InSPECt: Interactive Surveillance Portal for Evaluating Clinical support

描述(由申请人提供)： 许多医疗保健提供商正在采用临床决策支持(CDS)系统来提高患者安全性并满足有意义的使用要求。最常见的是计算机警报，提示临床医生药物过敏、药物药物和药物疾病警告或提供剂量指导。警报覆盖可能会阻碍患者结果的改善，有必要对警报和临床医生响应的适当性进行详细评估；然而，传统方法需要手动查看图表，这是劳动密集型的，很难在整个机构中复制所有警报。该提案侧重于开发新的方法来评估和改进建立在传统信息学方法基础上的CDS警报。目标1首先应用先前描述的模型来预测警报覆盖，然后通过添加基于生物医学信息学中先前未评估的测量的协变量来改进这些模型。AIM 2扩展了基于Web的监控工具的使用，开发了一个交互式仪表板，用于评估CDS警报和响应的适当性，其中纳入了AIM 1中开发的模型。假设这些方法将使信息技术人员能够识别和改进性能不佳的警报，从而减少警报疲劳并提高患者安全性。

DESCRIPTION (provided by applicant): Many healthcare providers are adopting clinical decision support (CDS) systems to improve patient safety and meet Meaningful Use requirements. Computerized alerts that prompt clinicians about drug- allergy, drug-drug, and drug-disease warnings or provide dosing guidance are most commonly implemented. Alert overrides can hinder improved patient outcomes, and detailed evaluation of the appropriateness of alerts and clinician responses is necessary; however, traditional methods require manual chart reviews, which are labor intensive and difficult to replicate for all alerts across institutions. This proposal focuses on developing nove methods for evaluating and improving CDS alerts that build upon traditional informatics approaches. Aim 1 begins by applying previously described models for predicting alert overrides then improves these models by adding covariates based on measures not previously assessed within biomedical informatics. Aim 2 expands the use of web-based monitoring tools, developing an interactive dashboard for evaluating CDS alert and response appropriateness that incorporates the models developed in Aim 1. It is hypothesized that these methods will allow informatics personnel to identify and improve poorly performing alerts, thus reducing alert fatigue and increasing patient safety.