Electronic medical records for discovery research in rheumatoid arthritis.
Electronic medical records for discovery research in rheumatoid arthritis.
复制标题
DOI：
10.1002/acr.20184
复制
发表时间：
2010-08
影响因子：
4.7
通讯作者：
Plenge, Robert M.
中科院分区：
文献类型：
--
作者：
Liao, Katherine P.;Cai, Tianxi;Gainer, Vivian;Goryachev, Sergey;Zeng-Treitler, Qing;Raychaudhuri, Soumya;Szolovits, Peter;Churchill, Susanne;Murphy, Shawn;Kohane, Isaac;Karlson, Elizabeth W.;Plenge, Robert M.
电子病历（emr）是发现研究的丰富数据源，但由于难以提取高度准确的临床数据而未得到充分利用。我们评估了与单独使用编码EMR数据的算法相比，结合叙述性EMR数据（键入的医生笔记）的分类算法是否更准确地对类风湿关节炎（RA）患者进行分类。≥1 ICD9 RA代码（714.xx）或在两个大型学术中心的EMR中检查过anti-CCP的受试者被纳入“RA Mart”（n=29,432）。对于所有29,432名受试者，我们提取叙述性（使用自然语言处理）并编纂RA临床信息。在一个由96例RA病例和404例非RA病例组成的训练集中，我们使用叙事和编码数据来开发使用逻辑回归的分类算法。这些算法被应用于整个RA Mart。我们通过回顾另外400名被算法分类为RA的受试者的记录，计算并比较了这些算法的阳性预测值（PPV）。一个完整的算法（叙述和编码数据）分类RA受试者的PPV为94%，明显高于单独编码数据的算法（PPV为88%）。通过完整算法确定的RA队列特征与现有RA队列相当（80%为女性，63%为抗ccp +， 59%为糜烂+）。我们证明了利用完整的EMR数据来定义PPV为94%的RA队列的能力，这优于仅使用编码数据的算法。
Electronic medical records (EMRs) are a rich data source for discovery research but are underutilized due to the difficulty of extracting highly accurate clinical data. We assessed whether a classification algorithm incorporating narrative EMR data (typed physician notes), more accurately classifies subjects with rheumatoid arthritis (RA) compared to an algorithm using codified EMR data alone. Subjects with ≥1 ICD9 RA code (714.xx) or who had anti-CCP checked in the EMR of two large academic centers were included into an ‘RA Mart’ (n=29,432). For all 29,432 subjects, we extracted narrative (using natural language processing) and codified RA clinical information. In a training set of 96 RA and 404 non-RA cases from the RA Mart classified by medical record review, we used narrative and codified data to develop classification algorithms using logistic regression. These algorithms were applied to the entire RA Mart. We calculated and compared the positive predictive value (PPV) of these algorithms by reviewing records of an additional 400 subjects classified as RA by the algorithms. A complete algorithm (narrative and codified data) classified RA subjects with a significantly higher PPV of 94%, than an algorithm with codified data alone (PPV 88%). Characteristics of the RA cohort identified by the complete algorithm were comparable to existing RA cohorts (80% female, 63% anti-CCP+, 59% erosion+). We demonstrate the ability to utilize complete EMR data to define an RA cohort with a PPV of 94%, which was superior to an algorithm using codified data alone.
登录
查看更多内容
影响因子：
27.4
作者：
Forslind, K;Ahlmén, M;Svensson, B
通讯作者：
Svensson, B
影响因子：
9.7
作者：
Jha, Ashish K.;Ferris, Timothy G.;Blumenthal, David
通讯作者：
Blumenthal, David
影响因子：
--
作者：
GABRIEL, SE
通讯作者：
GABRIEL, SE
DOI：
10.1002/art.20827
发表时间：
2004-12-15
期刊：
ARTHRITIS & RHEUMATISM-ARTHRITIS CARE & RESEARCH
影响因子：
--
作者：
Singh, JA;Holmgren, AR;Noorbaloochi, S
通讯作者：
Noorbaloochi, S
抗菌柠檬硫化肽抗体在预测炎症性多关节炎中放射学损伤严重程度时的性能：诺福克关节炎登记册的结果。
影响因子：
--
作者：
Bukhari, M.;Thomson, W.;Naseem, H.;Bunn, D.;Silman, A.;Symmons, D.;Barton, A.
通讯作者：
Barton, A.