Predictive models for pressure ulcers from intensive care unit electronic health records using Bayesian networks.
Predictive models for pressure ulcers from intensive care unit electronic health records using Bayesian networks.
复制标题
DOI：
10.1186/s12911-017-0471-z
复制
发表时间：
2017-07-05
影响因子：
3.5
通讯作者：
Machiraju R
中科院分区：
文献类型：
--
作者：
Kaewprag P;Newton C;Vermillion B;Hyun S;Huang K;Machiraju R
我们开发了预测模型，使临床医生能够更好地了解和探索患者的临床数据以及来自电子健康记录数据的重症监护病房患者压疮的风险因素。准确识别压疮的危险因素对于确定适当的预防策略至关重要；在这项工作中，我们将药物治疗、诊断和传统的Braden压疮评估量表测量作为患者的特征。为了更好地预测压疮的发生率，更好地了解相关危险因素的结构，我们根据患者的特征构建了贝叶斯网络。利用统计网络技术简化贝叶斯网络节点(特征)和边(条件依赖)。在回顾我们模型的网络可视化后，我们的临床医生合作者能够识别出被广泛认为与压疮相关的危险因素之间的强烈关系。我们提出了一个用于患者临床数据预测分析的三阶段框架：1)在临床医生的帮助下开发电子健康记录特征提取功能，2)简化特征，3)建立贝叶斯网络预测模型。我们从不同的搜索算法、评分函数、先验结构初始化和特征集来评估贝叶斯网络模型的所有组合。从7,717名ICU患者的电子病历中，我们根据86种药物、诊断和Braden量表特征构建了贝叶斯网络预测模型。我们的模型不仅识别已知和怀疑的高PU风险因素，而且大大提高了预测的敏感性-与逻辑回归模型相比高出近三倍-而不牺牲总体准确性。我们设想了一个具有代表性的模型，通过该模型，我们的临床医生合作者确定了被广泛认为与压疮相关的风险因素之间的强烈关系。鉴于压疮对患者的强烈不良影响和治疗压疮的高昂成本，我们基于贝叶斯网络的模型提供了一种新的框架，可以显著提高预测模型的灵敏度。因此，当该模型被部署到临床环境中时，照顾者可以适当地对可能与压疮发生率相关的情况做出反应。
We develop predictive models enabling clinicians to better understand and explore patient clinical data along with risk factors for pressure ulcers in intensive care unit patients from electronic health record data. Identifying accurate risk factors of pressure ulcers is essential to determining appropriate prevention strategies; in this work we examine medication, diagnosis, and traditional Braden pressure ulcer assessment scale measurements as patient features. In order to predict pressure ulcer incidence and better understand the structure of related risk factors, we construct Bayesian networks from patient features. Bayesian network nodes (features) and edges (conditional dependencies) are simplified with statistical network techniques. Upon reviewing a network visualization of our model, our clinician collaborators were able to identify strong relationships between risk factors widely recognized as associated with pressure ulcers. We present a three-stage framework for predictive analysis of patient clinical data: 1) Developing electronic health record feature extraction functions with assistance of clinicians, 2) simplifying features, and 3) building Bayesian network predictive models. We evaluate all combinations of Bayesian network models from different search algorithms, scoring functions, prior structure initializations, and sets of features. From the EHRs of 7,717 ICU patients, we construct Bayesian network predictive models from 86 medication, diagnosis, and Braden scale features. Our model not only identifies known and suspected high PU risk factors, but also substantially increases sensitivity of the prediction - nearly three times higher comparing to logistical regression models - without sacrificing the overall accuracy. We visualize a representative model with which our clinician collaborators identify strong relationships between risk factors widely recognized as associated with pressure ulcers. Given the strong adverse effect of pressure ulcers on patients and the high cost for treating pressure ulcers, our Bayesian network based model provides a novel framework for significantly improving the sensitivity of the prediction model. Thus, when the model is deployed in a clinical setting, the caregivers can suitably respond to conditions likely associated with pressure ulcer incidence.
登录
查看更多内容
影响因子：
4.2
作者：
Kaitani, Toshiko;Tokunaga, Keiko;Sanada, Hiromi
通讯作者：
Sanada, Hiromi
影响因子：
9
作者：
Jugun, Kheeldass;Richard, Jean-Christophe;Uckay, Ilker
通讯作者：
Uckay, Ilker
DOI：
10.1016/j.apmr.2016.01.003
发表时间：
2016-10-01
影响因子：
4.3
作者：
Krishnan, Shilpa;Karg, Patricia E.;Brienza, David M.
通讯作者：
Brienza, David M.
影响因子：
38.9
作者：
Bours, GJJW;De Laat, E;Lubbers, M
通讯作者：
Lubbers, M
影响因子：
3.7
作者：
Kunkle BW;Yoo C;Roy D
通讯作者：
Roy D