• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

使用门控循环单元和SHAP可解释性为帕金森病患者提供个性化药物推荐。

Personalized medication recommendations for Parkinson's disease patients using gated recurrent units and SHAP interpretability.

作者信息

Riasi Atiye, Delrobaei Mehdi, Salari Mehri

机构信息

Department of Biomedical Engineering, Faculty of Electrical Engineering, K. N. Toosi University of Technology, Tehran, Iran.

Department of Mechatronics, Faculty of Electrical Engineering, K. N. Toosi University of Technology, Tehran, Iran.

出版信息

Sci Rep. 2025 May 30;15(1):19074. doi: 10.1038/s41598-025-04217-8.

DOI:10.1038/s41598-025-04217-8
PMID:40447777
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12125215/
Abstract

Managing Parkinson's disease (PD) through medication can be challenging due to varying symptoms and disease duration. This study aims to demonstrate the potential of sequence-by-sequence algorithms in recommending personalized medication combinations for patients with PD based on their previous visits. Our proposed method employs a gated recurrent unit model to predict accurate combinations of critical medication types for PD based on each patient's motor symptoms and prescribed medication from previous visits. We built a multi-label model with gated recurrent units on two data architectures: (1) personalized input using each patient's previous visits as a sample and (2) non-personalized input treating each visit as an independent sample. The 10-fold cross-validation results showed that the personalized architecture model outperforms the non-personalized model in accuracy (0.92), precision (0.94), recall (0.94), F1-score (0.94), Hamming loss (0.03), and macro average area under the receiver operating characteristic (0.94). To interpret the model's predictions, we employed SHapley Additive exPlanations (SHAP) values, which provide insights into the importance of variables both globally (across the entire model) and at the individual patient level. The results contribute to the sequential-based decision support system potentially enhancing the remote management of PD pharmacologic issues.

摘要

由于帕金森病(PD)症状各异且病程不同,通过药物治疗来管理该病具有挑战性。本研究旨在证明序列到序列算法在根据帕金森病患者的既往就诊情况推荐个性化药物组合方面的潜力。我们提出的方法采用门控循环单元模型,根据每位患者的运动症状和既往就诊时开具的药物,预测帕金森病关键药物类型的准确组合。我们在两种数据架构上构建了带有门控循环单元的多标签模型:(1)使用每位患者的既往就诊情况作为样本的个性化输入,以及(2)将每次就诊视为独立样本的非个性化输入。10倍交叉验证结果表明,个性化架构模型在准确率(0.92)、精确率(0.94)、召回率(0.94)、F1分数(0.94)、汉明损失(0.03)以及接收器操作特征曲线下的宏平均面积(0.94)方面均优于非个性化模型。为了解释模型的预测结果,我们采用了夏普利值(SHapley Additive exPlanations,SHAP),它能从全局(整个模型)和个体患者层面深入了解变量的重要性。这些结果有助于基于序列的决策支持系统潜在地加强帕金森病药物问题的远程管理。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/ab4b380ef4b9/41598_2025_4217_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/6ccddb7e1277/41598_2025_4217_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/dd7744dbe93f/41598_2025_4217_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/1bc54e081722/41598_2025_4217_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/3b78ececd445/41598_2025_4217_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/ab4b380ef4b9/41598_2025_4217_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/6ccddb7e1277/41598_2025_4217_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/dd7744dbe93f/41598_2025_4217_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/1bc54e081722/41598_2025_4217_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/3b78ececd445/41598_2025_4217_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a915/12125215/ab4b380ef4b9/41598_2025_4217_Fig5_HTML.jpg

