Improving Diagnostic Accuracy in Preoperative Glioma Classification: Performance of Knowledge-Enhanced Large Language Models Compared With Radiologists

Authors

Shuang Li
Xin Fang
Yuqi Jin
YuJiao Deng
Wei Hu
Bing Wu
Xiaobo Zhou
Guotai Wang
Kang Li
Qiang Yue

Language

English

Publication Date

11-27-2025

Journal

npj Precision Oncology

DOI

10.1038/s41698-025-01171-6

PMID

41310391

PMCID

PMC12660956

PubMedCentral® Posted Date

11-27-2025

PubMedCentral® Full Text Version

Post-print

Abstract

Accurate preoperative MRI classification of gliomas is essential but challenging due to complex radiological features and inter-observer variability. This study evaluated three large language models (LLMs) for VASARI-based glioma classification compared to radiologist interpretations. We retrospectively analyzed 150 histopathologically confirmed gliomas (43 circumscribed astrocytic, 53 high-grade diffuse, 54 low-grade diffuse gliomas) using standardized MRI protocols. Three radiologists extracted VASARI features, while three LLMs (GPT-4, Claude3.5-Sonnet, Claude3.0-Opus) analyzed these features using standard input-output or knowledge-enhanced prompting incorporating diagnostic guidelines. Knowledge-enhanced prompting consistently outperformed standard prompting, improving diagnostic consistency (intra-model agreement: Sonnet κ = 0.91, Opus κ = 0.92, GPT-4 κ = 0.72). For diffuse versus circumscribed classification, senior radiologists (AUC = 0.88) and Claude3.5-Sonnet with knowledge-enhanced prompting (AUC = 0.84) performed similarly (p > 0.05). LLM assistance significantly improved junior radiologists' performance, with AUC increases from 0.77 to 0.83 (p = 0.026). Knowledge-enhanced LLMs demonstrate diagnostic performance comparable to experienced radiologists and improve junior accuracy, suggesting potential as decision-support tools requiring radiologist oversight.

Keywords

Cancer, Medical research, Neurology, Neuroscience, Oncology

Published Open-Access

yes

Recommended Citation

Li, Shuang; Fang, Xin; Jin, Yuqi; et al., "Improving Diagnostic Accuracy in Preoperative Glioma Classification: Performance of Knowledge-Enhanced Large Language Models Compared With Radiologists" (2025). Faculty, Staff and Student Publications. 819.
https://digitalcommons.library.tmc.edu/uthshis_docs/819