Ontology-Constrained Generation of Domain-Specific Clinical Summaries

TL;DR

This paper introduces an ontology-guided constrained decoding method for generating domain-specific clinical summaries from EHRs, reducing hallucinations and improving relevance in medical text summarization.

Contribution

It presents a novel ontology-constrained decoding approach that enhances domain-specific summarization and minimizes hallucinations in clinical text generation.

Findings

Improved relevance in medical summaries

Reduced hallucination in generated content

Effective on MIMIC-III dataset

Abstract

Large Language Models (LLMs) offer promising solutions for text summarization. However, some domains require specific information to be available in the summaries. Generating these domain-adapted summaries is still an open challenge. Similarly, hallucinations in generated content is a major drawback of current approaches, preventing their deployment. This study proposes a novel approach that leverages ontologies to create domain-adapted summaries both structured and unstructured. We employ an ontology-guided constrained decoding process to reduce hallucinations while improving relevance. When applied to the medical domain, our method shows potential in summarizing Electronic Health Records (EHRs) across different specialties, allowing doctors to focus on the most relevant information to their domain. Evaluation on the MIMIC-III dataset demonstrates improvements in generating domain-adapted summaries of clinical notes and hallucination reduction.