2025-03-05 ワシントン大学セントルイス校 (WashU)
<関連情報>
- https://source.washu.edu/2025/03/foundation-ai-model-predicts-postoperative-risks-from-clinical-notes/
- https://www.nature.com/articles/s41746-025-01489-2
クリニカルノートを用いた術後リスク予測における大規模言語モデルの基礎的能力 The foundational capabilities of large language models in predicting postoperative risks using clinical notes
Charles Alba,Bing Xue,Joanna Abraham,Thomas Kannampallil & Chenyang Lu
npj Digital Medicine Published:11 February 2025
DOI:https://doi.org/10.1038/s41746-025-01489-2
Abstract
Clinical notes recorded during a patient’s perioperative journey holds immense informational value. Advances in large language models (LLMs) offer opportunities for bridging this gap. Using 84,875 preoperative notes and its associated surgical cases from 2018 to 2021, we examine the performance of LLMs in predicting six postoperative risks using various fine-tuning strategies. Pretrained LLMs outperformed traditional word embeddings by an absolute AUROC of 38.3% and AUPRC of 33.2%. Self-supervised fine-tuning further improved performance by 3.2% and 1.5%. Incorporating labels into training further increased AUROC by 1.8% and AUPRC by 2%. The highest performance was achieved with a unified foundation model, with improvements of 3.6% for AUROC and 2.6% for AUPRC compared to self-supervision, highlighting the foundational capabilities of LLMs in predicting postoperative risks, which could be potentially beneficial when deployed for perioperative care.
