Prompt Configurations for Multimodal Large Language Models in Diagnosing and Staging Osteonecrosis of the Femoral Head: Multimodel Retrospective Observational Diagnostic Study

作者：Jiesheng Zhu, Xingxing Huang, Jincheng Shi, Shaoming Chen, Daosen Chen, Zhihan Gao, Yi Lu, Tao Yang, Xue Wang, Yimu Lin, Peiyu Xu, Li Li, Pei Fan · 发表于：Journal of Medical Internet Research · 年份：2026 · DOI：10.2196/92919 · 研究领域：Medicine

Abstract Background Multimodal large language models (MLLMs) have emerging potential for interpreting medical images and text, but their performance in orthopedic imaging tasks and the influence of prompt configuration remain insufficiently studied. Objective This study aimed to evaluate the performance of commercial and open-source MLLMs for diagnosing and staging osteonecrosis of the femoral head (ONFH) and to assess how different prompt configurations affect model performance. Methods This single-center retrospective diagnostic accuracy study included 159 radiograph patients contributing 318 hip-level observations and 170 magnetic resonance imaging (MRI) patients contributing 340 hip-level observations; 55 patients with both modalities formed the multi-image (MI) subgroup between July 2023 and December 2024. Four MLLMs were evaluated: GPT-4o, Claude 3.7 Sonnet, Qwen2.5-VL 72B, and Gemma 3 27B. Three prompt configurations were tested: single image (SI), image plus radiology description (ID), and MI. Model performance was assessed for ONFH detection; early- versus late-stage differentiation; detailed grading using the Ficat, Association Research Circulation Osseous (ARCO), and Steinberg systems; and grading reliability using intraclass correlation coefficients (ICCs). Results Model performance varied by prompt configuration and imaging input. For ONFH detection, the SI configuration yielded a mean detection area under the receiver operating characteristic curve (AUC) of 0.55...