Mining Primary Care Electronic Health Records for Automatic Disease Phenotyping: A Transparent Machine Learning Framework.

Mining Primary Care Electronic Health Records for Automatic Disease Phenotyping: A Transparent Machine Learning Framework.
复制标题

DOI:
10.3390/diagnostics11101908
复制
发表时间:
2021-10-15
期刊:
Diagnostics (Basel, Switzerland)
影响因子:
--
通讯作者:
Zhou SM
Zhou SM
中科院分区:
其他
文献类型:
--
作者:
Fernández-Gutiérrez F;Kennedy JI;Cooksey R;Atkinson M;Choy E;Brophy S;Huo L;Zhou SM

文献摘要

参考文献

被引文献

相似文献

(1) 背景:我们的目标是开发一个透明的机器学习 (ML) 框架,通过一组简约的功能自动识别电子健康记录 (EHR) 中患有某种疾病的患者。 (2) 方法:我们链接了多个来源的 EHR,包括 2002 年至 2012 年间的 917,496,869 条初级保健记录和 40,656,805 条二级保健记录以及 694,954 条专科手术记录,以生成一个独特的数据集。然后,我们将患者识别视为文本分类问题,并提出了一个透明的疾病表型框架。该框架包括一代患者表示、特征选择和最佳表型算法开发,以解决数据的不平衡性质。通过识别类风湿关节炎(RA)和强直性脊柱炎(AS)对该框架进行了广泛评估。 (3)结果:应用于9657例患者(其中1484例类风湿性关节炎(RA)和204例强直性脊柱炎(AS))的关联数据集,该框架对RA的准确率和阳性预测值分别为86.19%和88.46%,对AS的准确度和阳性预测值分别为99.23%和97.75%,与专家知识驱动的方法相当。 (4) 结论:该框架有可能成为一种有效的工具,用于从 EHR 中识别出感兴趣的患者,帮助临床医生进行临床决策支持过程。
(1) Background: We aimed to develop a transparent machine-learning (ML) framework to automatically identify patients with a condition from electronic health records (EHRs) via a parsimonious set of features. (2) Methods: We linked multiple sources of EHRs, including 917,496,869 primary care records and 40,656,805 secondary care records and 694,954 records from specialist surgeries between 2002 and 2012, to generate a unique dataset. Then, we treated patient identification as a problem of text classification and proposed a transparent disease-phenotyping framework. This framework comprises a generation of patient representation, feature selection, and optimal phenotyping algorithm development to tackle the imbalanced nature of the data. This framework was extensively evaluated by identifying rheumatoid arthritis (RA) and ankylosing spondylitis (AS). (3) Results: Being applied to the linked dataset of 9657 patients with 1484 cases of rheumatoid arthritis (RA) and 204 cases of ankylosing spondylitis (AS), this framework achieved accuracy and positive predictive values of 86.19% and 88.46%, respectively, for RA and 99.23% and 97.75% for AS, comparable with expert knowledge-driven methods. (4) Conclusions: This framework could potentially be used as an efficient tool for identifying patients with a condition of interest from EHRs, helping clinicians in clinical decision-support process.
DOI: 10.1038/s41746-021-00438-z
发表时间: 2021-04-07
影响因子: 15.2
作者:
Aggarwal R;Sounderajah V;Martin G;Ting DSW;Karthikesalingam A;King D;Ashrafian H;Darzi A
通讯作者: Darzi A
DOI: 10.1136/amiajnl-2013-001935
发表时间: 2014-03
期刊: Journal of the American Medical Informatics Association : JAMIA
影响因子: --
作者:
Shivade C;Raghavan P;Fosler-Lussier E;Embi PJ;Elhadad N;Johnson SB;Lai AM
通讯作者: Lai AM
DOI: 10.1186/1472-6947-9-3
发表时间: 2009-01-16
影响因子: 3.5
作者:
Lyons RA;Jones KH;John G;Brooks CJ;Verplancke JP;Ford DV;Brown G;Leake K
通讯作者: Leake K
DOI: 10.3399/bjgp16x683965
发表时间: 2016-03-01
影响因子: 5.9
作者:
Looijmans-Van den Akker, Ingrid;van Luijn, Karen;Verheij, Theo
通讯作者: Verheij, Theo
DOI: 10.1002/wics.1278
发表时间: 2013-11-01
影响因子: 3.2
作者:
de Ville, Barry
通讯作者: de Ville, Barry