Division of General Internal Medicine, Brigham and Women's Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA.
Division of General Internal Medicine, Brigham and Women's Hospital, Boston, MA, USA.
Thromb Res. 2024 Nov;243:109143. doi: 10.1016/j.thromres.2024.109143. Epub 2024 Sep 7.
Accurate identification of incident venous thromboembolism (VTE) for quality improvement and health services research is challenging. The purpose of this study was to evaluate the performance of a novel incident VTE phenotyping algorithm defined using standard terminologies, requiring three key indicators documented in the electronic health record (EHR): VTE diagnostic code, VTE-related imaging procedure code, and anticoagulant medication code.
Retrospective chart reviews were conducted to assess the performance of the algorithm using a random sample of phenotype(+) and phenotype(-) diagnostic encounters from primary care practices and acute care sites affiliated with five hospitals across a large integrated care delivery system in Massachusetts. The performance of the algorithm was evaluated by calculating the positive predictive value (PPV), negative predictive value (NPV), sensitivity, and specificity, using the phenotype(+) and phenotype(-) diagnostic encounters sample and target population data.
Based on gold-standard manual chart review, the algorithm had a PPV of 95.2 % (95 % CI: 93.1-96.8 %), NPV of 97.1 % (95 % CI: 95.3-98.4 %), sensitivity of 91.7 % (95 % CI: 90.8-92.6 %), and specificity of 98.4 % (95 % CI: 98.1-98.6 %). The algorithm systematically misclassified a low number of specific types of encounters, highlighting potential areas for improvement.
This novel phenotyping algorithm offers an accurate approach for identifying incident VTE in general populations using EHR data and standard terminologies, and accurately identifies the specific encounter and date of diagnosis of the incident VTE. This approach can be used for measurement of incident VTE to drive quality improvement, research to expand the evidence, and development of quality metrics and clinical decision support to improve the diagnostic process.
准确识别新发静脉血栓栓塞症（VTE）对于质量改进和卫生服务研究具有挑战性。本研究旨在评估一种新的基于标准术语的新发 VTE 表型算法的性能，该算法需要在电子健康记录（EHR）中记录三个关键指标：VTE 诊断代码、VTE 相关影像学检查代码和抗凝药物代码。
通过回顾性病历审查，使用来自马萨诸塞州五个医院附属的初级保健诊所和急症护理场所的随机样本表型（+）和表型（-）诊断就诊，评估算法的性能。使用表型（+）和表型（-）诊断就诊样本和目标人群数据，计算阳性预测值（PPV）、阴性预测值（NPV）、敏感性和特异性，评估算法的性能。
基于金标准手动病历审查，该算法的 PPV 为 95.2%（95%置信区间：93.1%-96.8%），NPV 为 97.1%（95%置信区间：95.3%-98.4%），敏感性为 91.7%（95%置信区间：90.8%-92.6%），特异性为 98.4%（95%置信区间：98.1%-98.6%）。该算法系统地错误分类了少量特定类型的就诊，突出了潜在的改进领域。
该新型表型算法使用 EHR 数据和标准术语提供了一种准确识别一般人群新发 VTE 的方法，并准确识别新发 VTE 的具体就诊和诊断日期。该方法可用于测量新发 VTE 以推动质量改进、开展研究以扩大证据基础，并开发质量指标和临床决策支持以改善诊断过程。
