Can Large Language Models Augment a Biomedical Ontology with missing Concepts and Relations?

TL;DR

This paper investigates using large language models to semi-automatically expand biomedical ontologies by identifying missing concepts and relations, demonstrated on SNOMED-CT with promising initial results.

Contribution

It introduces a novel method leveraging conversational LLMs to detect new medical concepts and relationships in clinical guidelines for ontology augmentation.

Findings

Initial experiments show promising results with manual gold standards.

The approach effectively identifies missing concepts and relations.

Future improvements are directed by preliminary success.

Abstract

Ontologies play a crucial role in organizing and representing knowledge. However, even current ontologies do not encompass all relevant concepts and relationships. Here, we explore the potential of large language models (LLM) to expand an existing ontology in a semi-automated fashion. We demonstrate our approach on the biomedical ontology SNOMED-CT utilizing semantic relation types from the widely used UMLS semantic network. We propose a method that uses conversational interactions with an LLM to analyze clinical practice guidelines (CPGs) and detect the relationships among the new medical concepts that are not present in SNOMED-CT. Our initial experimentation with the conversational prompts yielded promising preliminary results given a manually generated gold standard, directing our future potential improvements.