Enabling personalized decision support with patient-generated data and attributable components.

Enabling personalized decision support with patient-generated data and attributable components.
复制标题

DOI:
10.1016/j.jbi.2020.103639
复制
发表时间:
2021-01
影响因子:
4.5
通讯作者:
Albers DJ
Albers DJ
中科院分区:
医学3区
文献类型:
--
作者:
Mitchell EG;Tabak EG;Levine ME;Mamykina L;Albers DJ

文献摘要

参考文献

被引文献

相似文献

与健康有关的决策是复杂的。机器学习(ML)和患者生成的数据可以识别个体层面的模式和见解,人类认知福尔斯在这方面有所欠缺,但并非所有ML生成的信息都具有做出健康相关决策的同等效用。我们开发并应用归因成分分析(ACA),一种受最佳运输理论启发的方法,对2型糖尿病自我监测数据进行分析,以确定营养和血糖控制之间的关联模式。与线性回归相比,我们发现ACA提供了许多特性,使其有希望用于决策支持应用程序。例如,ACA能够识别非线性关系,对离群值更鲁棒,并提供更广泛和更有表现力的不确定性估计。此外,我们的研究结果突出了模型的准确性和可解释性之间的权衡,我们讨论了ML驱动的决策支持系统的影响。
Decision-making related to health is complex. Machine learning (ML) and patient generated data can identify patterns and insights at the individual level, where human cognition falls short, but not all ML-generated information is of equal utility for making health-related decisions. We develop and apply attributable components analysis (ACA), a method inspired by optimal transport theory, to type 2 diabetes self-monitoring data to identify patterns of association between nutrition and blood glucose control. In comparison with linear regression, we found that ACA offers a number of characteristics that make it promising for use in decision support applications. For example, ACA was able to identify non-linear relationships, was more robust to outliers, and offered broader and more expressive uncertainty estimates. In addition, our results highlight a tradeoff between model accuracy and interpretability, and we discuss implications for ML-driven decision support systems.
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: 10.2196/jmir.2430
发表时间: 2013-05-21
影响因子: 7.4
作者:
Fiordelli M;Diviani N;Schulz PJ
通讯作者: Schulz PJ
DOI: 10.1093/jamia/ocy106
发表时间: 2018-10-01
期刊: Journal of the American Medical Informatics Association : JAMIA
影响因子: --
作者:
Albers DJ;Levine ME;Stuart A;Mamykina L;Gluckman B;Hripcsak G
通讯作者: Hripcsak G
DOI: 10.1147/jrd.2017.2762218
发表时间: 2018-01-01
影响因子: 1.3
作者:
Codella, J.;Partovian, C.;Chen, C-H
通讯作者: Chen, C-H
DOI: 10.1038/s41746-018-0030-8
发表时间: 2018-06-20
影响因子: 15.2
作者:
Genes, Nicholas;Violante, Samantha;Chan, Yu-Feng Yvonne
通讯作者: Chan, Yu-Feng Yvonne