arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.07166cs.AI
收藏

自然语言辅助的多模态药物推荐

Natural Language-Assisted Multi-modal Medication Recommendation

The Chinese University of Hong Kong（香港中文大学）；DAMO Academy, Alibaba Group（阿里巴巴达摩院）；Beijing Institute of Technology（北京理工大学）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）

Jie Tan, Yu Rong, Kangfei Zhao, Tian Bian, Tingyang Xu, Junzhou Huang, Hong Cheng, Helen Meng

备注：
10 pages
发表信息：
Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, Boise, ID, USA, 2024
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有组合药物推荐方法忽略药物文本说明、未充分利用EHR文本知识的问题，提出多模态对齐框架NLA-MMR，通过预训练语言模型提取患者与药物的领域知识并实现模态对齐，在三个公开数据集上取得SOTA性能，Jaccard系数平均提升4.72%。

摘要：

组合药物推荐（CMR）是医疗健康领域的一项基础任务，它为临床医生给病情复杂的患者开具更精准的处方提供了可能，尤其是在长期医疗护理场景中。此前的研究工作尝试从电子健康记录（EHRs）中提取有效信息，以助力组合药物推荐。现有的基于学习的方法进一步考虑了药物的化学结构，但忽略了明确描述药物功能的文本药物说明。此外，从患者电子健康记录中提取的文本知识在很大程度上仍未得到充分利用。为解决这些问题，我们提出了自然语言辅助多模态药物推荐（NLA-MMR），这是一种多模态对齐框架，旨在同时从患者视角和药物视角学习知识。具体而言，NLA-MMR将组合药物推荐建模为患者模态与药物模态之间的对齐问题。按照这一思路，我们采用预训练语言模型（PLMs）提取与患者和药物相关的领域内知识，作为两种模态的基础表征。在药物模态中，我们同时利用化学结构和文本描述来生成药物表征。在患者模态中，我们基于诊断、手术操作和症状的文本描述生成患者表征。在三个公开数据集上开展的大量实验表明，NLA-MMR取得了新的最优性能，其Jaccard系数平均提升了4.72%，效果显著。我们的源代码已公开在https://github.com/jtan1102/NLA-MMR_CIKM_2024上。

英文摘要：

Combinatorial medication recommendation(CMR) is a fundamental task of healthcare, which offers opportunities for clinical physicians to provide more precise prescriptions for patients with intricate health conditions, particularly in the scenarios of long-term medical care. Previous research efforts have sought to extract meaningful information from electronic health records (EHRs) to facilitate combinatorial medication recommendations. Existing learning-based approaches further consider the chemical structures of medications, but ignore the textual medication descriptions in which the functionalities are clearly described. Furthermore, the textual knowledge derived from the EHRs of patients remains largely underutilized. To address these issues, we introduce the Natural Language-Assisted Multi-modal Medication Recommendation(NLA-MMR), a multi-modal alignment framework designed to learn knowledge from the patient view and medication view jointly. Specifically, NLA-MMR formulates CMR as an alignment problem from patient and medication modalities. In this vein, we employ pretrained language models(PLMs) to extract in-domain knowledge regarding patients and medications, serving as the foundational representation for both modalities. In the medication modality, we exploit both chemical structures and textual descriptions to create medication representations. In the patient modality, we generate the patient representations based on textual descriptions of diagnosis, procedure, and symptom. Extensive experiments conducted on three publicly accessible datasets demonstrate that NLA-MMR achieves new state-of-the-art performance, with a notable average improvement of 4.72% in Jaccard score. Our source code is publicly available on https://github.com/jtan1102/NLA-MMR_CIKM_2024.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