University of California, San Francisco, San Francisco, California (M.J.P., V.F., N.N., S.P., R.J.R., A.H., A.R., R.J.C., C.E.M., R.G., A.A.).
Ann Intern Med. 2020 Jun 2;172(11 Suppl):S85-S91. doi: 10.7326/M19-0877.
Electronic health record (EHR) systems can be configured to deliver novel EHR interventions that influence clinical decision making and to support efficient randomized controlled trials (RCTs) designed to evaluate the effectiveness, safety, and costs of those interventions. In designing RCTs of EHR interventions, one should carefully consider the unit of randomization (for example, patient, encounter, clinician, or clinical unit), balancing concerns about contamination of an intervention across randomization units within clusters (for example, patients within clinical units) against the superior control of measured and unmeasured confounders that comes with randomizing a larger number of units. One should also consider whether the key computational assessment components of the EHR intervention, such as a predictive algorithm used to target a subgroup for decision support, should occur before randomization (so that only 1 subgroup is randomized) or after randomization (including all subgroups). When these components are applied after randomization, one must consider expected heterogeneity in the effect of the differential decision support across subgroups, which has implications for overall impact potential, analytic approach, and sample size planning. Trials of EHR interventions should be reviewed by an institutional review board, but may not require patient-level informed consent when the interventions being tested can be considered minimal risk or quality improvement, and when clinical decision making is supported, rather than controlled, by an EHR intervention. Data and safety monitoring for RCTs of EHR interventions should be conducted to guide institutional pragmatic decision making about implementation and ensure that continuing randomization remains justified. Reporting should follow the CONSORT (Consolidated Standards of Reporting Trials) Statement, with extensions for pragmatic trials and cluster RCTs when applicable, and should include detailed materials to enhance reproducibility.
电子健康记录 (EHR) 系统可以配置为提供新颖的 EHR 干预措施，以影响临床决策，并支持旨在评估这些干预措施的有效性、安全性和成本的高效随机对照试验 (RCT)。在设计 EHR 干预措施的 RCT 时，应仔细考虑随机化单位（例如，患者、就诊、临床医生或临床单位），在考虑干预措施在聚类内的随机化单位（例如，临床单位内的患者）之间交叉污染的问题的同时，平衡与更大数量的单位随机化带来的对测量和未测量混杂因素的更好控制。还应考虑 EHR 干预措施的关键计算评估组件，例如用于针对决策支持目标亚组的预测算法，是否应在随机化之前（因此仅随机化 1 个亚组）或随机化之后（包括所有亚组）发生。当这些组件在随机化后应用时，必须考虑不同亚组之间差异化决策支持效果的预期异质性，这对总体影响潜力、分析方法和样本量规划有影响。EHR 干预措施的试验应由机构审查委员会审查，但当所测试的干预措施可以被认为是最小风险或质量改进，并且 EHR 干预措施支持而不是控制临床决策时，可能不需要患者级别的知情同意。应进行 EHR 干预措施 RCT 的数据和安全监测，以指导机构关于实施的务实决策，并确保继续随机化仍然合理。报告应遵循 CONSORT（临床试验报告统一标准）声明，并在适用时扩展到务实试验和聚类 RCT，并应包括详细的材料以增强可重复性。
