Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes

Yuan Luo*, Yu Cheng, Özlem Uzuner, Peter Szolovits, Justin B Starren

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

52 Scopus citations


We propose Segment Convolutional Neural Networks (Seg-CNNs) for classifying relations from clinical notes. Seg-CNNs use only word-embedding features without manual feature engineering. Unlike typical CNN models, relations between 2 concepts are identified by simultaneously learning separate representations for text segments in a sentence: preceding, concept1, middle, concept2, and succeeding. We evaluate Seg-CNN on the i2b2/ VA relation classification challenge dataset. We show that Seg-CNN achieves a state-of-the-art micro-average F-measure of 0.742 for overall evaluation, 0.686 for classifying medical problem-treatment relations, 0.820 for medical problem-test relations, and 0.702 for medical problem-medical problem relations. We demonstrate the benefits of learning segment-level representations. We show that medical domain word embeddings help improve relation classification. Seg-CNNs can be trained quickly for the i2b2/VA dataset on a graphics processing unit (GPU) platform. These results support the use of CNNs computed over segments of text for classifying medical relations, as they show state-of-the-art performance while requiring no manual feature engineering.

Original languageEnglish (US)
Article numberocx090
Pages (from-to)93-98
Number of pages6
JournalJournal of the American Medical Informatics Association
Issue number1
StatePublished - Jan 1 2018


  • Convolutional neural network
  • Machine learning
  • Medical relation classification
  • Natural language processing

ASJC Scopus subject areas

  • Health Informatics


Dive into the research topics of 'Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes'. Together they form a unique fingerprint.

Cite this