Department of Medicine Solna, Division of Infectious Disease, Karolinska Institutet, Stockholm, Sweden.
Department of Medicine Solna, Division of Infectious Disease, Karolinska Institutet, Stockholm, Sweden; Department of Infectious Diseases, Karolinska University Hospital, Stockholm, Sweden.
J Hosp Infect. 2021 Apr;110:139-147. doi: 10.1016/j.jhin.2021.01.023. Epub 2021 Feb 3.
Surveillance for healthcare-associated infections such as healthcare-associated urinary tract infections (HA-UTI) is important for directing resources and evaluating interventions. However, traditional surveillance methods are resource-intensive and subject to bias.
To develop and validate a fully automated surveillance algorithm for HA-UTI using electronic health record (EHR) data.
Five algorithms were developed using EHR data from 2979 admissions at Karolinska University Hospital from 2010 to 2011: (1) positive urine culture (UCx); (2) positive UCx + UTI codes (International Statistical Classification of Diseases and Related Health Problems, 10 revision); (3) positive UCx + UTI-specific antibiotics; (4) positive UCx + fever and/or UTI symptoms; (5) algorithm 4 with negation for fever without UTI symptoms. Natural language processing (NLP) was used for processing free-text medical notes. The algorithms were validated in 1258 potential UTI episodes from January to March 2012 and results extrapolated to all UTI episodes within this period (N = 16,712). The reference standard for HA-UTIs was manual record review according to the European Centre for Disease Prevention and Control (and US Centers for Disease Control and Prevention) definitions by trained healthcare personnel.
Of the 1258 UTI episodes, 163 fulfilled the ECDC HA-UTI definition and the algorithms classified 391, 150, 189, 194, and 153 UTI episodes, respectively, as HA-UTI. Algorithms 1, 2, and 3 had insufficient performances. Algorithm 4 achieved better performance and algorithm 5 performed best for surveillance purposes with sensitivity 0.667 (95% confidence interval: 0.594-0.733), specificity 0.997 (0.996-0.998), positive predictive value 0.719 (0.624-0.807) and negative predictive value 0.997 (0.996-0.997).
A fully automated surveillance algorithm based on NLP to find UTI symptoms in free-text had acceptable performance to detect HA-UTI compared to manual record review. Algorithms based on administrative and microbiology data only were not sufficient.
对医疗保健相关性感染（如医疗保健相关性尿路感染[HA-UTI]）进行监测对于指导资源利用和评估干预措施非常重要。然而，传统的监测方法资源密集且存在偏倚。
使用电子健康记录（EHR）数据开发和验证一种用于 HA-UTI 的全自动监测算法。
我们从 2010 年至 2011 年在卡罗林斯卡大学医院的 2979 例住院患者中开发了五种算法：（1）阳性尿液培养（UCx）；（2）阳性 UCx+UTI 编码（国际疾病分类和相关健康问题统计分类，第 10 修订版）；（3）阳性 UCx+UTI 特异性抗生素；（4）阳性 UCx+发热和/或 UTI 症状；（5）算法 4，无 UTI 症状的发热否定。自然语言处理（NLP）用于处理自由文本医疗记录。该算法在 2012 年 1 月至 3 月期间的 1258 例潜在 UTI 发作中进行了验证，并将结果推断至该期间内的所有 UTI 发作（N=16712）。HA-UTIs 的参考标准是由经过培训的医疗保健人员根据欧洲疾病预防控制中心（和美国疾病控制与预防中心）的定义进行的手动记录审查。
在 1258 例 UTI 发作中，有 163 例符合 ECDC 的 HA-UTI 定义，而算法分别将 391、150、189、194 和 153 例 UTI 发作归类为 HA-UTI。算法 1、2 和 3 的性能不足。算法 4 具有更好的性能，而算法 5 用于监测目的的性能最佳，敏感性为 0.667（95%置信区间：0.594-0.733），特异性为 0.997（0.996-0.998），阳性预测值为 0.719（0.624-0.807），阴性预测值为 0.997（0.996-0.997）。
与手动记录审查相比，基于 NLP 查找自由文本中 UTI 症状的全自动监测算法在检测 HA-UTI 方面具有可接受的性能。仅基于行政和微生物学数据的算法不够充分。
