Mao Huajian, Chi Chenyang, Huang Boyu, Meng Haibin, Yu Jinghui, Zhao Dongsheng
Institute of Health Service and Medical Informatics, Academy of Military Medical Sciences of Chinese PLA, Beijing, China.
Stud Health Technol Inform. 2017;245:511-515.
Standardized terminology is the prerequisite of data exchange in analysis of clinical processes. However, data from different electronic health record systems are based on idiosyncratic terminology systems, especially when the data is from different hospitals and healthcare organizations. Terminology standardization is necessary for the medical data analysis. We propose a crowdsourcing-based terminology mapping method, CrowdMapping, to standardize the terminology in medical data. CrowdMapping uses a confidential model to determine how terminologies are mapped to a standard system, like ICD-10. The model uses mappings from different health care organizations and evaluates the diversity of the mapping to determine a more sophisticated mapping rule. Further, the CrowdMapping model enables users to rate the mapping result and interact with the model evaluation. CrowdMapping is a work-in-progress system, we present initial results mapping terminologies.
标准化术语是临床过程分析中数据交换的前提条件。然而，来自不同电子健康记录系统的数据基于各自特有的术语系统，尤其是当数据来自不同医院和医疗保健组织时。术语标准化对于医学数据分析而言是必要的。我们提出一种基于众包的术语映射方法CrowdMapping，以对医学数据中的术语进行标准化。CrowdMapping使用一种保密模型来确定术语如何映射到标准系统，如国际疾病分类第十版（ICD-10）。该模型使用来自不同医疗保健组织的映射，并评估映射的多样性以确定更完善的映射规则。此外，CrowdMapping模型允许用户对映射结果进行评分并与模型评估进行交互。CrowdMapping是一个仍在开发中的系统，我们展示了术语映射的初步结果。
