## Winter 2018: HS 853

#### Homework 2

Problem 2.1: Use the University of Queensland Vital Signs Dataset data to do some QC charts and vital sign monitoring for several patients (e.g., cases 1, 3, 4). Some cases are available here. Filenames “UQ_VitalSignsData_Case0#.csv” (where “#” is a number indexing the case).
• Generate some (clinically relevant) plots of the data.
• Use Control Charts to identify possible critical time-points (events).

Note:
``` VitalData <- read.csv('https://umich.instructure.com/files/366336/download?download_frd=1',as.is=T, header=T) VitalData\$Time <- gsub("_", ".", VitalData\$Time) # replace the “_” with “.” In the Time to indicate milliseconds head(strptime(VitalData\$Time, "%H:%M:%OS")) library("reshape2"); library("ggplot2") VitalData_long <- melt(VitalData, id.vars="Time", # The source columns measure.vars=c("SpO2", "CO2", "ECG", "AWF", "inO2", "Pulse", "Pleth", "NBP_.Mean.", "awRR", "MAC", "Minute_Volume", "inN2O", "imCO2"), # Name of the destination column that will identify the original # column that the measurement came from variable.name="Feature", value.name="Measurement") # convert to long format ggplot(data=VitalData_long, aes(x=strptime(VitalData_long\$Time, "%H:%M:%OS"), y=Measurement, colour=Feature)) + geom_line() ```
Problem 2.2: Fit in a mixed effects model to the lung cancer data. Determine several covariates of clinical interest and interpret your findings in terms of the specific measures/results.

SOCR Resource Visitor number