医院就诊数据疾病诊断自动编码和分类统计工具的建立与评价

Establishment and evaluation of automatic coding and classification statistical tool for disease diagnosis in hospital outpatient cases

目的建立ICD-10自动编码和分类统计软件工具,快速实现医院就诊数据疾病诊断的ICD-10编码和分类统计,并对其适用性进行客观评价。方法采用模块化思想,使用精确匹配和正则匹配相结合的方式进行编码分析和分类统计;采用某三甲医院2015年12月份的就诊数据,以其原始ICD编码为标准进行适用性评价。结果该软件具有数据导入、编码匹配、分类统计等业务功能,字典管理、模板管理、权限管理等管理功能;导入数据耗时38 s,完成ICD-10编码耗时456 s,完成统计报表耗时61 s;ICD编码初始成功率为83.3%,编码符合率为90.9%,分类统计结果准确率为100%。结论本研究建立的疾病诊断自动编码分析工具简便、快速、准确、可行,为提高空气污染人群就诊影响等研究数据质量提供有效支持。

Objective To establish automatic International Classification of Diseases-10(ICD-10)coding and classification statistical tool,and to objectively evaluate its applicability so as to rapidly implement ICD-10 coding and classification statistics based on disease diagnosis in hospital outpatient cases.Methods Based on the modular idea,the method of exact matching combined with regular matching was used to perform coding analysis and classification statistics.We selected the data concerning outpatients in December 2015 from a grade A tertiary hospital,and then set the original ICD as the standard to make the applicability evaluation.Results This software had service functions(such as data input,code matching and classification statistics)and management functions(such as dictionary applying,template creating and authority allocating).During the operation,it cost 38 seconds to input the data,456 seconds to implement ICD-10 coding,and 61 seconds to generate statistic reports.The initial success and coincidence rates of ICD coding were 83.3%and 90.9%respectively,and the accuracy of classification was 100%.Conclusions The automatic ICD-10 coding and classification statistical tool can be used conveniently,rapidly,accurately and feasibly;moreover,it can provide effective support for improving data quality relating to the study of impacts of air pollution on outpatients.