A broadly applicable approach to enrich electronic-health-record cohorts by identifying patients with complete data: a multisite evaluation.
A broadly applicable approach to enrich electronic-health-record cohorts by identifying patients with complete data: a multisite evaluation.
复制标题
DOI：
10.1093/jamia/ocad166
复制
发表时间：
2023-11-17
影响因子：
6.4
通讯作者：
Murphy, Shawn N.
中科院分区：
文献类型：
--
作者：
Klann, Jeffrey G.;Henderson, Darren W.;Morris, Michele;Estiri, Hossein;Weber, Griffin M.;Visweswaran, Shyam;Murphy, Shawn N.
关键词：
在单一医疗保健系统中接受最多护理的患者（俗称“忠诚度队列”，因为他们通常返回相同的提供者）在该组织的电子健康记录（EHR）中拥有大部分完整的数据。忠诚度队列的数据缺失率较低，这可能会无意中使研究结果产生偏差。使用常规护理和医疗保健利用指标的代理，我们计算每个患者的得分，以确定忠诚度队列。我们为广泛采用的i2b2平台实现了一个可计算程序，该平台基于机器学习模型识别EHR中的忠诚度队列，该模型先前已使用链接的索赔数据进行了验证。我们开发了一种新的验证方法，该方法仅使用EHR数据来测试患者在训练期后是否返回同一医疗系统。我们使用2017年至2019年的数据在3家机构评估了这些工具。通过忠诚队列计算确定在1年随访期间返回的患者，使用原始模型获得的受试者工作特征曲线下平均面积为0.77，在各个研究中心校准模型后为0.80。多种药物或访视等因素在所有研究中心均具有显著影响。筛选试验（例如结肠镜检查）的贡献在不同研究中心之间存在差异，可能是由于编码和人群差异。这个开源的“忠诚度评分”算法的实现具有良好的预测能力。通过利用这些低缺失患者来丰富研究队列是获得准确因果分析所需的数据完整性的一种方法。i2b2站点可以使用这种方法来选择具有大多数完整EHR数据的队列。
Patients who receive most care within a single healthcare system (colloquially called a “loyalty cohort” since they typically return to the same providers) have mostly complete data within that organization’s electronic health record (EHR). Loyalty cohorts have low data missingness, which can unintentionally bias research results. Using proxies of routine care and healthcare utilization metrics, we compute a per-patient score that identifies a loyalty cohort. We implemented a computable program for the widely adopted i2b2 platform that identifies loyalty cohorts in EHRs based on a machine-learning model, which was previously validated using linked claims data. We developed a novel validation approach, which tests, using only EHR data, whether patients returned to the same healthcare system after the training period. We evaluated these tools at 3 institutions using data from 2017 to 2019. Loyalty cohort calculations to identify patients who returned during a 1-year follow-up yielded a mean area under the receiver operating characteristic curve of 0.77 using the original model and 0.80 after calibrating the model at individual sites. Factors such as multiple medications or visits contributed significantly at all sites. Screening tests’ contributions (eg, colonoscopy) varied across sites, likely due to coding and population differences. This open-source implementation of a “loyalty score” algorithm had good predictive power. Enriching research cohorts by utilizing these low-missingness patients is a way to obtain the data completeness necessary for accurate causal analysis. i2b2 sites can use this approach to select cohorts with mostly complete EHR data.
登录
查看更多内容
影响因子：
7.4
作者：
Kohane IS;Aronow BJ;Avillach P;Beaulieu-Jones BK;Bellazzi R;Bradford RL;Brat GA;Cannataro M;Cimino JJ;García-Barrio N;Gehlenborg N;Ghassemi M;Gutiérrez-Sacristán A;Hanauer DA;Holmes JH;Hong C;Klann JG;Loh NHW;Luo Y;Mandl KD;Daniar M;Moore JH;Murphy SN;Neuraz A;Ngiam KY;Omenn GS;Palmer N;Patel LP;Pedrera-Jiménez M;Sliz P;South AM;Tan ALM;Taylor DM;Taylor BW;Torti C;Vallejos AK;Wagholikar KB;Consortium For Clinical Characterization Of COVID-19 By EHR (4CE);Weber GM;Cai T
通讯作者：
Cai T
DOI：
10.13063/2327-9214.1074
发表时间：
2014
期刊：
EGEMS (Washington, DC)
影响因子：
--
作者：
Murphy S;Wilcox A
通讯作者：
Wilcox A
DOI：
10.1056/nejmsr1809937
发表时间：
2019-08-15
期刊：
The New England journal of medicine
影响因子：
--
作者：
All of Us Research Program Investigators;Denny JC;Rutter JL;Goldstein DB;Philippakis A;Smoller JW;Jenkins G;Dishman E
通讯作者：
Dishman E
影响因子：
4
作者：
Gianfrancesco MA;Goldstein ND
通讯作者：
Goldstein ND
影响因子：
15.2
作者：
Brat, Gabriel A.;Weber, Griffin M.;Kohane, Isaac S.
通讯作者：
Kohane, Isaac S.