Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype.

Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype.
复制标题

DOI:
10.1093/jamia/ocy106
复制
发表时间:
2018-10-01
期刊:
Journal of the American Medical Informatics Association : JAMIA
影响因子:
--
通讯作者:
Hripcsak G
Hripcsak G
中科院分区:
其他
文献类型:
--
作者:
Albers DJ;Levine ME;Stuart A;Mamykina L;Gluckman B;Hripcsak G

文献摘要

参考文献

被引文献

相似文献

我们引入数据同化作为一种计算方法,它使用机器学习将数据与人类知识以机械模型的形式结合起来,以便预测未来状态,通过平滑来估计过去丢失的数据,并推断代表临床和科学重要表型的可测量和不可测量的量。我们通过展示数据同化如何被用来预测未来的血糖值,计算以前丢失的血糖值,以及推断2型糖尿病的表型,展示了它在2型糖尿病背景下所提供的优势。数据同化的核心是机械模型,这里是内分泌模型。这类模型的复杂程度各不相同,包含关于控制系统的重要机制(例如,营养对血糖的影响)的可检验假设,因此限制了模型空间,允许使用非常少的数据进行准确的估计。
We introduce data assimilation as a computational method that uses machine learning to combine data with human knowledge in the form of mechanistic models in order to forecast future states, to impute missing data from the past by smoothing, and to infer measurable and unmeasurable quantities that represent clinically and scientifically important phenotypes. We demonstrate the advantages it affords in the context of type 2 diabetes by showing how data assimilation can be used to forecast future glucose values, to impute previously missing glucose values, and to infer type 2 diabetes phenotypes. At the heart of data assimilation is the mechanistic model, here an endocrine model. Such models can vary in complexity, contain testable hypotheses about important mechanics that govern the system (eg, nutrition’s effect on glucose), and, as such, constrain the model space, allowing for accurate estimation using very little data.
DOI: 10.1371/journal.pone.0096443
发表时间: 2014
期刊: PloS one
影响因子: 3.7
作者:
Albers DJ;Elhadad N;Tabak E;Perotte A;Hripcsak G
通讯作者: Hripcsak G
DOI: 10.1080/01621459.2012.713876
发表时间: 2012
影响因子: 3.7
作者:
通讯作者: --
DOI: 10.1208/aapsj070237
发表时间: 2005-10-05
期刊: The AAPS journal
影响因子: --
作者:
Bonate, Peter L
通讯作者: Bonate, Peter L
DOI: 10.1029/2005jd006021
发表时间: 2006-04-22
影响因子: 4.4
作者:
Gove, JH;Hollinger, DY
通讯作者: Hollinger, DY
DOI: 10.1371/journal.pcbi.1005232
发表时间: 2017-04
影响因子: 4.3
作者:
Albers DJ;Levine M;Gluckman B;Ginsberg H;Hripcsak G;Mamykina L
通讯作者: Mamykina L