相似文献

1
Personalized medication recommendations for Parkinson's disease patients using gated recurrent units and SHAP interpretability.使用门控循环单元和SHAP可解释性为帕金森病患者提供个性化药物推荐。
Sci Rep. 2025 May 30;15(1):19074. doi: 10.1038/s41598-025-04217-8.
2
Supervised Machine Learning Models for Predicting Sepsis-Associated Liver Injury in Patients With Sepsis: Development and Validation Study Based on a Multicenter Cohort Study.用于预测脓毒症患者脓毒症相关肝损伤的监督式机器学习模型:基于多中心队列研究的开发与验证研究
J Med Internet Res. 2025 May 26;27:e66733. doi: 10.2196/66733.
3
Development and validation of a machine learning-based diagnostic model for Parkinson's disease in community-dwelling populations: Evidence from the China health and retirement longitudinal study (CHARLS).基于机器学习的社区居住人群帕金森病诊断模型的开发与验证:来自中国健康与养老追踪调查(CHARLS)的证据
Parkinsonism Relat Disord. 2025 Jan;130:107182. doi: 10.1016/j.parkreldis.2024.107182. Epub 2024 Oct 30.
4
A decision support system based on recurrent neural networks to predict medication dosage for patients with Parkinson's disease.基于循环神经网络的帕金森病患者药物剂量预测决策支持系统。
Sci Rep. 2024 Apr 10;14(1):8424. doi: 10.1038/s41598-024-59179-0.
5
Explainable artificial intelligence to diagnose early Parkinson's disease via voice analysis.通过语音分析实现可解释的人工智能以诊断早期帕金森病。
Sci Rep. 2025 Apr 5;15(1):11687. doi: 10.1038/s41598-025-96575-6.
6
Development and validation of an interpretable machine learning model for predicting in-hospital mortality for ischemic stroke patients in ICU.用于预测ICU中缺血性中风患者院内死亡率的可解释机器学习模型的开发与验证
Int J Med Inform. 2025 Jun;198:105874. doi: 10.1016/j.ijmedinf.2025.105874. Epub 2025 Mar 9.
7
Intelligent Prediction Platform for Sepsis Risk Based on Real-Time Dynamic Temporal Features: Design Study.基于实时动态时间特征的脓毒症风险智能预测平台:设计研究
JMIR Med Inform. 2025 May 30;13:e74940. doi: 10.2196/74940.
8
Explainable machine learning models based on multimodal time-series data for the early detection of Parkinson's disease.基于多模态时间序列数据的可解释机器学习模型用于帕金森病的早期检测。
Comput Methods Programs Biomed. 2023 Jun;234:107495. doi: 10.1016/j.cmpb.2023.107495. Epub 2023 Mar 23.
9
Decision Support for Medication Change of Parkinson's Disease Patients.帕金森病患者药物变更的决策支持
Comput Methods Programs Biomed. 2020 Nov;196:105552. doi: 10.1016/j.cmpb.2020.105552. Epub 2020 May 29.
10
Development and internal validation of machine learning models for personalized survival predictions in spinal cord glioma patients.机器学习模型在脊髓神经胶质瘤患者个体化生存预测中的开发和内部验证。
Spine J. 2024 Jun;24(6):1065-1076. doi: 10.1016/j.spinee.2024.02.002. Epub 2024 Feb 15.

本文引用的文献

1
A decision support system based on recurrent neural networks to predict medication dosage for patients with Parkinson's disease.基于循环神经网络的帕金森病患者药物剂量预测决策支持系统。
Sci Rep. 2024 Apr 10;14(1):8424. doi: 10.1038/s41598-024-59179-0.
2
Disease progression strikingly differs in research and real-world Parkinson's populations.在帕金森病的研究人群和现实世界人群中,疾病进展存在显著差异。
NPJ Parkinsons Dis. 2024 Mar 13;10(1):58. doi: 10.1038/s41531-024-00667-5.
3
Machine learning in medication prescription: A systematic review.
机器学习在药物处方中的应用:系统评价。
Int J Med Inform. 2023 Dec;180:105241. doi: 10.1016/j.ijmedinf.2023.105241. Epub 2023 Oct 20.
4
Artificial intelligence for dementia prevention.人工智能在预防痴呆中的应用。
Alzheimers Dement. 2023 Dec;19(12):5952-5969. doi: 10.1002/alz.13463. Epub 2023 Oct 14.
5
Artificial intelligence-based preventive, personalized and precision medicine for cardiovascular disease/stroke risk assessment in rheumatoid arthritis patients: a narrative review.基于人工智能的预防、个体化和精准医学在类风湿关节炎患者心血管疾病/中风风险评估中的应用:叙述性综述。
Rheumatol Int. 2023 Nov;43(11):1965-1982. doi: 10.1007/s00296-023-05415-1. Epub 2023 Aug 30.
6
Artificial Intelligence and Machine Learning Approaches to Facilitate Therapeutic Drug Management and Model-Informed Precision Dosing.人工智能和机器学习方法在促进治疗药物管理和模型指导的精准剂量方面的应用
Ther Drug Monit. 2023 Apr 1;45(2):143-150. doi: 10.1097/FTD.0000000000001078. Epub 2023 Feb 3.
7
Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda.疾病诊断中的人工智能:系统文献综述、综合框架及未来研究议程
J Ambient Intell Humaniz Comput. 2023;14(7):8459-8486. doi: 10.1007/s12652-021-03612-z. Epub 2022 Jan 13.
8
Artificial intelligence in drug discovery: applications and techniques.人工智能在药物发现中的应用与技术。
Brief Bioinform. 2022 Jan 17;23(1). doi: 10.1093/bib/bbab430.
9
Artificial Intelligence Surgery: How Do We Get to Autonomous Actions in Surgery?人工智能手术:我们如何实现手术中的自主操作?
Sensors (Basel). 2021 Aug 17;21(16):5526. doi: 10.3390/s21165526.
10
Application of Big Data and Artificial Intelligence in COVID-19 Prevention, Diagnosis, Treatment and Management Decisions in China.大数据和人工智能在中国 COVID-19 预防、诊断、治疗和管理决策中的应用。
J Med Syst. 2021 Jul 24;45(9):84. doi: 10.1007/s10916-021-01757-0.