Convolutional neural networks for biomedical text classification
- 9 September 2015
- conference paper
- research article
- Published by Association for Computing Machinery (ACM)
- Vol. 2015, 258-267
- https://doi.org/10.1145/2808719.2808746
Abstract
Building high accuracy text classifiers is an important task in biomedicine given the wealth of information hidden in unstructured narratives such as research articles and clinical documents. Due to large feature spaces, traditionally, discriminative approaches such as logistic regression and support vector machines with n-gram and semantic features (e.g., named entities) have been used for text classification where additional performance gains are typically made through feature selection and ensemble approaches. In this paper, we demonstrate that a more direct approach using convolutional neural networks (CNNs) outperforms several traditional approaches in biomedical text classification with the specific use-case of assigning medical subject headings (or MeSH terms) to biomedical articles. Trained annotators at the national library of medicine (NLM) assign on an average 13 codes to each biomedical article, thus semantically indexing scientific literature to support NLM's PubMed search system. Recent evidence suggests that effective automated efforts for MeSH term assignment start with binary classifiers for each term. In this paper, we use CNNs to build binary text classifiers and achieve an absolute improvement of over 3% in macro F-score over a set of selected hard-to-classify MeSH terms when compared with the best prior results on a public dataset. Additional experiments on 50 high frequency terms in the dataset also show improvements with CNNs. Our results indicate the strong potential of CNNs in biomedical text classification tasks.Keywords
Funding Information
- National Institutes of Health (UL1TR000117)
This publication has 23 references indexed in Scilit:
- An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competitionBMC Bioinformatics, 2015
- Feature engineering for MEDLINE citation categorization with MeSHBMC Bioinformatics, 2015
- Context-driven automatic subgraph creation for literature-based discoveryJournal of Biomedical Informatics, 2015
- Knowledge based word-concept model estimation and refinement for biomedical text miningJournal of Biomedical Informatics, 2015
- Leveraging output term co-occurrence frequencies and latent associations in predicting medical subject headingsData & Knowledge Engineering, 2014
- Learning regular expressions for clinical text classificationJournal of the American Medical Informatics Association, 2014
- Large-Scale Multi-label Text Classification — Revisiting Neural NetworksLecture Notes in Computer Science, 2014
- Recommending MeSH terms for annotating biomedical articlesJournal of the American Medical Informatics Association, 2011
- Classifier chains for multi-label classificationMachine Learning, 2011
- Optimal Training Sets for Bayesian Prediction of MeSH(R) AssignmentJournal of the American Medical Informatics Association, 2008