提取癌症症状文档使临床医生能够开发高度个性化的症状预测算法来提供症状管理护理。利用先进的语言模型来检测临床叙述中的症状数据可以显着增强这一过程。本研究使用预先训练的大型语言模型来检测和提取临床记录中的癌症症状。我们开发了一种预先训练的语言模型来识别临床记录中的癌症症状基于美国中西部医疗保健系统研究企业数据仓库的临床语料库的临床记录。这项研究分 4 个阶段进行：1 在 100 万份未标记的临床文档上预训练生物临床 BERT 模型，2 微调 Symptom-BERT 以检测 1112 个带注释的临床记录中的 13 个癌症症状组，3 生成 180 个综合临床记录使用 ChatGPT-4 进行外部验证，4 将 Symptom-BERT 与非预训练版本和其他六个 BERT 实现的内部和外部性能进行比较。Symptom-BERT 模型有效地检测了临床记录中的癌症症状。它的微平均 F1 分数为 0.933，内部 AUC 为 0.929，外部为 0.831 和 0.834。我们的分析表明，瘙痒等身体症状通常比焦虑等心理症状具有更高的性能。这项研究强调了对特定领域数据进行专门预训练在提高医疗应用语言模型性能方面的变革潜力。 Symptom-BERT 模型在检测癌症症状方面的卓越功效预示着以患者为中心的 AI 技术的突破性进展，为提升症状管理和培养卓越的患者自我护理结果提供了一条充满希望的道路。版权所有 © 2024。由 Elsevier Inc. 出版。

Extracting cancer symptom documentation allows clinicians to develop highly individualized symptom prediction algorithms to deliver symptom management care. Leveraging advanced language models to detect symptom data in clinical narratives can significantly enhance this process.This study uses a pre-trained large language model to detect and extract cancer symptoms in clinical notes.We developed a pre-trained language model to identify cancer symptoms in clinical notes based on a clinical corpus from the Enterprise Data Warehouse for Research at a healthcare system in the Midwestern United States. This study was conducted in 4 phases:1 pre-training a Bio-Clinical BERT model on 1 million unlabeled clinical documents,2 fine-tuning Symptom-BERT for detecting 13 cancer symptom groups within 1112 annotated clinical notes,3 generating 180 synthetic clinical notes using ChatGPT-4 for external validation, and4 comparing the internal and external performance of Symptom-BERT against a non-pre-trained version and six other BERT implementations.The Symptom-BERT model effectively detected cancer symptoms in clinical notes. It achieved results with a micro-averaged F1-score of 0.933, an AUC of 0.929 internally, and 0.831 and 0.834 externally. Our analysis shows that physical symptoms, like Pruritus, are typically identified with higher performance than psychological symptoms, such as Anxiety.This study underscores the transformative potential of specialized pre-training on domain-specific data in boosting the performance of language models for medical applications. The Symptom-BERT model's exceptional efficacy in detecting cancer symptoms heralds a groundbreaking stride in patient-centered AI technologies, offering a promising path to elevate symptom management and cultivate superior patient self-care outcomes.Copyright © 2024. Published by Elsevier Inc.