Yuchen Wang, PhD: No relevant disclosure to display
Mathematical and Computational Sciences (MCS) SIG Presentation The automation of the analysis and reporting of common exposure response analysis can accelerate drug development. PoissonERM is an open-source R package that performs a full exposure–response (ER) analysis on binary outcomes, including data pre-processing, model building with covariate selection, and simulations, and generates an abbreviated report as an R markdown (Rmd) file which includes the essential analysis details with brief conclusions. PoissonERM processes the provided data set using the information from the user's control script and generates summary tables/figures for the exposure metrics, covariates, and event counts of each endpoint (each type of adverse events [AE]). After checking the incidence rate of each AE, the correlation, and missing values in each covariate, an exposure–response model is developed for each endpoint based on the provided specifications. PoissonERM has the flexibility to incorporate and compare multiple scale transformations in its modeling, select the base model and covariate model based on p-value or deviance (ΔD) as specified and predict event incidence rates using external (simulated) exposure metric data. Additionally, PoissonERM saves the cleaned data sets, models and figures as R objects, which makes it a powerful tool that not only conducts standard analysis and generates brief report but also provides users the opportunities to modify the analysis/report further.
