@conference {ICBO_2018_35, title = {ICBO_2018_35: Can a Convolutional Neural Network Support Auditing of NCI Thesaurus Neoplasm Concepts?}, booktitle = {International Conference on Biomedical Ontology (ICBO 2018)}, series = {Proceedings of the International Conference on Biological Ontology (2018)}, year = {2018}, month = {08/06/2018}, publisher = {International Conference on Biological Ontology}, organization = {International Conference on Biological Ontology}, abstract = {

We present a Machine Learning methodology using a Convolutional Neural Network to perform a specific case of an ontology Quality Assurance, namely discovery of missing IS-A relationships for Neoplasm concepts in the National Cancer Institute Thesaurus (NCIt). The training step checking all {\textquotedblleft}uncles{\textquotedblright} of a concept is computationally intensive. To shorten the time and to improve the accuracy, we define a restricted methodology to check only uncles that are similar to each current concept. The restricted technique yields higher classification recall (compared to the unrestricted one) when testing against known errors found by domain experts who manually reviewed Neoplasm concepts in a prior study. The results are encouraging and provide impetus for further improvements to our technique.

}, keywords = {Abstraction Network, CNN, deep learning, machine learning, National Cancer Institute Thesaurus, Neoplasm Hierarchy, quality assurance}, url = {http://ceur-ws.org/Vol-2285/ICBO_2018_paper_35.pdf}, author = {Hao Liu and Ling Zheng and Yehoshua Perl and James Geller and Gai Elhanan} }