出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Clinical documents are a repository of information about patients' conditions. However, thiswealth of data is not properly tapped by the existing analysis tools. Dengue is one of the mostwidespread water borne diseases known today. Every year, dengue has been threatening livesthe world over. Systems already developed have concentrated on extracting disorder mentionsusing dictionary look-up, or supervised learning methods. This project aims at performingNamed Entity Recognition to extract disorder mentions, time expressions and other relevantfeatures from clinical data. These can be used to build a model, which can in turn be used topredict the presence or absence of the disease, dengue. Further, we perform a frequencyanalysis which correlates the occurrence of dengue and the manifestation of its symptoms overthe months. The system produces appreciable accuracy and serves as a valuable tool formedical experts.
关键词：Named Entity Recognition; Part of Speech tagging; Classification; Prediction; SMO
