当前位置:
X-MOL 学术
›
Journal of Speech Language and Hearing Research
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Automated Phenotyping Tool for Identifying Developmental Language Disorder Cases in Health Systems Data (APT-DLD): A New Research Algorithm for Deployment in Large-Scale Electronic Health Record Systems
Journal of Speech Language and Hearing Research Pub Date : 2020-08-13 , DOI: 10.1044/2020_jslhr-19-00397 Courtney E Walters 1, 2 , Rachana Nitin 1, 3 , Katherine Margulis 4, 5 , Olivia Boorom 4 , Daniel E Gustavson 1, 6 , Catherine T Bush 4 , Lea K Davis 6, 7 , Jennifer E Below 6, 7 , Nancy J Cox 6, 7 , Stephen M Camarata 4 , Reyna L Gordon 1, 3, 6
Purpose Data mining algorithms using electronic health records (EHRs) are useful in large-scale population-wide studies to classify etiology and comorbidities (Casey et al., 2016 ). Here, we apply this approach to developmental language disorder (DLD), a prevalent communication disorder whose risk factors and epidemiology remain largely undiscovered.Method We first created a reliable system for manually identifying DLD in EHRs based on speech-language pathologist (SLP) diagnostic expertise. We then developed and validated an automated algorithmic procedure, called, Automated Phenotyping Tool for identifying DLD cases in health systems data (APT-DLD), that classifies a DLD status for patients within EHRs on the basis of ICD (International Statistical Classification of Diseases and Related Health Problems) codes. APT-DLD was validated in a discovery sample (N = 973) using expert SLP manual phenotype coding as a gold-standard comparison and then applied and further validated in a replication sample ofN = 13,652 EHRs.Results In the discovery sample, the APT-DLD algorithm correctly classified 98% (concordance) of DLD cases in concordance with manually coded records in the training set, indicating that APT-DLD successfully mimics a comprehensive chart review. The output of APT-DLD was also validated in relation to independently conducted SLP clinician coding in a subset of records, with a positive predictive value of 95% of cases correctly classified as DLD. We also applied APT-DLD to the replication sample, where it achieved a positive predictive value of 90% in relation to SLP clinician classification of DLD.Conclusions APT-DLD is a reliable, valid, and scalable tool for identifying DLD cohorts in EHRs. This new method has promising public health implications for future large-scale epidemiological investigations of DLD and may inform EHR data mining algorithms for other communication disorders.Supplemental Material https://doi.org/10.23641/asha.12753578
中文翻译:
用于识别卫生系统数据中的发育性语言障碍病例的自动表型工具(APT-DLD):一种用于大规模电子健康记录系统中部署的新研究算法
目的 使用电子健康记录 (EHR) 的数据挖掘算法可用于大规模人群研究中对病因和合并症进行分类。凯西等人,2016 )。在这里,我们将这种方法应用于发展性语言障碍(DLD),这是一种普遍存在的沟通障碍,其危险因素和流行病学在很大程度上仍未被发现。方法 我们首先创建了一个可靠的系统,用于根据语音病理学家 (SLP) 的诊断专业知识在 EHR 中手动识别 DLD。然后,我们开发并验证了一种自动化算法程序,称为自动表型分析工具,用于识别卫生系统数据中的 DLD 病例 (APT-DLD),该程序根据 ICD(国际疾病统计分类)对 EHR 内患者的 DLD 状态进行分类。相关健康问题)代码。APT-DLD 在发现样本中得到验证(氮 = 973)使用专家 SLP 手动表型编码作为黄金标准比较,然后在复制样本中应用并进一步验证氮 = 13,652 份电子病历。结果 在发现样本中,APT-DLD 算法根据训练集中的手动编码记录正确分类了 98%(一致性)的 DLD 案例,这表明 APT-DLD 成功模拟了全面的图表审查。APT-DLD 的输出还根据记录子集中独立进行的 SLP 临床医生编码进行了验证,其中 95% 的病例正确分类为 DLD 的阳性预测值。我们还将 APT-DLD 应用于复制样本,相对于 SLP 临床医生对 DLD 的分类,其阳性预测值达到 90%。结论 APT-DLD 是一种可靠、有效且可扩展的工具,用于识别 EHR 中的 DLD 群组。这种新方法对未来大规模 DLD 流行病学调查具有良好的公共卫生影响,并可能为其他沟通障碍的 EHR 数据挖掘算法提供信息。补充材料 https://doi.org/10.23641/asha.12753578
更新日期:2020-08-13
Journal of Speech Language and Hearing Research Pub Date : 2020-08-13 , DOI: 10.1044/2020_jslhr-19-00397 Courtney E Walters 1, 2 , Rachana Nitin 1, 3 , Katherine Margulis 4, 5 , Olivia Boorom 4 , Daniel E Gustavson 1, 6 , Catherine T Bush 4 , Lea K Davis 6, 7 , Jennifer E Below 6, 7 , Nancy J Cox 6, 7 , Stephen M Camarata 4 , Reyna L Gordon 1, 3, 6
Affiliation
中文翻译:
用于识别卫生系统数据中的发育性语言障碍病例的自动表型工具(APT-DLD):一种用于大规模电子健康记录系统中部署的新研究算法