@article{ce9d21c603504e958f112be387b4a64c,
title = "Ontology-enhanced automatic chief complaint classification for syndromic surveillance",
abstract = "Emergency department free-text chief complaints (CCs) are a major data source for syndromic surveillance. CCs need to be classified into syndromic categories for subsequent automatic analysis. However, the lack of a standard vocabulary and high-quality encodings of CCs hinder effective classification. This paper presents a new ontology-enhanced automatic CC classification approach. Exploiting semantic relations in a medical ontology, this approach is motivated to address the CC vocabulary variation problem in general and to meet the specific need for a classification approach capable of handling multiple sets of syndromic categories. We report an experimental study comparing our approach with two popular CC classification methods using a real-world dataset. This study indicates that our ontology-enhanced approach performs significantly better than the benchmark methods in terms of sensitivity, F measure, and F2 measure.",
keywords = "Bootstrapping, Chief complaint classification, Free-text chief complaints, Medical ontology, Statistical evaluation, Syndromic surveillance, UMLS",
author = "Lu, {Hsin Min} and Daniel Zeng and Lea Trujillo and Ken Komatsu and Hsinchun Chen",
note = "Funding Information: The setting using the SGT and rule set adapted from ECCCS is referred to as ECCCS in BioPortal. The BioPortal project is an infectious disease informatics project with funding support from the National Science Foundation and other federal state agencies. The reported research is part of this project [11,49,50] . ECCCS in BioPortal and ECCCS share the common symptom grouping table and compatible syndrome rules. As such, we can examine the effect of the WSSS component in isolation and fairness. Comparing ECCCS in BioPortal to CoCoNBC can help us evaluate whether an ontology-enhanced approach can achieve performance comparable to that of the na{\"i}ve Bayesian method. Funding Information: This work was supported in part by the US National Science Foundation through Grant No. IIS-0428241 and by the Arizona Department of Health Services. The authors thank Dr. Peter Kelly, Dr. Ayesha Bashir, Dr. Rebecca Sunenshine, and Ms. Leah Chinnaswamy for their significant help establishing the reference standard dataset and syndrome definitions used in this study. The second author wishes to acknowledge support from a Research Grant (60573078) from the National Natural Science Foundation of China, an International Collaboration Grant (2F05N01) from the Chinese Academy of Sciences, a National Basic Research Program of China (973) Grant (2006CB705500) from the Ministry of Science and Technology, and an Innovative Research Group Grant (60621001) from the National Science Foundation of China. We also appreciate valuable comments and suggestions for improvement from anonymous reviewers. ",
year = "2008",
month = apr,
doi = "10.1016/j.jbi.2007.08.009",
language = "English (US)",
volume = "41",
pages = "340--356",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",
number = "2",
}