A prototype classification schema of ICD-genetic disorder system: Chapter 2 neoplasm as an example

• Main Authors: Ming-Kan Wu, 吳明侃
• Other Authors: Wen-Chang Lin
• Format: Others
• Language: zh-TW
• Published: 2009
• Online Access: http://ndltd.ncl.edu.tw/handle/5nav46

碩士 === 國立陽明大學 === 生物醫學資訊研究所 === 97 === Online Mendelian Inheritance in Man (OMIM™), a well-known online database of human genetic disorders provides a interactive query service for disease disorders and genes related human genetic diseases. On the other hand, International Classification of Diseases version 10 (ICD-10) is a coding schema of diseases and signs, symptoms, abnormal findings, complaints, social circumstances and external causes of injury or diseases, as classified by 43 countries at the World Health Organization (WHO). This new code set provides medical process classification standard, and allows a significant expansion on more clinical codes available than the previous ICD-9 classification. Nowadays, almost all disease related genomic research classification tools are built according to the human body physiological systems, a.d OMIM dataset. Therefore, these tools are not oriented for clinical medical professionals, not to mention the user interfaces and data structures. However, ICD system has been widely used by most modern countries, and offers a true medical information classification standard in Hospitals. Therefore, merging the ICD schema as the classification standard for OMIM disease gene dataset might be a novel and efficient way to provide clinical medical researchers a way for browsing OMIM information with clinical relevance and also to help basic biological scientists learning the clinical significance of genes they are interested in through the ICD code integration. This study would like to construct such a database by automatically integrating the rich OMIM information and the classification standard of ICD-10, and to provide user-friendly search and query tools. By using an innovative classification method, this database could provide user more relevant search information and different perspectives through the integration of OMIM-ICD knowledge. OMIM was processed by text mining techniques, and the keywords were tokenized and collected for subsequent automatically classification using the ICD-10 schema. Following the future OMIM and ICD-10 databases update schedule, an automated bioinformatic pipeline was established and the user could then obtain the newest knowledge without any additional manual intervention step. In addition to diseases and genes statistics, searching tools and interface visualizations will be established in the near future for basic research scientists and clinical professionals to provide a new OMIM-ICD knowledge integration database.