• 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

机器学习在帕金森病计算机辅助诊断中的应用：进展与基准案例研究

Applications of machine learning for computer-aided diagnosis of Parkinson's disease: progress and benchmark case study.

作者信息

Zhang Juntao, Zhang Yiming, Weng Ying, Hosseini Akram A, Wang Boding, Dening Tom, Fan Weinyu, Xiao Weizhong

机构信息

School of Computer Science, University of Nottingham Ningbo China, Ningbo, 315100 China.

School of Computer Science, University of Nottingham, Nottingham, NG8 1BB UK.

出版信息

Artif Intell Rev. 2025;58(11):357. doi: 10.1007/s10462-025-11347-y. Epub 2025 Aug 29.

DOI:10.1007/s10462-025-11347-y
PMID:40895221
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12397128/
Abstract

Machine learning (ML) has emerged as a vital tool for the diagnosis of Parkinson's Disease (PD). This study presents a comprehensive review on the applications of ML for computer-aided diagnosis (CAD) of PD. We conducted a comprehensive review by searching articles published from 2010 till 2024. The risk of bias is assessed using the PROBAST checklist. Case studies are also provided. This review includes 117 articles with six categories: neuroimaging data (20.5%); voice data (40.2%); handwriting data (12.0%); gait data (14.5%); EEG data (8.5%); and other data (4.3%). According to the PROBAST checklist, only 28 articles (23.9%) have a low risk of bias. A benchmark case study is conducted for five different data modalities. We also discuss current limitations and future directions of applying ML to the diagnosis of PD. This review reduces the gap between Artificial Intelligence (AI) and PD medical professionals and provides helpful information for future research.

摘要

机器学习（ML）已成为诊断帕金森病（PD）的重要工具。本研究对ML在PD计算机辅助诊断（CAD）中的应用进行了全面综述。我们通过检索2010年至2024年发表的文章进行了全面综述。使用PROBAST清单评估偏倚风险。还提供了案例研究。本综述包括117篇文章，分为六类：神经影像数据（20.5%）；语音数据（40.2%）；笔迹数据（12.0%）；步态数据（14.5%）；脑电图数据（8.5%）；以及其他数据（4.3%）。根据PROBAST清单，只有28篇文章（23.9%）的偏倚风险较低。针对五种不同的数据模式进行了基准案例研究。我们还讨论了将ML应用于PD诊断的当前局限性和未来方向。本综述缩小了人工智能（AI）与PD医学专业人员之间的差距，并为未来研究提供了有用信息。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/faa3e3343fc3/10462_2025_11347_Fig15_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/a4de470024d7/10462_2025_11347_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/b99ebf22f462/10462_2025_11347_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/ec083848fa74/10462_2025_11347_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/807b12c6cddf/10462_2025_11347_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/3b5233d6a116/10462_2025_11347_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/7ec57c9d231a/10462_2025_11347_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/3ad8876706ee/10462_2025_11347_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/707e55430cc2/10462_2025_11347_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/42a61e859cec/10462_2025_11347_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/293c0f78f99d/10462_2025_11347_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/74eb742c79a7/10462_2025_11347_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/c7480c6050b1/10462_2025_11347_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/0404701d47b6/10462_2025_11347_Fig13_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/0f99621ae97f/10462_2025_11347_Fig14_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/faa3e3343fc3/10462_2025_11347_Fig15_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/a4de470024d7/10462_2025_11347_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/b99ebf22f462/10462_2025_11347_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/ec083848fa74/10462_2025_11347_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/807b12c6cddf/10462_2025_11347_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/3b5233d6a116/10462_2025_11347_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/7ec57c9d231a/10462_2025_11347_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/3ad8876706ee/10462_2025_11347_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/707e55430cc2/10462_2025_11347_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/42a61e859cec/10462_2025_11347_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/293c0f78f99d/10462_2025_11347_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/74eb742c79a7/10462_2025_11347_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/c7480c6050b1/10462_2025_11347_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/0404701d47b6/10462_2025_11347_Fig13_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/0f99621ae97f/10462_2025_11347_Fig14_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/cfc3/12397128/faa3e3343fc3/10462_2025_11347_Fig15_HTML.jpg

