NPS MedicineWise, Level 7 / 418a Elizabeth St, Strawberry Hills, NSW, 2012, Sydney, Australia.
Medicines Policy Research Unit, Centre for Big Data Research in Health, UNSW Sydney, Australia.
Int J Popul Data Sci. 2022 Jun 29;7(1):1713. doi: 10.23889/ijpds.v7i1.1713. eCollection 2022.
MedicineInsight is a database containing de-identified electronic health records (EHRs) from over 700 Australian general practices. Previous research validated algorithms used to derive medical condition flags in MedicineInsight, but the accuracy of data fields following EHR extractions from clinical practices and data warehouse transformation processes have not been formally validated.
To examine the accuracy of the extraction and transformation of EHR fields for selected demographics, observations, diagnoses, prescriptions, and tests into MedicineInsight.
We benchmarked MedicineInsight values against those recorded in original EHRs. Forty-six general practices contributing data to MedicineInsight met our eligibility criteria, eight were randomly selected, and four agreed to participate. We randomly selected 200 patients >18 years of age within each participating practice from MedicineInsight. Trained staff reviewed the original EHRs for the selected patients and recorded data from the relevant fields. We calculated the percentage of agreement (POA) between MedicineInsight and EHR data for all fields; Cohen's Kappa for categorical and intra-class correlation (ICC) for continuous measures; and sensitivity, specificity, and positive and negative predictive values (PPV/NPV) for diagnoses.
A total of 796 patients were included in our analysis. All demographic characteristics, observations, diagnoses, prescriptions and random pathology test results had excellent (>90%) POA, Kappa, and ICC. POA for most recent pathology/imaging test was moderate (81%, [95% CI: 78% to 84%]). Sensitivity, specificity, PPV, and NPV were excellent (>90%) for all but one of the examined diagnoses which had a poor PPV.
Overall, our study shows good agreement between the majority of MedicineInsight data and those from original EHRs, suggesting MedicineInsight data extraction and warehousing procedures accurately conserve the data in these key fields. Discrepancies between test data may have arisen due to how data from pathology, radiology and other imaging providers are stored in EHRs and MedicineInsight and this requires further investigation.
MedicineInsight 是一个数据库，其中包含来自 700 多家澳大利亚全科诊所的去识别电子健康记录 (EHR)。先前的研究验证了用于从 MedicineInsight 中提取医学病症标志的算法，但尚未正式验证从临床实践和数据仓库转换过程中提取 EHR 后的数据字段的准确性。
检查将选定人口统计学信息、观察结果、诊断、处方和测试提取和转换到 MedicineInsight 中的准确性。
我们将 MedicineInsight 的值与原始 EHR 中记录的值进行了基准测试。符合 MedicineInsight 数据纳入标准的 46 家提供数据的全科诊所中，有 8 家被随机选择，其中 4 家同意参与。我们从每个参与实践中随机选择了 200 名年龄在 18 岁以上的 MedicineInsight 患者。经过培训的工作人员对选定患者的原始 EHR 进行了审查，并记录了相关字段的数据。我们计算了所有字段的 MedicineInsight 与 EHR 数据之间的一致性百分比 (POA)；分类的 Cohen's Kappa 和连续测量的组内相关系数 (ICC)；以及诊断的敏感性、特异性、阳性和阴性预测值 (PPV/NPV)。
共有 796 名患者纳入我们的分析。所有人口统计学特征、观察结果、诊断、处方和随机病理检查结果的 POA、Kappa 和 ICC 均大于 90%。最近的病理/影像学检查的 POA 为中度 (81%，[95%CI：78%至 84%])。除一个检查诊断的 PPV 较差外，所有诊断的敏感性、特异性、PPV 和 NPV 均大于 90%。
总体而言，我们的研究表明，MedicineInsight 数据与原始 EHR 数据的大部分具有良好的一致性，表明 MedicineInsight 数据提取和仓库处理过程准确地保存了这些关键字段的数据。测试数据之间的差异可能是由于病理学、放射学和其他成像提供商的数据在 EHR 和 MedicineInsight 中的存储方式造成的，这需要进一步调查。
