Large language model trained on clinical oncology data predicts cancer progression

作者：Menglei Zhu, Hui Lin, Jue Jiang, Abbas J. Jinia, Justin Jee, Karl Pichotta, Michele Waters, Doori Rose, Nikolaus Schultz, Sulov Chalise, Lohit Valleru, Olivier Morin, Jean M. Moran, Joseph O. Deasy, Shirin Pilai, Chelsea Nichols, Gregory J. Riely, Lior Z. Braunstein, Anyi Li · 发表于：npj Digital Medicine · 年份：2025 · DOI：10.1038/s41746-025-01780-2 · 被引用次数：26 · 研究领域：Artificial Intelligence in Healthcare and Education、Radiomics and Machine Learning in Medical Imaging、AI in cancer detection

Subspecialty knowledge barriers have limited the adoption of large language models (LLMs) in oncology. We introduce Woollie, an open-source, oncology-specific LLM trained on real-world data from Memorial Sloan Kettering Cancer Center (MSK) across lung, breast, prostate, pancreatic, and colorectal cancers, with external validation using University of California, San Francisco (UCSF) data. Woollie surpasses ChatGPT in medical benchmarks and excels in eight non-medical benchmarks. Analyzing 39,319 radiology impression notes from 4002 patients, it achieved an overall area under the receiver operating characteristic curve (AUROC) of 0.97 for cancer progression prediction on MSK data, including a notable 0.98 AUROC for pancreatic cancer. On UCSF data, it achieved an overall AUROC of 0.88, excelling in lung cancer detection with an AUROC of 0.95. As the first oncology specific LLM validated across institutions, Woollie demonstrates high accuracy and consistency across cancer types, underscoring its potential to enhance cancer progression analysis.