arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.08970cs.LGstat.ML
收藏

多任务时间序列分析在药物反应建模中的应用

Multi-Task Time Series Analysis applied to Drug Response Modelling

University of Edinburgh(爱丁堡大学);The Alan Turing Institute(艾伦·图灵研究所);NHS Greater Glasgow and Clyde(英国国家医疗服务体系大格拉斯哥和克莱德分部)

Alex Bird, Christopher K. I. Williams, Christopher Hawthorne

摘要:

时间序列模型(如动态系统)经常被拟合到一组数据中,忽略了个体实体(如患者)之间的变化。在本文中,我们将展示如何通过使用多任务学习(MTL)将这些模型个性化到个人水平,同时保留统计能力。据我们所知,这是一个新的发展MTL适用于时间序列和无控制输入。的建模框架上表现出的生理药物反应的问题,从而提高了预测精度和不确定性估计超过现有的国家的最先进的模型。

英文摘要:

Time series models such as dynamical systems are frequently fitted to a cohort of data, ignoring variation between individual entities such as patients. In this paper we show how these models can be personalised to an individual level while retaining statistical power, via use of multi-task learning (MTL). To our knowledge this is a novel development of MTL which applies to time series both with and without control inputs. The modelling framework is demonstrated on a physiological drug response problem which results in improved predictive accuracy and uncertainty estimation over existing state-of-the-art models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