An independently validated, portable algorithm for the rapid identification of COPD patients using electronic health records.
An independently validated, portable algorithm for the rapid identification of COPD patients using electronic health records.
复制标题
一种独立验证的便携式算法，用于使用电子健康记录快速识别COPD患者。
DOI：
10.1038/s41598-021-98719-w
复制
发表时间：
2021-10-07
影响因子：
4.6
通讯作者：
Karlson E
中科院分区：
文献类型：
--
作者：
Chu SH;Wan ES;Cho MH;Goryachev S;Gainer V;Linneman J;Scotty EJ;Hebbring SJ;Murphy S;Lasky-Su J;Weiss ST;Smoller JW;Karlson E
电子健康记录（EHR）为开展大型、经济高效、基于人群的研究提供了前所未有的机会。然而，异质性疾病的研究，如慢性阻塞性肺疾病（COPD），往往需要劳动密集型的临床审查和测试，限制了这些重要资源的广泛使用。为了开发一种用于准确识别EHR中大型COPD队列的可推广且有效的方法，从符合Mass General Brigham Biobank中纳入标准的3420名参与者中开发了COPD数据集市。选择训练和测试集，并使用从肺病学家的图表审查中获得的金标准COPD分类进行标记。通过弹性网络回归，利用结构化（例如ICD代码）和非结构化（例如医疗记录）数据构建了多类算法。明确包括和排除肺功能的模型进行了比较。最终算法的外部验证在具有不同EHR系统的独立生物库中进行。最终的COPD分类模型表现出极好的阳性预测值（PPV; 91.7%）、灵敏度（71.7%）和特异性（94.4%）。该算法不仅在MGBB中表现良好，而且在独立生物库中表现出相似或改进的分类性能（PPV 93.5%，灵敏度61.4%，特异性90%）。辅助比较显示，包含FEV 1/FVC二元特征的分类模型产生的灵敏度显著高于不包含二元特征的分类模型。这项研究填补了COPD研究中的一个空白，涉及基于人群的EHR，为COPD病例的快速自动分类提供了一个重要的资源，既具有成本效益，又需要来自非结构化病历的最少信息。
Electronic health records (EHR) provide an unprecedented opportunity to conduct large, cost-efficient, population-based studies. However, the studies of heterogeneous diseases, such as chronic obstructive pulmonary disease (COPD), often require labor-intensive clinical review and testing, limiting widespread use of these important resources. To develop a generalizable and efficient method for accurate identification of large COPD cohorts in EHRs, a COPD datamart was developed from 3420 participants meeting inclusion criteria in the Mass General Brigham Biobank. Training and test sets were selected and labeled with gold-standard COPD classifications obtained from chart review by pulmonologists. Multiple classes of algorithms were built utilizing both structured (e.g. ICD codes) and unstructured (e.g. medical notes) data via elastic net regression. Models explicitly including and excluding spirometry features were compared. External validation of the final algorithm was conducted in an independent biobank with a different EHR system. The final COPD classification model demonstrated excellent positive predictive value (PPV; 91.7%), sensitivity (71.7%), and specificity (94.4%). This algorithm performed well not only within the MGBB, but also demonstrated similar or improved classification performance in an independent biobank (PPV 93.5%, sensitivity 61.4%, specificity 90%). Ancillary comparisons showed that the classification model built including a binary feature for FEV1/FVC produced substantially higher sensitivity than those excluding. This study fills a gap in COPD research involving population-based EHRs, providing an important resource for the rapid, automated classification of COPD cases that is both cost-efficient and requires minimal information from unstructured medical records.
登录
查看更多内容
影响因子：
64.8
作者：
Bycroft C;Freeman C;Petkova D;Band G;Elliott LT;Sharp K;Motyer A;Vukcevic D;Delaneau O;O'Connell J;Cortes A;Welsh S;Young A;Effingham M;McVean G;Leslie S;Allen N;Donnelly P;Marchini J
通讯作者：
Marchini J
DOI：
10.3122/jabfm.2009.04.090081
发表时间：
2009-07-01
影响因子：
2.9
作者：
Birtwhistle, Richard;Keshavjee, Karim;Lagace, Claudia
通讯作者：
Lagace, Claudia
DOI：
10.1164/rccm.201604-0861oc
发表时间：
2017-02-15
影响因子：
24.7
作者：
Almoguera, Berta;Vazquez, Lyam;Hakonarson, Hakon
通讯作者：
Hakonarson, Hakon
DOI：
10.1093/jamia/ocv130
发表时间：
2016-04-01
影响因子：
6.4
作者：
Wei, Wei-Qi;Teixeira, Pedro L.;Denny, Joshua C.
通讯作者：
Denny, Joshua C.
影响因子：
14.6
作者：
Hill, Kylie;Goldstein, Roger S.;Stanbrook, Matthew B.
通讯作者：
Stanbrook, Matthew B.