Key points are not available for this paper at this time.
Abstract Purpose Research on rare diseases and atypical healthcare demographics is often slowed by high inter-subject heterogeneity and overall scarcity of data. Synthetic data (SD) has been proposed as means for data sharing, enlargement, and diversification, by artificially generating ‘real’ phenomena while obscuring the ‘real’ subject data. The utility of SD is actively scrutinised in healthcare research, but the role of sample size for actionability of SD is insufficiently explored. We aim to understand the interplay of actionability and sample size by generating SD sets of varying sizes from gradually diminishing amounts of real subjects’ data. We evaluate the actionability of SD in a highly heterogeneous and rare demographic: adolescents and young adults (AYAs) with cancer. Methodology A population-based cross-sectional cohort study of 3735 AYAs was sub-sampled at random to produce 13 training datasets of varying sample sizes. We studied four distinct generator architectures built on the open-source Synthetic Data Vault library. Each architecture was used to generate SD of varying sizes based on each aforementioned training subsets. SD actionability was assessed by comparing the resulting SD to its respective ‘real’ data against three metrics – veracity, utility, and privacy concealment. Results All examined generator architectures yielded actionable data when generating SD with sizes similar to the ‘real’ data. Large SD sample size increased veracity but generally increased privacy risks. Using fewer training subjects led to faster convergence in veracity, but partially exacerbated privacy concealment issues. Conclusion SD is a potentially promising option for data sharing and data augmentation, yet sample size plays a significant role in its actionability. SD generation should go hand-in-hand with consistent scrutiny and sample size should be carefully considered in this process.
Hogenboom et al. (Wed,) studied this question.