Incorporating large language models as clinical decision support in oncology: the Woollie model

Integrating large language models (LLMs) into oncology holds promise for clinical decision support. Woollie is an LLM recently developed by Zhu et al., fine-tuned using radiology impression notes from Memorial Sloan Kettering Cancer Center and externally validated on UCSF oncology datasets. This met...

Full description

Saved in:
Bibliographic Details
Main Authors: Kimia Heydari, Elizabeth J. Enichen, Ben Li, Joseph C. Kvedar
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01941-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225903435939840
author Kimia Heydari
Elizabeth J. Enichen
Ben Li
Joseph C. Kvedar
author_facet Kimia Heydari
Elizabeth J. Enichen
Ben Li
Joseph C. Kvedar
author_sort Kimia Heydari
collection DOAJ
description Integrating large language models (LLMs) into oncology holds promise for clinical decision support. Woollie is an LLM recently developed by Zhu et al., fine-tuned using radiology impression notes from Memorial Sloan Kettering Cancer Center and externally validated on UCSF oncology datasets. This methodology prioritizes data accuracy, preempts catastrophic forgetting, and demonstrates unparalleled rigor in predicting the progression of various cancer types. This work establishes a foundation for reliable, scalable, and equitable applications of LLMs in oncology.
format Article
id doaj-art-458b0de4ed144c24aa840fbfabfdfc53
institution Kabale University
issn 2398-6352
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-458b0de4ed144c24aa840fbfabfdfc532025-08-24T11:51:57ZengNature Portfolionpj Digital Medicine2398-63522025-08-01811210.1038/s41746-025-01941-3Incorporating large language models as clinical decision support in oncology: the Woollie modelKimia Heydari0Elizabeth J. Enichen1Ben Li2Joseph C. Kvedar3Harvard Medical SchoolHarvard Medical SchoolDivision of Vascular Surgery, University of TorontoHarvard Medical SchoolIntegrating large language models (LLMs) into oncology holds promise for clinical decision support. Woollie is an LLM recently developed by Zhu et al., fine-tuned using radiology impression notes from Memorial Sloan Kettering Cancer Center and externally validated on UCSF oncology datasets. This methodology prioritizes data accuracy, preempts catastrophic forgetting, and demonstrates unparalleled rigor in predicting the progression of various cancer types. This work establishes a foundation for reliable, scalable, and equitable applications of LLMs in oncology.https://doi.org/10.1038/s41746-025-01941-3
spellingShingle Kimia Heydari
Elizabeth J. Enichen
Ben Li
Joseph C. Kvedar
Incorporating large language models as clinical decision support in oncology: the Woollie model
npj Digital Medicine
title Incorporating large language models as clinical decision support in oncology: the Woollie model
title_full Incorporating large language models as clinical decision support in oncology: the Woollie model
title_fullStr Incorporating large language models as clinical decision support in oncology: the Woollie model
title_full_unstemmed Incorporating large language models as clinical decision support in oncology: the Woollie model
title_short Incorporating large language models as clinical decision support in oncology: the Woollie model
title_sort incorporating large language models as clinical decision support in oncology the woollie model
url https://doi.org/10.1038/s41746-025-01941-3
work_keys_str_mv AT kimiaheydari incorporatinglargelanguagemodelsasclinicaldecisionsupportinoncologythewoolliemodel
AT elizabethjenichen incorporatinglargelanguagemodelsasclinicaldecisionsupportinoncologythewoolliemodel
AT benli incorporatinglargelanguagemodelsasclinicaldecisionsupportinoncologythewoolliemodel
AT josephckvedar incorporatinglargelanguagemodelsasclinicaldecisionsupportinoncologythewoolliemodel