使用机器学习算法检测异常静脉输液告警模式。
Detecting Unusual Intravenous Infusion Alerting Patterns with Machine Learning Algorithms.
机构信息
Marian Obuseh is a PhD student in the School of Industrial Engineering at Purdue University in West Lafayette, IN. Email:
Denny Yu, PhD, is an assistant professor in the School of Industrial Engineering at Purdue University in West Lafayette, IN.
出版信息
Biomed Instrum Technol. 2022 Apr 1;56(2):58-70. doi: 10.2345/0899-8205-56.2.58.
OBJECTIVE
To detect unusual infusion alerting patterns using machine learning (ML) algorithms as a first step to advance safer inpatient intravenous administration of high-alert medications.
MATERIALS AND METHODS
We used one year of detailed propofol infusion data from a hospital. Interpretable and clinically relevant variables were feature engineered, and data points were aggregated per calendar day. A univariate (maximum times-limit) moving range (mr) control chart was used to simulate clinicians' common approach to identifying unusual infusion alerting patterns. Three different unsupervised multivariate ML-based anomaly detection algorithms (Local Outlier Factor, Isolation Forest, and k-Nearest Neighbors) were used for the same purpose. Results from the control chart and ML algorithms were compared.
RESULTS
The propofol data had 3,300 infusion alerts, 92% of which were generated during the day shift and seven of which had a times-limit greater than 10. The mr-chart identified 15 alert pattern anomalies. Different thresholds were set to include the top 15 anomalies from each ML algorithm. A total of 31 unique ML anomalies were grouped and ranked by agreeability. All algorithms agreed on 10% of the anomalies, and at least two algorithms agreed on 36%. Each algorithm detected one specific anomaly that the mr-chart did not detect. The anomaly represented a day with 71 propofol alerts (half of which were overridden) generated at an average rate of 1.06 per infusion, whereas the moving alert rate for the week was 0.35 per infusion.
DISCUSSION
These findings show that ML-based algorithms are more robust than control charts in detecting unusual alerting patterns. However, we recommend using a combination of algorithms, as multiple algorithms serve a benchmarking function and allow researchers to focus on data points with the highest algorithm agreeability.
CONCLUSION
Unsupervised ML algorithms can assist clinicians in identifying unusual alert patterns as a first step toward achieving safer infusion practices.
目的
使用机器学习（ML）算法检测异常输液报警模式，作为推进高危药物住院静脉输液更安全的第一步。
材料和方法
我们使用了一家医院一年的详细丙泊酚输注数据。对可解释和临床相关的变量进行特征工程处理，并按日历日对数据点进行聚合。使用单变量（最大时间限制）移动范围（mr）控制图来模拟临床医生识别异常输液报警模式的常见方法。还使用了三种不同的无监督多元 ML 异常检测算法（局部离群因子、孤立森林和 k-最近邻）来达到相同的目的。将控制图和 ML 算法的结果进行了比较。
结果
丙泊酚数据有 3300 次输液警报，其中 92%是在白班生成的，其中 7 次的时间限制超过 10 次。mr 图识别出 15 个报警模式异常。为包含每个 ML 算法中的前 15 个异常，设置了不同的阈值。总共 31 个独特的 ML 异常被分组并按一致性进行排序。所有算法对 10%的异常达成一致，至少有两种算法对 36%的异常达成一致。每种算法都检测到了 mr 图未检测到的一个特定异常。该异常代表一天内有 71 次丙泊酚警报（其中一半被覆盖），平均每输注一次产生 1.06 次警报，而该周的移动警报率为每输注 0.35 次。
讨论
这些发现表明，基于 ML 的算法比控制图更能可靠地检测异常报警模式。但是，我们建议使用多种算法相结合，因为多种算法可以起到基准测试的作用，并使研究人员能够专注于具有最高算法一致性的数据点。
结论
无监督 ML 算法可以帮助临床医生识别异常报警模式，作为实现更安全输液实践的第一步。
Zotero 插件