Strategies for Deploying Large Language Models for Ascertaining Clinical Outcomes and Sites of Metastases From Radiology Impressions in Patients With Cancer

作者：Syed Arsalan Ahmed Naqvi, Irbaz Bin Riaz, Amir Saeidi, Mihir Parmar, Atul Jain, Imon Banerjee, Chitta Baral, Kenneth L. Kehl · 发表于：JCO Clinical Cancer Informatics · 年份：2026 · DOI：10.1200/cci-25-00164 · 研究领域：Artificial Intelligence in Healthcare and Education、Radiomics and Machine Learning in Medical Imaging、Topic Modeling

PURPOSE To evaluate open-source large language models (LLMs) for extracting cancer-specific phenotypic data, benchmark their performance against GPT4 models, and assess the impact of fine-tuning with training data sizes. METHODS Open-source LLMs (Mistral, LLaMa, MAMBA, BioMistral) were evaluated in zero-/one-shot and fine-tuned setups against GPT4-turbo/GPT4o to extract the cancer presence, progression, response, and metastatic sites from radiology impressions of patients with solid tumors treated at Dana-Farber Cancer Institute. Performance metrics (accuracy, precision, recall, F1-score) were computed. McNemar's odds ratio (OR), measuring which model is more likely to be correct when they disagree, was computed with 95% CI. Statistical significance was assessed using the alpha of .000139. RESULTS This study included 2,623 patients (25,273 radiology impressions). In zero-/one-shot settings, GPT4-turbo/GPT4o outperformed open-source LLMs. However, fine-tuned open-source LLMs achieved higher F1-scores than GPT4 models. Compared with the best-performing GPT4 model, fine-tuned Mistral0.2-7.3B (OR, 0.27 [95% CI, 0.20 to 0.36]; P < .00001), Mistral0.3-7.3B (OR, 0.26 [95% CI, 0.19 to 0.36]; P < .00001), LLaMa2-6.7B (OR, 0.30 [95% CI, 0.22 to 0.40]; P < .00001), LLaMa3.1-8B (OR, 0.37 [95% CI, 0.28 to 0.48]; P < .00001), and MAMBA-2.8B (OR, 0.32 [95% CI, 0.24 to 0.42]; P < .00001) showed significantly better performance in ascertaining disease progression. Performance w...