Wu Danny T Y, Meganathan Karthikeyan, Newcomb Matthew, Ni Yizhao, Dexheimer Judith W, Kirkendall Eric S, Spooner S Andrew
Department of Biomedical Informatics, University of Cincinnati, Cincinnati, OH.
Department of Pediatrics, University of Cincinnati, Cincinnati, OH.
AMIA Annu Symp Proc. 2018 Dec 5;2018:1103-1109. eCollection 2018.
Dosing errors due to erroneous body weight entry can be mitigated through algorithms designed to detect anomalies in weight patterns. To prepare for the development of a new algorithm for weight-entry error detection, we compared methods for detecting weight anomalies to human annotation, including a regression-based method employed in a real-time web service. Using a random sample of 4,000 growth charts, annotators identified clinically important anomalies with good inter-rater reliability. Performance of the three detection algorithms was variable, with the best performance from the algorithm that takes into account weights collected after the anomaly was recorded. All methods were highly specific, but positive predictive value ranged from < 5% to over 82%. There were 203 records of missed errors, but all of these were either due to no prior data points or errors too small to be clinically significant. This analysis illustrates the need for better weight-entry error detection algorithms.
由于体重输入错误导致的给药错误，可以通过旨在检测体重模式异常的算法来减轻。为了准备开发一种用于体重输入错误检测的新算法，我们将检测体重异常的方法与人工标注进行了比较，包括一种在实时网络服务中使用的基于回归的方法。使用4000份生长图表的随机样本，标注人员识别出具有良好评分者间可靠性的临床重要异常。三种检测算法的性能各不相同，考虑到异常记录后收集的体重的算法表现最佳。所有方法的特异性都很高，但阳性预测值范围从<5%到超过82%。有203条漏报错误记录，但所有这些要么是由于没有先前的数据点，要么是错误太小以至于在临床上不显著。该分析表明需要更好的体重输入错误检测算法。
