Classifying medical relations in clinical text via convolutional neural networks.

Journal: Artificial intelligence in medicine
Published Date: May 18, 2018

Abstract

Deep learning research on relation classification has achieved solid performance in the general domain. This study proposes a convolutional neural network (CNN) architecture with a multi-pooling operation for medical relation classification on clinical records and explores a loss function with a category-level constraint matrix. Experiments using the 2010 i2b2/VA relation corpus demonstrate these models, which do not depend on any external features, outperform previous single-model methods and our best model is competitive with the existing ensemble-based method.

Authors

  • Bin He
    Clinical Translational Medical Center, The Affiliated Dongguan Songshan Lake Central Hospital, Guangdong Medical University, Dongguan, Guangdong, China.
  • Yi Guan
    School of Computer Science and Technology, Harbin Institute of Technology, Integrated Laboratory Building 803, Harbin 150001, China. Electronic address: guanyi@hit.edu.cn.
  • Rui Dai
    Department of Mathematics, Harbin Institute of Technology, Harbin, China. Electronic address: 13B912003@hit.edu.cn.

Keywords

External Resources

Popular Topics
Recent Journals