Heng Weng, Chuanliang Yi, Yingzi Lin, Y. Zeng, Yang Li, S. Wu, Dacan Chen, Hao Fu
{"title":"中医非结构化病案语义分析系统的构建","authors":"Heng Weng, Chuanliang Yi, Yingzi Lin, Y. Zeng, Yang Li, S. Wu, Dacan Chen, Hao Fu","doi":"10.1109/BIBMW.2011.6112479","DOIUrl":null,"url":null,"abstract":"Purpose: To develop an intelligent analysis system applying in Traditional Chinese Medicine (TCM) medical records, according to the language description characteristics of TCM; Methodology: Constructing semantic analysis system by several relevant technique, such as corpus database training, Chinese word segmentation and latent semantic analysis modeling etc, through the study of the language characteristics of medical records and the demands in research of TCM; Findings: A corpus database for specialties has been established by processing over 50,000 medical records of TCM; Over 1,400 records regarding to kidney disease have been evaluated automatically by their symptoms descriptions; The result shows a high consistency compared with the human analysis of random sample; Conclusion: It displays the feasibility and advantage of the whole system designing for unstructured medical records, and provides data mining method for massive unstructured data of TCM in integrated solution.","PeriodicalId":158587,"journal":{"name":"BIBM Workshops","volume":"67 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Construction of semantic analysis system for Traditional Chinese Medicine unstructured medical records\",\"authors\":\"Heng Weng, Chuanliang Yi, Yingzi Lin, Y. Zeng, Yang Li, S. Wu, Dacan Chen, Hao Fu\",\"doi\":\"10.1109/BIBMW.2011.6112479\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Purpose: To develop an intelligent analysis system applying in Traditional Chinese Medicine (TCM) medical records, according to the language description characteristics of TCM; Methodology: Constructing semantic analysis system by several relevant technique, such as corpus database training, Chinese word segmentation and latent semantic analysis modeling etc, through the study of the language characteristics of medical records and the demands in research of TCM; Findings: A corpus database for specialties has been established by processing over 50,000 medical records of TCM; Over 1,400 records regarding to kidney disease have been evaluated automatically by their symptoms descriptions; The result shows a high consistency compared with the human analysis of random sample; Conclusion: It displays the feasibility and advantage of the whole system designing for unstructured medical records, and provides data mining method for massive unstructured data of TCM in integrated solution.\",\"PeriodicalId\":158587,\"journal\":{\"name\":\"BIBM Workshops\",\"volume\":\"67 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BIBM Workshops\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/BIBMW.2011.6112479\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BIBM Workshops","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BIBMW.2011.6112479","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Construction of semantic analysis system for Traditional Chinese Medicine unstructured medical records
Purpose: To develop an intelligent analysis system applying in Traditional Chinese Medicine (TCM) medical records, according to the language description characteristics of TCM; Methodology: Constructing semantic analysis system by several relevant technique, such as corpus database training, Chinese word segmentation and latent semantic analysis modeling etc, through the study of the language characteristics of medical records and the demands in research of TCM; Findings: A corpus database for specialties has been established by processing over 50,000 medical records of TCM; Over 1,400 records regarding to kidney disease have been evaluated automatically by their symptoms descriptions; The result shows a high consistency compared with the human analysis of random sample; Conclusion: It displays the feasibility and advantage of the whole system designing for unstructured medical records, and provides data mining method for massive unstructured data of TCM in integrated solution.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
