Pezoulas Vasileios C, Grigoriadis Grigorios I, Tachos Nikolaos S, Barlocco Fausto, Olivotto Iacopo, Fotiadis Dimitrios I
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:5343-5346. doi: 10.1109/EMBC44109.2020.9176567.
In-silico clinical platforms have been recently used as a new revolutionary path for virtual patients (VP) generation and further analysis, such as, drug development. Advanced individualized models have been developed to enhance flexibility and reliability of the virtual patient cohorts. This study focuses on the implementation and comparison of three different methodologies for generating virtual data for in-silico clinical trials. Towards this direction, three computational methods, namely: (i) the multivariate log-normal distribution (log- MVND), (ii) the supervised tree ensembles, and (iii) the unsupervised tree ensembles are deployed and evaluated against their performance towards the generation of high-quality virtual data using the goodness of fit (gof) and the dataset correlation matrix as performance evaluation measures. Our results reveal the dominance of the tree ensembles towards the generation of virtual data with similar distributions (gof values less than 0.2) and correlation patterns (average difference less than 0.03).
计算机模拟临床平台最近已被用作生成虚拟患者（VP）并进行进一步分析（如药物开发）的一条全新的革命性途径。已经开发出先进的个性化模型，以提高虚拟患者队列的灵活性和可靠性。本研究着重于实现和比较三种不同的方法，用于为计算机模拟临床试验生成虚拟数据。朝着这个方向，部署了三种计算方法，即：（i）多元对数正态分布（log-MVND），（ii）有监督树集成，以及（iii）无监督树集成，并使用拟合优度（gof）和数据集相关矩阵作为性能评估指标，针对它们在生成高质量虚拟数据方面的性能进行评估。我们的结果表明，树集成在生成具有相似分布（gof值小于0.2）和相关模式（平均差异小于0.03）的虚拟数据方面占主导地位。
