美文网首页收入即学习
R语言超详细Logistic回归模型进行临床决策曲线绘制(DCA

R语言超详细Logistic回归模型进行临床决策曲线绘制(DCA

作者: 灵活胖子的进步之路 | 来源:发表于2020-10-07 00:06 被阅读0次

程序包准备,#一定要把dca.R放在之前设定的起始目录中。

source("dca.R")#需要把这个代码放到加载目录里,文章最后会贴出,用的时候直接复查到.R后缀的文件并改名为dca.R就行
library(nricens)
library(rms)
library(foreign)

#数据准备

mydata<-read.table("2020090873.csv",header=T,sep = ",")#读取当前目录文件,CSV文件分割为",",标题为真,第一行设定为标题

str(mydata)#展示数据集的结构


mydata$MVI<-factor(mydata$MVI,labels=c("M1","M2","M3"))
mydata$preHBeAg<-factor(mydata$preHBeAg,labels=c("negative","positive"))
mydata$diameter5<-factor(mydata$diameter5,labels=c("≤5",">5"))
mydata$Multiple.shots<-factor(mydata$Multiple.shots,labels=c("Single","Multiple"))
mydata$Satellite<-factor(mydata$Satellite,labels=c("no","yes"))
mydata$Serosa<-factor(mydata$Serosa,labels=c("no","yes"))
#把需要应用的分类变量设定哑变量并设定为无序多分类变量,原则上二分类变量无序上述改变,但改变后后续列线图会同时显示lable的名称。
#AFP值取了自然对数为底的对数,对其进行正太化,此处未显示

str(mydata)#再次展示数据集的结构,注意确定为因子变量的变量名称变化

attach(mydata)#把数据集加载入当前环境中

dev = mydata[mydata$devlopval==0,]#根据devlopval拆分为建模集
vad = mydata[mydata$devlopval==1,]#根据devlopval拆分为验证集


#构建三个回归模型

modelA <- glm(team  ~ LnAFP+preHBeAg +diameter5+Multiple.shots+Serosa+MVI+Satellit, data = dev, family = binomial(link="logit"),x=TRUE)
summary(modelA)
cbind(coef= coef(modelA),confint(modelA))
exp(cbind(OR= coef(modelA),confint(modelA)))
dev$predmodelA<- predict(newdata=dev,modelA,"response")

modelB <- glm(team  ~BCLC , data = dev, family = binomial(link="logit"),x=TRUE)
summary(modelB)
cbind(coef= coef(modelB),confint(modelB))
exp(cbind(OR= coef(modelB),confint(modelB)))
dev$predmodelB<- predict(newdata=dev,modelB,"response")

modelC <- glm(team  ~AJCC8th , data = dev, family = binomial(link="logit"),x=TRUE)
summary(modelC)
cbind(coef= coef(modelC),confint(modelC))
exp(cbind(OR= coef(modelC),confint(modelC)))
dev$predmodelC<- predict(newdata=dev,modelC,"response")

#建模人群Decision Curve Analysis 
dca(data=dev, outcome="team", predictors=c("predmodelA", "predmodelB","predmodelC"),smooth="TRUE", probability=c("TRUE", "TRUE","TRUE")) 

#验证人群Decision Curve Analysis 

#计算验证人群预测值
vad$predmodelA<- predict(newdata=vad,modelA,"response")
vad$predmodelB<- predict(newdata=vad,modelB,"response")
vad$predmodelC<- predict(newdata=vad,modelC,"response")


dca(data=vad, outcome="team", predictors=c("predmodelA", "predmodelB","predmodelC"),smooth="TRUE", probability=c("TRUE", "TRUE","TRUE")) 
验证组DCA曲线

以下为dca.R的内容

dca <- function(data, outcome, predictors, xstart=0.01, xstop=0.99, xby=0.01, 
  ymin=-0.05, probability=NULL, harm=NULL,graph=TRUE, intervention=FALSE, 
  interventionper=100, smooth=FALSE,loess.span=0.10) {
  
  # LOADING REQUIRED LIBRARIES
  require(stats)

  # data MUST BE A DATA FRAME
  if (class(data)!="data.frame") {
      stop("Input data must be class data.frame")
  }
  
  #ONLY KEEPING COMPLETE CASES
  data=data[complete.cases(data[append(outcome,predictors)]),append(outcome,predictors)]

  # outcome MUST BE CODED AS 0 AND 1
  if (max(data[[outcome]])>1 | min(data[[outcome]])<0) {
    stop("outcome cannot be less than 0 or greater than 1")
  }
  # xstart IS BETWEEN 0 AND 1
  if (xstart<0 | xstart>1) {
    stop("xstart must lie between 0 and 1")
  }
  
