Random control selection for conducting high‐throughput adverse drug events screening using large‐scale longitudinal health data

Abstract

Case-control design based high-throughput pharmacoinformatics study using large-scale longitudinal health data is able to detect new adverse drug events (ADEs) signals. Existing control selection approaches for case-control design including dynamic/super control selection approach. Dynamic/super control selection approach requires all individuals to be evaluated at all ADE case index dates, as the individuals' eligibilities as control depend on ADE/enrolment history. Thus, using large-scale longitudinal health data, dynamic/super control selection approach requires extraordinarly high computational time. We proposed a random control selection approach in which ADE case index dates were matched by randomly generated control index dates. Random control selection approach doesn't depend on ADE/enrolment history. It is able to significantly reduce computational time to prepare case-control data sets, as it requires all individuals to be evaluated only once. We compared the performance metrics of all control selection approaches using two large-scale longitudinal health data and a drug-ADE gold standard including 399 drug-ADE pairs. The F-scores for random control selection approach were between 0.586 -0.600 compared to between 0.545 -0.562 for dynamic/super control selection approaches. Random control selection approach was approximately 1,000 times faster than dynamic/super control selection approach on preparing case-control data sets. With large-scale longitudinal health data, case-control design based pharmacoinformatics study using random control selection is able to generate comparable ADE signals than the existing control selection approaches. Random control selection approach also significantly reduces computational time to prepare the case-control data sets.