TY - JOUR AU - Fan,吴云舟AU - Wu,曹燕燕,邹雄静AU - Zhu, AU - Ming AU - Dai, Di AU - Lu, Lin AU - Yin,熊晓曦AU - Xiong,丽娟PY - 2020 DA - 2020/10/23 TI -基于局域网过程数据多源监测的医疗相关感染自动聚类检测:算法开发和验证回顾性研究JO - JMIR Med Inform SP - e16901 VL - 8 IS - 10kw -卫生保健相关感染KW -聚类检测KW -早期预警KW -多源监测KW -处理数据AB -背景:卫生保健相关感染(HAI)的聚类检测对于早期识别HAI暴发至关重要。目的:验证基于局域网过程数据的多源监测能否有效检测HAI集群。方法:回顾性分析国内某三级医院4个独立高危单位的HAIs发生率及与感染相关的3项流程数据,即联合抗生素使用率、细菌标本检出率、细菌标本阳性率。我们利用Shewhart预警模型来检测时间序列数据的峰值。随后,我们根据过程数据设计了5种监测策略用于HAI聚类检测:(1)仅组合抗生素使用率,(2)仅细菌标本检出率,(3)仅细菌标本阳性率,(4)组合抗生素使用率+细菌标本检出率+平行细菌标本阳性率,(5)组合抗生素使用率+细菌标本检出率+串联细菌标本阳性率。我们使用受试者工作特征(ROC)曲线和约登指数来评估这些监测策略对HAI集群检测的预警性能。结果:5种监测策略的ROC曲线均位于标准线上方,平行策略的ROC曲线下面积大于串联策略和单指标策略。在抗生素使用率为1.5的组合策略下,优登指数为0.48 (95% CI 0.29 ~ 0.67),在细菌标本检出率为0.5的阈值下,优登指数为0.49 (95% CI 0.45 ~ 0.53),在细菌标本阳性率为1.1的阈值下,优登指数为0.50 (95% CI 0.28 ~ 0.71),在平行策略下,优登指数为0.63 (95% CI 0.49 ~ 0.77),阈值为2.6。 and 0.32 (95% CI 0.00-0.65) at a threshold of 0.0 in the series strategy. The warning performance of the parallel strategy was greater than that of the single-indicator strategies when the threshold exceeded 1.5. Conclusions: The multisource surveillance of process data in the area network is an effective method for the early detection of HAI clusters. The combination of multisource data and the threshold of the warning model are 2 important factors that influence the performance of the model. SN - 2291-9694 UR - http://medinform.www.mybigtv.com/2020/10/e16901/ UR - https://doi.org/10.2196/16901 UR - http://www.ncbi.nlm.nih.gov/pubmed/32965228 DO - 10.2196/16901 ID - info:doi/10.2196/16901 ER -
Baidu
map