Longitudinal K-means approaches to clustering and analyzing EHR opioid use trajectories for clinical subtypes.

Longitudinal K-means approaches to clustering and analyzing EHR opioid use trajectories for clinical subtypes.
复制标题

DOI:
10.1016/j.jbi.2021.103889
复制
发表时间:
2021-10
影响因子:
4.5
通讯作者:
Elkin, Peter L.
Elkin, Peter L.
中科院分区:
医学3区
文献类型:
--
作者:
Mullin, Sarah;Zola, Jaroslaw;Lee, Robert;Hu, Jinwei;MacKenzie, Brianne;Brickman, Arlen;Anaya, Gabriel;Sinha, Shyamashree;Li, Angie;Elkin, Peter L.

文献摘要

参考文献

被引文献

相似文献

从回顾性电子健康记录 (EHR) 数据中识别患者亚型充满了固有的建模问题,例如数据缺失和时间间隔长度可变,并且获得的结果高度依赖于数据预处理策略。随着我们走向个性化医疗,评估准确的患者亚型将成为制定患者特定治疗计划的关键因素。将纵向轨迹从不规则间隔和可变长度的时间间隔中划分出来是一个既定但尚未解决的问题。在这项工作中,我们提出并比较了用于根据 EHR 数据对阿片类药物使用轨迹进行子分类的 k 均值方法。然后,我们使用决策树解释产生的亚型,检查每种亚型如何受到阿片类药物特征以及患者诊断、手术和人口统计的影响。最后,我们讨论如何将这些亚型纳入静态机器学习模型中,以提高其预测阿片类药物过量和不良事件的性能。所提出的方法是通用的,并且可以扩展到其他 EHR 处方剂量轨迹。
Identification of patient subtypes from retrospective Electronic Health Record (EHR) data is fraught with inherent modeling issues, such as missing data and variable length time intervals, and the results obtained are highly dependent on data pre-processing strategies. As we move towards personalized medicine, assessing accurate patient subtypes will be a key factor in creating patient specific treatment plans. Partitioning longitudinal trajectories from irregularly spaced and variable length time intervals is a well-established, but open problem. In this work, we present and compare k-means approaches for subtyping opioid use trajectories from EHR data. We then interpret the resulting subtypes using decision trees, examining how each subtype is influenced by opioid medication features and patient diagnoses, procedures, and demographics. Finally, we discuss how the subtypes can be incorporated in static machine learning models to improve their performance in predicting opioid overdose and adverse events. The proposed methods are general, and can be extended to other EHR prescription dosage trajectories.
DOI: 10.1016/j.patcog.2015.05.006
发表时间: 2015-11-01
影响因子: 8
作者:
Jing, Liping;Tian, Kuang;Huang, Joshua Z.
通讯作者: Huang, Joshua Z.
DOI: 10.1371/journal.pone.0222677
发表时间: 2019-10-04
期刊: PLOS ONE
影响因子: 3.7
作者:
Elmer, Jonathan;Fogliato, Riccardo;Nagin, Daniel
通讯作者: Nagin, Daniel
DOI: 10.1016/j.drugpo.2017.05.039
发表时间: 2017-08-01
影响因子: 4.4
作者:
Kelty, Erin;Hulse, Gary
通讯作者: Hulse, Gary
DOI: 10.15585/mmwr.rr6501e1
发表时间: 2016-03-18
影响因子: 33.7
作者:
Dowell, Deborah;Haegerich, Tamara M.;Chou, Roger
通讯作者: Chou, Roger
DOI: 10.1186/1472-6947-11-51
发表时间: 2011-07-29
影响因子: 3.5
作者:
Khalilia, Mohammed;Chakraborty, Sounak;Popescu, Mihail
通讯作者: Popescu, Mihail