  # xstop IS BETWEEN 0 AND 1
  if (xstop<0 | xstop>1) {
    stop("xstop must lie between 0 and 1")
  }
  
  # xby IS BETWEEN 0 AND 1
  if (xby<=0 | xby>=1) {
    stop("xby must lie between 0 and 1")
  }
  
  # xstart IS BEFORE xstop
  if (xstart>=xstop) {
    stop("xstop must be larger than xstart")
  }
     
  #STORING THE NUMBER OF PREDICTORS SPECIFIED
  pred.n=length(predictors)
  
  #IF probability SPECIFIED ENSURING THAT EACH PREDICTOR IS INDICATED AS A YES OR NO
  if (length(probability)>0 & pred.n!=length(probability)) {
    stop("Number of probabilities specified must be the same as the number of predictors being checked.")
  }
 
  #IF harm SPECIFIED ENSURING THAT EACH PREDICTOR HAS A SPECIFIED HARM
  if (length(harm)>0 & pred.n!=length(harm)) {
    stop("Number of harms specified must be the same as the number of predictors being checked.")
  }
  
  #INITIALIZING DEFAULT VALUES FOR PROBABILITES AND HARMS IF NOT SPECIFIED
  if (length(harm)==0) {
    harm=rep(0,pred.n)
  }
  if (length(probability)==0) {
    probability=rep(TRUE,pred.n)
  }
  
  
  #CHECKING THAT EACH probability ELEMENT IS EQUAL TO YES OR NO, 
  #AND CHECKING THAT PROBABILITIES ARE BETWEEN 0 and 1
  #IF NOT A PROB THEN CONVERTING WITH A LOGISTIC REGRESSION
  for(m in 1:pred.n) { 
    if (probability[m]!=TRUE & probability[m]!=FALSE) {
      stop("Each element of probability vector must be TRUE or FALSE")
    }
    if (probability[m]==TRUE & (max(data[predictors[m]])>1 | min(data[predictors[m]])<0)) {
      stop(paste(predictors[m],"must be between 0 and 1 OR sepcified as a non-probability in the probability option",sep=" "))  
    }
    if(probability[m]==FALSE) {
      model=NULL
      pred=NULL
      model=glm(data.matrix(data[outcome]) ~ data.matrix(data[predictors[m]]), family=binomial("logit"))
      pred=data.frame(model$fitted.values)
      pred=data.frame(pred)
      names(pred)=predictors[m]
      data=cbind(data[names(data)!=predictors[m]],pred)
      print(paste(predictors[m],"converted to a probability with logistic regression. Due to linearity assumption, miscalibration may occur.",sep=" "))
    }
  }

  # THE PREDICTOR NAMES CANNOT BE EQUAL TO all OR none.
  if (length(predictors[predictors=="all" | predictors=="none"])) {
    stop("Prediction names cannot be equal to all or none.")
  }  
  
  #########  CALCULATING NET BENEFIT   #########
  N=dim(data)[1]
  event.rate=colMeans(data[outcome])
  
  # CREATING DATAFRAME THAT IS ONE LINE PER THRESHOLD PER all AND none STRATEGY
  nb=data.frame(seq(from=xstart, to=xstop, by=xby))
  names(nb)="threshold"
  interv=nb
  
  nb["all"]=event.rate - (1-event.rate)*nb$threshold/(1-nb$threshold)
  nb["none"]=0
  
  # CYCLING THROUGH EACH PREDICTOR AND CALCULATING NET BENEFIT
  for(m in 1:pred.n){
    for(t in 1:length(nb$threshold)){
      # COUNTING TRUE POSITIVES AT EACH THRESHOLD
      tp=mean(data[data[[predictors[m]]]>=nb$threshold[t],outcome])*sum(data[[predictors[m]]]>=nb$threshold[t])
      # COUNTING FALSE POSITIVES AT EACH THRESHOLD
      fp=(1-mean(data[data[[predictors[m]]]>=nb$threshold[t],outcome]))*sum(data[[predictors[m]]]>=nb$threshold[t])
      #setting TP and FP to 0 if no observations meet threshold prob.
      if (sum(data[[predictors[m]]]>=nb$threshold[t])==0) {
        tp=0
        fp=0
      }
      
      # CALCULATING NET BENEFIT
      nb[t,predictors[m]]=tp/N - fp/N*(nb$threshold[t]/(1-nb$threshold[t])) - harm[m]
    }
    interv[predictors[m]]=(nb[predictors[m]] - nb["all"])*interventionper/(interv$threshold/(1-interv$threshold))
  }
  
