王浩 王艺元 陈汝林 李杰

创业资助项目：基于健康档案的医疗卫生信息共享和协同服务系统 （编号：CYZZ20160531092327197）

【摘要】近年来，医疗卫生体制改革的不断深入，各级医院以及医疗卫生管理机构的信息化建设得到了很大a的发展，产生了大量医学健康数据。经过多年的努力，深圳市福田区建设的区域医疗卫生数据交换平台基本完成。如何有效提高卫生系统的互联互通数据的标准化、准确性，面临急需解决的问题，本文中的疾病标准匹配算法基于福田区卫计委在区域医疗卫生信息平台统建设的成果上，利用大数据挖掘技术，对已收集的数十亿条医院电子病历、健康档案等海量数据进行匹配并标准化，实现不同医疗机构间的数据标准化交换。该算法首先将规范编码表加载进内存生成一个键值对形式的集合，然后用规范编码表的键对目标字符串进行匹配，如果匹配成功，将目标字符转替换成为相对应的编码。可以有效提升匹配效果，避免重复匹配以及匹配不准确等问题。可应用于区域医疗卫生信息平台互联互通数据交换规范化、准确性方面。

【关键词】区域医疗卫生信息平台；互连互通；疾病标准；匹配算法

【中图分类号】R473

【文献标志码】A

【文章编号】1005-0019（2018）09-278-01

Abstract In recent years， the continuous deepening of the reform of the medical and health system， the informatization construction of hospitals at all levels and the medical and health management institutions have achieved great development， and a great deal of medical health data has been produced. After years of hard work， the regional medical and health data exchange platform built in Futian District of Shenzhen was basically completed. How to effectively improve the standardization and accuracy of interconnected interoperability data in health systems， and face problems that need to be solved urgently. The disease standard matching algorithm in this paper is based on the results of the Futian District Health and Development Commission's construction of the regional health and medical information platform and the use of big data mining. The technology matches and standardizes the massive data of billions of hospital electronic medical records and health records that have been collected， and realizes standardized data exchange between different medical institutions. The algorithm first loads the canonical coding table into memory to generate a set of key-value pairs， and then matches the target string with the keys of the canonical coding table. If the matching is successful， the target character is replaced by the corresponding code. It can effectively improve the matching effect and avoid problems such as repeated matching and inaccurate matching. It can be applied to the standardization and accuracy of data exchange between regional medical and health information platforms.

Key words：Regional health information platform； interconnection and intercommunication； disease standards； matching algorithm；

（一）概述

近年來，医疗卫生体制改革的不断深入，各级医院以及医疗卫生管理机构的信息化建设得到了很大的发展，产生了大量医学健康数据。经过多年的努力，深圳市福田区建设的区域医疗卫生数据交换平台基本完成。……