Similarity-based health risk prediction using Domain Fusion and electronic health records data.

Similarity-based health risk prediction using Domain Fusion and electronic health records data.
复制标题

DOI:
10.1016/j.jbi.2021.103711
复制
发表时间:
2021-04
影响因子:
4.5
通讯作者:
Wang S
Wang S
中科院分区:
医学3区
文献类型:
--
作者:
Guo J;Yuan C;Shang N;Zheng T;Bello NA;Kiryluk K;Weng C;Wang S

文献摘要

参考文献

被引文献

相似文献

电子健康记录(EHR)数据是对健康状况进行个性化前瞻性预测的宝贵资源。已经开发了统计方法来使用EHR数据来衡量患者的相似性,主要是使用临床属性。最近只有几种方法将临床分析与其他形式的相似性分析结合起来,目前还没有统一的框架来衡量全面的患者相似性。在这里,我们开发了一个通用的框架,称为基于域融合的患者相似度(PSDF)。PSDF分别对每个可用的领域数据进行患者相似度评估,然后将各个领域的相似度信息整合到一个综合的相似度度量中。我们使用综合的患者相似度来支持结果预测,方法是为每个患者分配一个风险分数。通过大量的模拟,我们证明了PSDF优于现有的风险预测方法,包括随机森林分类器、基于回归的模型和朴素相似方法,特别是在不同领域存在异质信号的情况下。使用从哥伦比亚大学欧文医学中心数据仓库中提取的PSDF和EHR数据,我们针对两种不同的临床结局开发了两种不同的临床预测工具:终末期肾病(ESKD)和需要瓣膜置换的严重主动脉瓣狭窄(AS)的发生病例。我们证明,我们的新预测方法可扩展到大数据集,对随机缺失具有健壮性,并可推广到不同的临床结果。
Electronic Health Record (EHR) data represents a valuable resource for individualized prospective prediction of health conditions. Statistical methods have been developed to measure patient similarity using EHR data, mostly using clinical attributes. Only a handful of recent methods have combined clinical analytics with other forms of similarity analytics, and no unified framework exists yet to measure comprehensive patient similarity. Here, we developed a generic framework named Patient similarity based on Domain Fusion (PsDF). PsDF performs patient similarity assessment on each available domain data separately, and then integrate the affinity information over various domains into a comprehensive similarity metric. We used the integrated patient similarity to support outcome prediction by assigning a risk score to each patient. With extensive simulations, we demonstrated that PsDF outperformed existing risk prediction methods including a random forest classifier, a regression-based model, and a naïve similarity method, especially when heterogeneous signals exist across different domains. Using PsDF and EHR data extracted from the data warehouse of Columbia University Irving Medical Center, we developed two different clinical prediction tools for two different clinical outcomes: incident cases of end stage kidney disease (ESKD) and severe aortic stenosis (AS) requiring valve replacement. We demonstrated that our new prediction method is scalable to large datasets, robust to random missingness, and generalizable to diverse clinical outcomes.
DOI: 10.13063/2327-9214.1035
发表时间: 2013
期刊: EGEMS (Washington, DC)
影响因子: --
作者:
Wells BJ;Chagin KM;Nowacki AS;Kattan MW
通讯作者: Kattan MW
DOI: 10.1016/j.jbi.2019.103308
发表时间: 2019-12-01
影响因子: 4.5
作者:
Chen, Xiaoyi;Garcelon, Nicolas;Burgun, Anita
通讯作者: Burgun, Anita
跨国评估方程的准确性预测肾衰竭风险:一项荟萃分析。
DOI: 10.1001/jama.2015.18202
发表时间: 2016-01-12
期刊: JAMA
影响因子: --
作者:
Tangri N;Grams ME;Levey AS;Coresh J;Appel LJ;Astor BC;Chodick G;Collins AJ;Djurdjev O;Elley CR;Evans M;Garg AX;Hallan SI;Inker LA;Ito S;Jee SH;Kovesdy CP;Kronenberg F;Heerspink HJ;Marks A;Nadkarni GN;Navaneethan SD;Nelson RG;Titze S;Sarnak MJ;Stengel B;Woodward M;Iseki K;CKD Prognosis Consortium
通讯作者: CKD Prognosis Consortium
DOI: 10.1371/journal.pcbi.1002141
发表时间: 2011-08
影响因子: 4.3
作者:
Roque FS;Jensen PB;Schmock H;Dalgaard M;Andreatta M;Hansen T;Søeby K;Bredkjær S;Juul A;Werge T;Jensen LJ;Brunak S
通讯作者: Brunak S
DOI: 10.1038/srep26094
发表时间: 2016-05-17
期刊: Scientific reports
影响因子: 4.6
作者:
Miotto R;Li L;Kidd BA;Dudley JT
通讯作者: Dudley JT