BoosTexter: A Boosting-based Systemfor Text Categorization
Machine Learning - Special issue on information retrieval
Clinical and financial outcomes analysis with existing hospital patient records
Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Extracting contrastive information from negation patterns in biomedical literature
ACM Transactions on Asian Language Information Processing (TALIP)
A shared task involving multi-label classification of clinical free text
BioNLP '07 Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing
Journal of Biomedical Informatics
Text categorization with class-based and corpus-based keyword selection
ISCIS'05 Proceedings of the 20th international conference on Computer and Information Sciences
Assertion modeling and its role in clinical phenotype identification
Journal of Biomedical Informatics
| Hi-index | 0.00 |
We explore the role negation and speculation identification plays in the multi-label document-level classification of medical reports for diseases. We identify the polarity of assertions made on noun phrases which reference diseases in the medical reports. We experiment with two machine learning classifiers: one based upon Lucene and the other based upon BoosTexter. We find the performance of these systems on document-level classification of medical reports for diseases fails to show improvement when their input is enhanced by the polarity of assertions made on noun phrases. We conclude that due to the nature of our machine learning classifiers, information on the polarity of phrase-level assertions does not improve performance on our data in a multilabel document-level classification task.