Kuperman G J, Hiltz F L, Teich J M
Department of Information Systems, Partners Healthcare System, Boston, MA, USA.
Proc AMIA Annu Fall Symp. 1997:243-7.
We added two advanced features to our automated alerting system. The first feature identifies and displays, at the time an alert is reviewed, relevant data filed between the login time of a specimen leading to an alerting result and the time the alert is reviewed. Relevant data is defined as data of the same kind as generated the alert. The other feature retracts alerts when the alerting value is edited and no longer satisfies the alerting criteria. We evaluated the two features for a 14-week period (new relevant data) and a 6-week period (retraction). Of a total of 1104 alerts in the 14-week evaluation, 286 (25.9%) had new relevant data displayed at alert review time. Of the 286, 75.2% were due to additions of comments to the original piece of alerting data; 24.1% were due to new or pending laboratory results of the same type that generated the alert. Two alerts (out of 490) were retracted in a 6 week period. We conclude that in our system, new clinically relevant data is often added between the time of specimen login and the time that an alerting result from that specimen is reviewed. Retractions occur rarely but are important to detect and communicate.
我们在自动警报系统中添加了两项高级功能。第一项功能是在审查警报时识别并显示在导致警报结果的标本登录时间与审查警报时间之间归档的相关数据。相关数据定义为产生警报的同类数据。另一项功能是在警报值被编辑且不再满足警报标准时撤回警报。我们对这两项功能进行了为期14周（新相关数据）和6周（撤回）的评估。在为期14周的评估中，总共1104条警报中，有286条（25.9%）在警报审查时显示了新的相关数据。在这286条警报中，75.2%是由于在原始警报数据中添加了注释；24.1%是由于产生警报的同类新的或待处理的实验室结果。在6周内撤回了两条警报（共490条）。我们得出结论，在我们的系统中，新的临床相关数据经常在标本登录时间与审查该标本的警报结果时间之间添加。撤回情况很少发生，但检测和沟通很重要。
