Muniz-Terrera Graciela, Mendelevitch Ofer, Barnes Rodrigo, Lesh Michael D
Edinburgh Dementia Prevention Group, University of Edinburgh, Edinburgh, United Kingdom.
Syntegra, San Carlos, CA, United States.
Front Artif Intell. 2021 May 17;4:613956. doi: 10.3389/frai.2021.613956. eCollection 2021.
When attempting to answer questions of interest, scientists often encounter hurdles that may stem from limited access to existing adequate datasets as a consequence of poor data sharing practices, constraining administrative practices. Further, when attempting to integrate data, differences in existing datasets also impose challenges that limit opportunities for data integration. As a result, the pace of scientific advancements is suboptimal. Synthetic data and virtual cohorts generated using innovative computational techniques represent an opportunity to overcome some of these limitations and consequently, to advance scientific developments. In this paper, we demonstrate the use of virtual cohorts techniques to generate a synthetic dataset that mirrors a deeply phenotyped sample of preclinical dementia research participants.
在试图回答感兴趣的问题时，科学家们常常遇到障碍，这些障碍可能源于数据共享实践不佳、行政限制等导致对现有充足数据集的获取受限。此外，在尝试整合数据时，现有数据集的差异也带来了限制数据整合机会的挑战。因此，科学进步的步伐并不理想。使用创新计算技术生成的合成数据和虚拟队列代表了克服其中一些限制从而推动科学发展的机会。在本文中，我们展示了使用虚拟队列技术生成一个合成数据集，该数据集反映了临床前痴呆症研究参与者的深度表型样本。
