exp(rangeplot[2]), 
                  fill = ordered(seq_along(var)%%2 + 1))) +
    scale_fill_manual(values = c("#FFFFFF33",  "#00000033"), guide = "none") + 
    geom_point(pch = 15, size = 4) + 
    geom_errorbar(aes(ymin = exp(conf.low), ymax = exp(conf.high)), 
                  width = 0.15) + 
    geom_hline(yintercept = 1, linetype = 3) + 
    coord_flip(ylim = exp(rangeplot)) + 
    ggtitle(main) + 
    scale_y_log10(name = "", labels = sprintf("%g", breaks), 
                  expand = c(0.02, 0.02), breaks = breaks) + 
    theme_light() +
    theme(panel.grid.minor.y = element_blank(), 
          panel.grid.minor.x = element_blank(), 
          panel.grid.major.y = element_blank(), 
          legend.position = "none", 
          panel.border = element_blank(), 
          axis.title.y = element_blank(), 
          axis.text.y = element_blank(), 
          axis.ticks.y = element_blank(), 
          plot.title = element_text(hjust = 0.5)) + 
    xlab("") + 
    annotate(geom = "text", x = x_annotate, y = exp(y_variable), 
             label = toShowExpClean$var, fontface = "bold", 
             hjust = 0, size = annot_size_mm) + 
    annotate(geom = "text", x = x_annotate, y = exp(y_nlevel), hjust = 0, 
             label = toShowExpClean$level, 
             vjust = -0.1, size = annot_size_mm) + 
    annotate(geom = "text", x = x_annotate, y = exp(y_nlevel), 
             label = toShowExpClean$N, fontface = "italic", hjust = 0, 
             vjust = ifelse(toShowExpClean$level == "", 0.5, 1.1),
             size = annot_size_mm) + 
    annotate(geom = "text", x = x_annotate, y = exp(y_cistring), 
             label = toShowExpClean$estimate.1, size = annot_size_mm, 
             vjust = ifelse(toShowExpClean$estimate.1 == "reference", 0.5, -0.1)) + 
    annotate(geom = "text", x = x_annotate, y = exp(y_cistring), 
             label = toShowExpClean$ci, size = annot_size_mm, 
             vjust = 1.1, fontface = "italic") + 
    annotate(geom = "text", x = x_annotate, y = exp(y_stars), 
             label = toShowExpClean$stars, size = annot_size_mm, 
             hjust = -0.2, fontface = "italic") +
    annotate(geom = "text", x = 0.5, y = exp(y_variable), 
             label = paste0("# Events: ", gmodel$nevent, 
                            "; Global p-value (Log-Rank): ", 
                            format.pval(gmodel$p.value.log, eps = ".001"), 
                            " \nAIC: ", round(gmodel$AIC, 2), 
                            "; Concordance Index: ", round(gmodel$concordance, 2)), 
             size = annot_size_mm, hjust = 0, vjust = 1.2, fontface = "italic")
  gt <- ggplot_gtable(ggplot_build(p))
  gt$layout$clip[gt$layout$name == "panel"] <- "off"
  ggpubr::as_ggplot(gt)
}