@inproceedings{3e50a4ebca51441eadb82aaad0cab64b,
title = "Discovering additional complex NCIt gene concepts with high error rate",
abstract = "The Gene hierarchy of the National Cancer Institute (NCI) Thesaurus (NCIt) is of high priority for NCI. It is important to have quality assurance (QA) techniques to improve its content quality. We present a two-step methodology concentrating on auditing the modeling of complex concepts, which are shown to have a higher error rate compared to control concepts. In the first step, we test whether concepts that appear complex in a so called 'partial-area taxonomy' have a higher error rate than control concepts. In the second step, we introduce an innovative technique based on a 'partial-area sub-taxonomy' (constructed with a subset of roles) to discover additional complex concepts. The results of the QA study show that these concepts are indeed statistically significantly more likely to have more errors than control concepts. This makes it easier for NCI staff to improve the modeling quality of gene concepts in NCIt.",
keywords = "Gene hierarchy, National Cancer Institute Thesaurus, auditing software, complex concepts, quality assurance",
author = "Ling Zheng and Hua Min and Yehoshua Perl and James Geller",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017 ; Conference date: 13-11-2017 Through 16-11-2017",
year = "2017",
month = dec,
day = "15",
doi = "10.1109/BIBM.2017.8217731",
language = "English (US)",
series = "Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "653--657",
editor = "Illhoi Yoo and Zheng, {Jane Huiru} and Yang Gong and Hu, {Xiaohua Tony} and Chi-Ren Shyu and Yana Bromberg and Jean Gao and Dmitry Korkin",
booktitle = "Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017",
address = "United States",
}