Bias in Area Under the Curve for Longitudinal Clinical Trials With Missing Patient Reported Outcome Data

A common approach to the analysis of longitudinal patient reportedoutcomes (PROs) is the use of summary measures such as area under the time curve (AUC).However, it is not clear how missing data affects the validity of AUC analysis. Thisstudy aimed to compare the use of AUC summary measures (in individuals) with AUC summarystatistics (on groups, calculated from the estimated parameters of a mixed model) whendata are complete, missing at random, and missing not at random. A simulation experimentbased on a two-armed randomized trial was carried out to investigate the precision andbias of AUC in longitudinal analysis where missingness, trajectory, and missingnessallocation were varied. Summary measures AUC with ad hoc approaches to missing data werecompared with mixed model AUC summary statistics. AUC summary statistics wereconsistently superior to AUC summary measures in terms of precision and bias. The biasof AUC summary statistic approach was very small, even when data were missing not atrandom and when differential attrition between groups existed. AUC summary measures onindividuals should not be used to analyze longitudinal PRO data in the presence ofmissing data