  # CYCLING THROUGH EACH PREDICTOR AND SMOOTH NET BENEFIT AND INTERVENTIONS AVOIDED 
  for(m in 1:pred.n) {
    if (smooth==TRUE){
      lws=loess(data.matrix(nb[!is.na(nb[[predictors[m]]]),predictors[m]]) ~ data.matrix(nb[!is.na(nb[[predictors[m]]]),"threshold"]),span=loess.span)
      nb[!is.na(nb[[predictors[m]]]),paste(predictors[m],"_sm",sep="")]=lws$fitted
      
      lws=loess(data.matrix(interv[!is.na(nb[[predictors[m]]]),predictors[m]]) ~ data.matrix(interv[!is.na(nb[[predictors[m]]]),"threshold"]),span=loess.span)
      interv[!is.na(nb[[predictors[m]]]),paste(predictors[m],"_sm",sep="")]=lws$fitted
    }
  }
    
  # PLOTTING GRAPH IF REQUESTED
  if (graph==TRUE) {
    require(graphics)
    
    # PLOTTING INTERVENTIONS AVOIDED IF REQUESTED
    if(intervention==TRUE) {
      # initialize the legend label, color, and width using the standard specs of the none and all lines
      legendlabel <- NULL
      legendcolor <- NULL
      legendwidth <- NULL
      legendpattern <- NULL
      
      #getting maximum number of avoided interventions
      ymax=max(interv[predictors],na.rm = TRUE)
      
      #INITIALIZING EMPTY PLOT WITH LABELS
      plot(x=nb$threshold, y=nb$all, type="n" ,xlim=c(xstart, xstop), ylim=c(ymin, ymax), xlab="Threshold probability", ylab=paste("Net reduction in interventions per",interventionper,"patients"))
      
      #PLOTTING INTERVENTIONS AVOIDED FOR EACH PREDICTOR
      for(m in 1:pred.n) {
        if (smooth==TRUE){
          lines(interv$threshold,data.matrix(interv[paste(predictors[m],"_sm",sep="")]),col=m,lty=2)
        } else {
          lines(interv$threshold,data.matrix(interv[predictors[m]]),col=m,lty=2)
        }
        
        # adding each model to the legend
        legendlabel <- c(legendlabel, predictors[m])
        legendcolor <- c(legendcolor, m)
        legendwidth <- c(legendwidth, 1)
        legendpattern <- c(legendpattern, 2)
      }
    } else {
    # PLOTTING NET BENEFIT IF REQUESTED
    
      # initialize the legend label, color, and width using the standard specs of the none and all lines
      legendlabel <- c("None", "All")
      legendcolor <- c(17, 8)
      legendwidth <- c(2, 2)
      legendpattern <- c(1, 1)
      
      #getting maximum net benefit
      ymax=max(nb[names(nb)!="threshold"],na.rm = TRUE)
      
      # inializing new benfit plot with treat all option
      plot(x=nb$threshold, y=nb$all, type="l", col=8, lwd=2 ,xlim=c(xstart, xstop), ylim=c(ymin, ymax), xlab="Threshold probability", ylab="Net benefit")
      # adding treat none option
      lines(x=nb$threshold, y=nb$none,lwd=2)
      #PLOTTING net benefit FOR EACH PREDICTOR
      for(m in 1:pred.n) {
        if (smooth==TRUE){
          lines(nb$threshold,data.matrix(nb[paste(predictors[m],"_sm",sep="")]),col=m,lty=2) 
        } else {
          lines(nb$threshold,data.matrix(nb[predictors[m]]),col=m,lty=2)
        }
        # adding each model to the legend
        legendlabel <- c(legendlabel, predictors[m])
        legendcolor <- c(legendcolor, m)
        legendwidth <- c(legendwidth, 1)
        legendpattern <- c(legendpattern, 2)
      }
    }
    # then add the legend
    legend("topright", legendlabel, cex=0.8, col=legendcolor, lwd=legendwidth, lty=legendpattern)
    
  }
  
  #RETURNING RESULTS
  results=list() 
  results$N=N
  results$predictors=data.frame(cbind(predictors,harm,probability))
  names(results$predictors)=c("predictor","harm.applied","probability")
  results$interventions.avoided.per=interventionper
  results$net.benefit=nb
  results$interventions.avoided=interv
  
  return(results)
              
}  
 

相关文章

网友评论

    本文标题:R语言超详细Logistic回归模型进行临床决策曲线绘制(DCA

    本文链接:https://www.haomeiwen.com/subject/uwhxpktx.html