Large language model trained on clinical oncology data predicts cancer progression Journal Article
| Authors: | Zhu, M.; Lin, H.; Jiang, J.; Jinia, A. J.; Jee, J.; Pichotta, K.; Waters, M.; Rose, D.; Schultz, N.; Chalise, S.; Valleru, L.; Morin, O.; Moran, J.; Deasy, J. O.; Pilai, S.; Nichols, C.; Riely, G.; Braunstein, L. Z.; Li, A. |
| Article Title: | Large language model trained on clinical oncology data predicts cancer progression |
| Abstract: | 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. © The Author(s) 2025. |
| Keywords: | major clinical study; cancer growth; cancer patient; pancreas cancer; cancer diagnosis; diagnostic accuracy; colorectal cancer; breast cancer; lung cancer; oncology; prostate cancer; health care; kettering; biological organs; diseases; california; cancer progression; san francisco; clinical oncology; receiver operating characteristic curves; real-world; human; article; university of california; malignant neoplasm; open-source; language model; large language model; chatgpt; knowledge barriers |
| Journal Title: | npj Digital Medicine |
| Volume: | 8 |
| ISSN: | 2398-6352 |
| Publisher: | Nature Publishing Group |
| Date Published: | 2025-07-02 |
| Start Page: | 397 |
| Language: | English |
| DOI: | 10.1038/s41746-025-01780-2 |
| PROVIDER: | scopus |
| PMCID: | PMC12223279 |
| PUBMED: | 40604229 |
| DOI/URL: | |
| Notes: | The MSK Cancer Center Support Grant (P30 CA008748) is acknowledged in the PubMed record and PDF. Corresponding MSK authors are Lior Z. Braunstein and Anyi Li -- Shirin Pillai's last name is misspelled in the publication -- Source: Scopus |
