Outlier detection for patient monitoring and alerting.

Outlier detection for patient monitoring and alerting.
复制标题

DOI:
10.1016/j.jbi.2012.08.004
复制
发表时间:
2013-02
影响因子:
4.5
通讯作者:
Clermont, Gilles
Clermont, Gilles
中科院分区:
医学3区
文献类型:
--
作者:
Hauskrecht, Milos;Batal, Iyad;Valko, Michal;Visweswaran, Shyam;Cooper, Gregory F.;Clermont, Gilles

文献摘要

参考文献

被引文献

相似文献

我们开发和评估了一种数据驱动的方法,用于使用存储在电子健康记录(EHR)中的过去患者病例来检测异常(异常)患者管理决策。我们的假设是,与过去的患者护理相比不寻常的患者管理决定可能是由于错误,如果遇到这样的决定,生成警报是值得的。我们使用从4,486名心脏手术后患者的EHR中获得的数据和从数据中产生的222个警报的子集来评估这一假设。我们的评估是基于一个专家小组的意见。研究结果支持了我们的假设,即基于离群值的警报可以导致有希望的真实警报率。我们观察到各种患者管理行动的真实警报率从25%到66%不等,其中66%对应于最强的离群值。
We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management decisions using past patient cases stored in electronic health records (EHRs). Our hypothesis is that a patient-management decision that is unusual with respect to past patient care may be due to an error and that it is worthwhile to generate an alert if such a decision is encountered. We evaluate this hypothesis using data obtained from EHRs of 4,486 post-cardiac surgical patients and a subset of 222 alerts generated from the data. We base the evaluation on the opinions of a panel of experts. The results of the study support our hypothesis that the outlier-based alerting can lead to promising true alert rates. We observed true alert rates that ranged from 25% to 66% for a variety of patient-management actions, with 66% corresponding to the strongest outliers.
DOI: 10.1197/jamia.m1556
发表时间: 2004-11-01
影响因子: 6.4
作者:
Hsieh, TC;Kuperman, GJ;Gandhi, TK
通讯作者: Gandhi, TK
DOI: 10.1136/qhc.12.3.194
发表时间: 2003-06-01
影响因子: --
作者:
Rozich, JD;Haraden, CR;Resar, RK
通讯作者: Resar, RK
DOI: 10.1001/jama.266.20.2847
发表时间: 1991-11-27
影响因子: 120.7
作者:
CLASSEN, DC;PESTOTNIK, SL;BURKE, JP
通讯作者: BURKE, JP
DOI: 10.1109/tnn.1997.641482
发表时间: 1997-01-01
影响因子: --
作者:
Cherkassky, V
通讯作者: Cherkassky, V
DOI: 10.1136/jamia.1998.0050305
发表时间: 1998-05-01
影响因子: 6.4
作者:
Jha, AK;Kuperman, GJ;Bates, DW
通讯作者: Bates, DW