Combining billing codes, clinical notes, and medications from electronic health records provides superior phenotyping performance
Combining billing codes, clinical notes, and medications from electronic health records provides superior phenotyping performance
复制标题
DOI：
10.1093/jamia/ocv130
复制
发表时间：
2016-04-01
影响因子：
6.4
通讯作者：
Denny, Joshua C.
中科院分区：
文献类型：
--
作者：
Wei, Wei-Qi;Teixeira, Pedro L.;Denny, Joshua C.
目的评价国际疾病分类（ICD）诊断代码、主要注释和特定药物这三个主要电子健康记录（EHR）组件的表型性能。材料和方法我们使用去识别的Vanderbilt EHR数据进行评估。我们预先选择了10种疾病：心房颤动、阿尔茨海默病、乳腺癌、痛风、人类免疫缺陷病毒感染、多发性硬化症、帕金森病、类风湿性关节炎、1型和2型糖尿病。对于每种疾病，根据诊断代码、主要记录和特定药物中的证据，将患者分为七类。每个疾病类别随机选择25例患者（每种疾病共175例患者，所有10种疾病共1750例患者）进行手工图表审查。回顾结果用于估计阳性预测值（PPV），敏感性，以及单独和组合每个EHR组件的f评分。结果单组分ppv不一致，不足以准确分型（0.06 ~ 0.71）。使用两个或更多的ICD代码将平均PPV提高到0.84。当使用至少两个分量时，我们观察到更稳定和更高的准确性（平均值+/-标准差：0.91 +/- 0.08）。主要音符的灵敏度最高（0.77）。ICD编码的灵敏度为0.67。同样，两种或更多的成分提供了相当高和稳定的灵敏度（0.59 +/- 0.16）。总的来说，使用两个或更多的组件可以实现最佳性能（F得分：0.70 +/- 0.12）。虽然使用ICD代码的总体性能（0.67 +/- 0.14）仅略低于使用两个或多个组件，但其PPV（0.71 +/- 0.13）明显更差（0.91 +/- 0.08）。结论多种电子病历成分对所选表型的检测比单一成分具有更高的一致性和性能。我们建议在未来的表型设计中考虑多种电子病历成分，以获得理想的结果。
Objective To evaluate the phenotyping performance of three major electronic health record (EHR) components: International Classification of Disease (ICD) diagnosis codes, primary notes, and specific medications.Materials and Methods We conducted the evaluation using de-identified Vanderbilt EHR data. We preselected ten diseases: atrial fibrillation, Alzheimer's disease, breast cancer, gout, human immunodeficiency virus infection, multiple sclerosis, Parkinson's disease, rheumatoid arthritis, and types 1 and 2 diabetes mellitus. For each disease, patients were classified into seven categories based on the presence of evidence in diagnosis codes, primary notes, and specific medications. Twenty-five patients per disease category (a total number of 175 patients for each disease, 1750 patients for all ten diseases) were randomly selected for manual chart review. Review results were used to estimate the positive predictive value (PPV), sensitivity, and F-score for each EHR component alone and in combination.Results The PPVs of single components were inconsistent and inadequate for accurately phenotyping (0.06-0.71). Using two or more ICD codes improved the average PPV to 0.84. We observed a more stable and higher accuracy when using at least two components (mean +/- standard deviation: 0.91 +/- 0.08). Primary notes offered the best sensitivity (0.77). The sensitivity of ICD codes was 0.67. Again, two or more components provided a reasonably high and stable sensitivity (0.59 +/- 0.16). Overall, the best performance (F score: 0.70 +/- 0.12) was achieved by using two or more components. Although the overall performance of using ICD codes (0.67 +/- 0.14) was only slightly lower than using two or more components, its PPV (0.71 +/- 0.13) is substantially worse (0.91 +/- 0.08).Conclusion Multiple EHR components provide a more consistent and higher performance than a single one for the selected phenotypes. We suggest considering multiple EHR components for future phenotyping design in order to obtain an ideal result.