ipro2动态血糖监测的原始数据提取与处理

读取原始数据

• 原始数据开始的12行是需要删去的，用 readLines 即删去24行。
• 这里只提取了监测血糖的读数和指尖血糖的读数。
• 所用缺失值都被删去，不进行 impute。

ReadRawFile <- function(id){
  lines =  readLines(paste("E:/direction/to/rawdata",id,".csv",sep = ""),encoding = "utf-16",skipNul = TRUE)
  # data begin from 24(12)lines, 24 in readLines and 12 in read.table
  lines = lines[23:length(lines)]
  lines = gsub("\"","",lines)
  data = read.table(text = lines,sep = '\t',quote = "",header = 1)
  data = checkAndRename('Timestamp','time',data)
  data = checkAndRename('Sensor.Glucose..mmol.L.','sgReading',data)
  data = checkAndRename('BG.Reading..mmol.L.','bgReading',data)
  ix = which(data[,"Excluded"]!="TRUE")
  data = data[ix,]
  cols=c('time','sgReading')
  data = data[,cols]
  data = data[which(!is.na(data$sgReading)),]
  return(data)
}

checkAndRename <- function(oldname,newname,data){
  ixT =  which(colnames(data)==oldname)
  if (length(ixT)==0){
    stop(paste("Column missing from input file:",oldname),call.=FALSE)
  }
  colnames(data)[ixT] = newname
  return(data)
}

分离每一天的数据和时间段

• 主要通过对每一天打上 tag 来实现
• 同理对每一个时间段打上 tag 可以区分时间段

getDays <- function(rawData){
  startDate = as.Date(rawData$time[1])
  for (i in 1:nrow(rawData)){
    currentDate = as.Date(rawData$time[i])
    dif = as.numeric(currentDate - startDate)
    rawData$dayIdx[i] = dif + 1
    #04:00-07:00这段时间的平均血糖定义为空腹血糖
    fastingStart = as.POSIXlt(paste(as.character(currentDate),"04:00:00"))
    fastingEnd = as.POSIXlt(paste(as.character(currentDate),"07:00:00"))
    #07:00-22：00用来评估餐后血糖
    PPEnd = as.POSIXlt(paste(as.character(currentDate),"22:00:00"))
    #00:00-07:00定义为夜间血糖
    NightStart = as.POSIXlt(paste(as.character(currentDate),"00:00:00"))
    currentTime = as.POSIXlt(rawData$time[i])
    if (currentTime>=fastingStart & currentTime<=fastingEnd) rawData$isFasting[i]=1 else rawData$isFasting[i]=0
    if (currentTime>=fastingEnd & currentTime<=PPEnd) rawData$PP[i]=1 else rawData$PP[i]=0
    if (currentTime>=NightStart & currentTime<=fastingEnd) rawData$atNight[i]=1 else rawData$atNight[i]=0
  }

  return(rawData)
}

取得某一天的血糖数据

• 因为不想对缺失值进行 impute，忽略没有完整数据的一天（即读数没有288个）。
• idlist 是一个包含所有需要提取某一天的数据 id 的 list
• Idx 即使这天的index，第一天就是1，第二天就是2。

getDayGlucose <- function(idlist,Idx){
  sgReading_dt=data.frame(timepoint=1:288)
  for (i in 1:length(idlist)){
    rawData=ReadRawFile(idlist[i])
    rawData=getDays(rawData)
    rawData_Day=rawData[which(rawData$dayIdx==Idx),"sgReading"]
    if (length(rawData_Day)==288) {
      sgReading_dt=cbind(sgReading_dt,rawData_Day) 
    } else {
      rawData_Day=rep(NA,times=288)
      sgReading_dt=cbind(sgReading_dt,rawData_Day)
  }
  }
  sgReading_dt=t(data.frame(sgReading_dt,row.names = 1))
  sgReading_dt=cbind(idlist,sgReading_dt)
}

计算曲线下面积

calculateAUC <- function(rawData, baseline){
  aucValue = 0
  rawData_High=rawData[which(rawData$sgReading>baseline),]
  for (idx in 2:nrow(rawData_High)){
    timeDiff = as.numeric(difftime(rawData_High$time[idx],rawData_High$time[idx-1],units = "mins"))
    if(timeDiff == 5){
      trapezoid = (rawData_High$sgReading[idx] + rawData_High$sgReading[idx-1]) * timeDiff* 0.5
      
    } else trapezoid=0
    aucValue = aucValue + trapezoid
  }
  return(aucValue)
}

参考文献

Software application profile: GLU: A tool for analysing continuously measured glucose in epidemiology