Multi-Ontology Refined Embeddings (MORE): A Hybrid Multi-Ontology and Corpus-based Semantic Representation for Biomedical Concepts

TL;DR

This paper introduces MORE, a hybrid framework that combines multiple ontologies and corpus-based methods to improve semantic representations of biomedical concepts in clinical texts, enhancing NLP analysis accuracy.

Contribution

The paper presents a novel hybrid approach integrating multiple ontologies with corpus data and a new learning objective to generate more accurate biomedical concept embeddings.

Findings

MORE achieves higher correlation with expert similarity ratings than baseline models.

It outperforms existing ontology-based similarity measures in biomedical concept similarity tasks.

The approach improves semantic understanding in clinical NLP applications.

Abstract

Objective: Currently, a major limitation for natural language processing (NLP) analyses in clinical applications is that a concept can be referenced in various forms across different texts. This paper introduces Multi-Ontology Refined Embeddings (MORE), a novel hybrid framework for incorporating domain knowledge from multiple ontologies into a distributional semantic model, learned from a corpus of clinical text. Materials and Methods: We use the RadCore and MIMIC-III free-text datasets for the corpus-based component of MORE. For the ontology-based part, we use the Medical Subject Headings (MeSH) ontology and three state-of-the-art ontology-based similarity measures. In our approach, we propose a new learning objective, modified from the Sigmoid cross-entropy objective function. Results and Discussion: We evaluate the quality of the generated word embeddings using two established datasets of semantic similarities among biomedical concept pairs. On the first dataset with 29 concept pairs, with the similarity scores established by physicians and medical coders, MORE's similarity scores have the highest combined correlation (0.633), which is 5.0% higher than that of the baseline model and 12.4% higher than that of the best ontology-based similarity measure.On the second dataset with 449 concept pairs, MORE's similarity scores have a correlation of 0.481, with the average of four medical residents' similarity ratings, and that outperforms the skip-gram model by 8.1% and the best ontology measure by 6.9%.