Logo image
Interpretable Cancer Staging Using Knowledge Elicitation in Large Language Models
Conference proceeding

Interpretable Cancer Staging Using Knowledge Elicitation in Large Language Models

Yeawon Lee
Proceedings (IEEE International Conference on Healthcare Informatics. Online), pp 654-654
18 Jun 2025

Abstract

Cancer Cancer Stage Knowledge Elicitation Large language models Medical services Pathology Reports Planning Prognostics and health management Retrieval augmented generation Informatics Pathology
Cancer staging is critical for patient prognosis and treatment planning, yet extracting pathologic TNM staging from unstructured pathology reports is challenging. In this study, we introduce two LLM-based knowledge elicitation methods-one using a Long-Term Memory approach (KEwLTM) and another employing Retrieval-Augmented Generation (KEwRAG)-to enable large language models (LLMs) to induce domain-specific rules for cancer staging.

Metrics

1 Record Views

Details

Logo image