Training a Convolutional Neural Network with Terminology Summarization Data Improves SNOMED CT Enrichment

Ling Zheng, Hao Liu, Yehoshua Perl, James Geller

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

As a step toward learning to automatically insert new concepts into a large biomedical ontology, we are studying the easier problem of automatically verifying that an IS-A link should exist between a new child concept and an existing parent concept. We are using a Convolutional Neural Network, a powerful machine learning method. However, results depend on the quality of the training data. We use SNOMED CT (July 2017) for training and the subsequent release for testing. The main problem is to find a good set of negative training data. We experiment with two approaches, based on uncle-nephew (not connected) pairs of concepts. We contrast using the complete Clinical Finding hierarchy of SNOMED CT with using the powerful Area Taxonomy ontology summarization mechanism to constrain the training data. The results for the task of verifying IS-A links are improved by 8.6% when going from the complete hierarchy to the Area Taxonomy.

Original languageEnglish (US)
Pages (from-to)972-981
Number of pages10
JournalAMIA ... Annual Symposium proceedings. AMIA Symposium
Volume2019
StatePublished - 2019

All Science Journal Classification (ASJC) codes

  • Medicine(all)

Fingerprint Dive into the research topics of 'Training a Convolutional Neural Network with Terminology Summarization Data Improves SNOMED CT Enrichment'. Together they form a unique fingerprint.

Cite this