Imai Takeshi, Kajino Masayuki, Sato Megumi, Ohe Kazuhiko
Graduate School of Medicine, The University of Tokyo, Japan.
Stud Health Technol Inform. 2010;160(Pt 2):1080-4.
This paper presents: (1) a framework of formal representation of ICD10, which functions as a bridge between ontological information and natural language expressions; and (2) a methodology to use formally described ICD10 for computer-assisted ICD coding. First, we analyzed and structurized the meanings of categories in 15 chapters of ICD10. Then we expanded the structured ICD10 (S-ICD10) by adding subordinate concepts and labels derived from Japanese Standard Disease Names. The information model to describe formal representation was refined repeatedly. The resultant model includes 74 types of semantic links. We also developed an ICD coding module based on S-ICD10 and a 'Coding Principle,' which achieved high accuracy (>70%) for four chapters. These results not only demonstrate the basic feasibility of our coding framework but might also inform the development of the information model for formal description framework in the ICD11 revision.
（1）ICD10的形式化表示框架，它充当本体信息与自然语言表达之间的桥梁；（2）一种使用形式化描述的ICD10进行计算机辅助ICD编码的方法。首先，我们分析并构建了ICD10十五章中各分类的含义。然后，我们通过添加源自日本标准疾病名称的从属概念和标签，对结构化ICD10（S-ICD10）进行了扩展。反复完善用于描述形式化表示的信息模型。最终模型包含74种语义链接。我们还基于S-ICD10和“编码原则”开发了一个ICD编码模块，该模块在四章内容上实现了较高的准确率（>70%）。这些结果不仅证明了我们编码框架的基本可行性，还可能为ICD11修订版中形式化描述框架的信息模型开发提供参考。
