Kang Hong, Wang Frank, Zhou Sicheng, Miao Qi, Gong Yang
School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA.
College of Natural Sciences, The University of Texas at Austin, Austin, TX, USA.
Stud Health Technol Inform. 2017;245:1048-1052.
Health information technology (HIT) events, a subtype of patient safety events, pose a major threat and barrier toward a safer healthcare system. It is crucial to gain a better understanding of the nature of the errors and adverse events caused by current HIT systems. The scarcity of HIT event-exclusive databases and event reporting systems indicates the challenge of identifying the HIT events from existing resources. FDA Manufacturer and User Facility Device Experience (MAUDE) database is a potential resource for HIT events. However, the low proportion and the rapid evolvement of HIT-related events present challenges for distinguishing them from other equipment failures and hazards. We proposed a strategy to identify and synchronize HIT events from MAUDE by using a filter based on structured features and classifiers based on unstructured features. The strategy will help us develop and grow an HIT event-exclusive database, keeping pace with updates to MAUDE toward shared learning.
健康信息技术（HIT）事件作为患者安全事件的一个子类型，对更安全的医疗系统构成了重大威胁和障碍。更好地了解当前HIT系统导致的错误和不良事件的性质至关重要。HIT事件专属数据库和事件报告系统的稀缺表明了从现有资源中识别HIT事件的挑战。美国食品药品监督管理局（FDA）的制造商和用户设施设备经验（MAUDE）数据库是HIT事件的一个潜在资源。然而，HIT相关事件的低比例和快速演变给将它们与其他设备故障和危害区分开来带来了挑战。我们提出了一种策略，通过使用基于结构化特征的过滤器和基于非结构化特征的分类器，从MAUDE中识别和同步HIT事件。该策略将帮助我们开发和扩充一个HIT事件专属数据库，与MAUDE的更新保持同步，以促进共享学习。
