RCTrep: An R Package for the Validation of Estimates of Average Treatment Effects

Abstract

Despite the recent development of numerous methods aiming to estimate individual-level treatment effects based on observational data, understanding the validity of these estimates remains challenging. Often it is unclear whether the observational data meet the assumptions imposed by the method. Additionally, there is often large flexibility in model choice when implementing a given method. We present the R package RCTrep designed to make it easy to compare and validate estimates of (conditional) average treatment effects obtained using observational data by a) making it easy to obtain and visualize estimates derived using a large variety of methods, and b) ensuring that estimates are easily compared to a gold standard (i.e., estimates derived from randomized controlled trials). RCTrep offers a generic protocol for treatment effect validation based on four simple steps, namely, set-selection, estimation, diagnosis, and validation. The package provides a simple dashboard to review the obtained results. This article presents design of RCTrep and serves as a user guide for researchers aiming to leverage the potential of observational data.

Value of Real-World Evidence for Treatment Selection: A Case Study in Colon Cancer

“…55 In the future, an RWE-based decision tree for the elderly patients can be constructed using a patient-tailored threshold. 57 Moreover, our method is generalizable for evaluating and developing guidelines in other disease areas. Using an RWE-based decision tree constructed by our method, two types of information can be derived: (1) subgroups for whom ACT is not deemed beneficial on average, and (2) the uncertainty of effect size of subgroups.…”

LRRK2G2019S variant is associated with transcriptional changes in Parkinson’s disease human myeloid cells under proinflammatory environment

“…To do that, we studied differences between samples treated with LPS or IFNγ in comparison to untreated samples, without considering genotype. After extensive quality control measures, we observed both proinflammatory stimuli induced a large change in the number of differentially expressed genes (DEGs) when compared to untreated samples (5955 for LPS and 7856 for IFNγ at FDR < 0.05; Supplementary tables 2 and 3), with a significant association of DEGs between both conditions (p-value = 2.2e-138, Odds ratio = 2.6, overlap tested using Fisher's exact test) 32 (Fig. 1C).…”