Ontology-Constrained Generation of Domain-Specific Clinical Summaries
This addresses the challenge of producing accurate, domain-adapted summaries for medical professionals, though it appears incremental as it builds on existing LLM and ontology-based approaches.
The study tackled the problem of generating domain-specific clinical summaries from Electronic Health Records by proposing an ontology-constrained decoding method, which improved relevance and reduced hallucinations in summaries on the MIMIC-III dataset.
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.