Tseng Yi-Ju, Wu Jung-Hsuan, Lin Hui-Chi, Chiu Hsiang-Ju, Huang Bo-Chiang, Shang Rung-Ji, Chen Ming-Yuan, Chen Wei-Hsin, Chen Huai-Te, Lai Feipei, Chen Yee-Chun
National Taiwan University, Taiwan.
Stud Health Technol Inform. 2013;186:145-9.
Healthcare-associated infections (HAIs) are a major patient safety issue. These adverse events add to the burden of resource use, promote resistance to antibiotics, and contribute to patient deaths and disability. A rule-based HAI classification and surveillance system was developed for automatic integration, analysis, and interpretation of HAIs and related pathogens. Rule-based classification system was design and implement to facilitate healthcare-associated bloodstream infection (HABSI) surveillance. Electronic medical records from a 2200-bed teaching hospital in Taiwan were classified according to predefined criteria of HABSI. The detailed information in each HABSI was presented systematically to support infection control personnel decision. The accuracy of HABSI classification was 0.94, and the square of the sample correlation coefficient was 0.99.
医疗保健相关感染（HAIs）是一个重大的患者安全问题。这些不良事件增加了资源使用负担，促进了对抗生素的耐药性，并导致患者死亡和残疾。开发了一种基于规则的HAI分类和监测系统，用于对HAIs和相关病原体进行自动整合、分析和解读。设计并实施了基于规则的分类系统，以促进医疗保健相关血流感染（HABSI）监测。根据HABSI的预定义标准，对台湾一家拥有2200张床位的教学医院的电子病历进行分类。系统呈现每个HABSI中的详细信息，以支持感染控制人员的决策。HABSI分类的准确率为0.94，样本相关系数的平方为0.99。
