Mapping layperson medical terminology into the Human Phenotype Ontology using neural machine translation models
作者：
Highlights：
• We propose a method to map lay expressions into the Human Phenotype Ontology.
• Inspired in machine translation we design different deep learning architectures.
• We explore strategies to encode the semantic space of the terms in the ontology.
• We evaluate several combinations of models, hyperparameters, and output embeddings.
• Overall, the correct term is identified for 80% of the lay terms in the test set.
摘要
•We propose a method to map lay expressions into the Human Phenotype Ontology.•Inspired in machine translation we design different deep learning architectures.•We explore strategies to encode the semantic space of the terms in the ontology.•We evaluate several combinations of models, hyperparameters, and output embeddings.•Overall, the correct term is identified for 80% of the lay terms in the test set.
论文关键词：Machine translation,Word embedding,Deep learning,Medical informatics,Deep phenotyping,Human Phenotype Ontology
论文评审过程：Received 2 November 2020, Revised 1 April 2022, Accepted 27 April 2022, Available online 6 May 2022, Version of Record 21 May 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117446