相似文献

1
Applications of machine learning for computer-aided diagnosis of Parkinson's disease: progress and benchmark case study.机器学习在帕金森病计算机辅助诊断中的应用：进展与基准案例研究
Artif Intell Rev. 2025;58(11):357. doi: 10.1007/s10462-025-11347-y. Epub 2025 Aug 29.
2
Physical exercise for people with Parkinson's disease: a systematic review and network meta-analysis.帕金森病患者的体育锻炼：系统评价与网状Meta分析
Cochrane Database Syst Rev. 2024 Apr 8;4(4):CD013856. doi: 10.1002/14651858.CD013856.pub3.
3
Physical exercise for people with Parkinson's disease: a systematic review and network meta-analysis.帕金森病患者的身体锻炼：系统评价和网络荟萃分析。
Cochrane Database Syst Rev. 2023 Jan 5;1(1):CD013856. doi: 10.1002/14651858.CD013856.pub2.
4
Prescription of Controlled Substances: Benefits and Risks管制药品的处方：益处与风险
5
Parkinson disease detection based on in-air dynamics feature extraction and selection using machine learning.基于机器学习的空中动力学特征提取与选择的帕金森病检测
Sci Rep. 2025 Jul 31;15(1):28027. doi: 10.1038/s41598-025-12115-2.
6
A Scoping Review of AI/ML Algorithm Updating Practices for Model Continuity and Patient Safety Using a Simplified Checklist.使用简化清单对用于模型连续性和患者安全的人工智能/机器学习算法更新实践的范围审查
Stud Health Technol Inform. 2025 Aug 7;329:809-813. doi: 10.3233/SHTI250952.
7
Research status, hotspots and perspectives of artificial intelligence applied to pain management: a bibliometric and visual analysis.人工智能应用于疼痛管理的研究现状、热点与展望：一项文献计量学与可视化分析
Updates Surg. 2025 Jun 28. doi: 10.1007/s13304-025-02296-w.
8
A systematic review of artificial intelligence techniques based on electroencephalography analysis in the diagnosis of epilepsy disorders: A clinical perspective.基于脑电图分析的人工智能技术在癫痫疾病诊断中的系统评价：临床视角
Epilepsy Res. 2025 May 16;215:107582. doi: 10.1016/j.eplepsyres.2025.107582.
9
Applied Machine Learning Techniques to Diagnose Voice-Affecting Conditions and Disorders: Systematic Literature Review.应用机器学习技术诊断嗓音影响条件和障碍：系统文献回顾。
J Med Internet Res. 2023 Jul 19;25:e46105. doi: 10.2196/46105.
10
The Use of Deep Learning and Machine Learning on Longitudinal Electronic Health Records for the Early Detection and Prevention of Diseases: Scoping Review.深度学习和机器学习在纵向电子健康记录中用于疾病的早期检测和预防的应用：范围综述。
J Med Internet Res. 2024 Aug 20;26:e48320. doi: 10.2196/48320.

本文引用的文献

1
Deep learning-integrated MRI brain tumor analysis: feature extraction, segmentation, and Survival Prediction using Replicator and volumetric networks.深度学习集成的MRI脑肿瘤分析：使用复制器和体积网络进行特征提取、分割和生存预测。
Sci Rep. 2025 Jan 9;15(1):1437. doi: 10.1038/s41598-024-84386-0.
2
LSTM-CNN: An efficient diagnostic network for Parkinson's disease utilizing dynamic handwriting analysis.长短期记忆网络-卷积神经网络：一种利用动态笔迹分析诊断帕金森病的高效诊断网络。
Comput Methods Programs Biomed. 2024 Apr;247:108066. doi: 10.1016/j.cmpb.2024.108066. Epub 2024 Feb 9.
3
Dual-3DMAD: Mixed Transformer Based Semantic Segmentation and Triplet Pre-Processing for Early Multi-Class Alzheimer's Diagnosis.
双重 3DMAD：基于混合 Transformer 的语义分割和三重预处理的早期多类阿尔茨海默病诊断。
IEEE Trans Neural Syst Rehabil Eng. 2024;32:696-707. doi: 10.1109/TNSRE.2024.3357723. Epub 2024 Feb 8.
4
Diagnostic performance of artificial intelligence-assisted PET imaging for Parkinson's disease: a systematic review and meta-analysis.人工智能辅助正电子发射断层显像（PET）成像对帕金森病的诊断效能：一项系统评价和Meta分析
NPJ Digit Med. 2024 Jan 22;7(1):17. doi: 10.1038/s41746-024-01012-z.
5
An interpretable model based on graph learning for diagnosis of Parkinson's disease with voice-related EEG.一种基于图学习的可解释模型，用于通过与语音相关的脑电图诊断帕金森病。
NPJ Digit Med. 2024 Jan 5;7(1):3. doi: 10.1038/s41746-023-00983-9.
6
Machine Learning in the Parkinson's disease smartwatch (PADS) dataset.帕金森病智能手表（PADS）数据集中的机器学习
NPJ Parkinsons Dis. 2024 Jan 5;10(1):9. doi: 10.1038/s41531-023-00625-7.
7
Integrative gene expression analysis for the diagnosis of Parkinson's disease using machine learning and explainable AI.基于机器学习和可解释人工智能的帕金森病诊断的综合基因表达分析。
Comput Biol Med. 2023 Sep;163:107140. doi: 10.1016/j.compbiomed.2023.107140. Epub 2023 Jun 8.
8
Diagnosis and classification of Parkinson's disease using ensemble learning and 1D-PDCovNN.使用集成学习和 1D-PDCovNN 对帕金森病进行诊断和分类。
Comput Biol Med. 2023 Jul;161:107031. doi: 10.1016/j.compbiomed.2023.107031. Epub 2023 May 17.
9
Detection of mild cognitive impairment in Parkinson's disease using gradient boosting decision tree models based on multilevel DTI indices.基于多层次 DTI 指标的梯度提升决策树模型在帕金森病轻度认知障碍检测中的应用。
J Transl Med. 2023 May 8;21(1):310. doi: 10.1186/s12967-023-04158-8.
10
Explainable classification of Parkinson's disease using deep learning trained on a large multi-center database of T1-weighted MRI datasets.利用基于 T1 加权 MRI 数据集的大型多中心数据库训练的深度学习对帕金森病进行可解释分类。
Neuroimage Clin. 2023;38:103405. doi: 10.1016/j.nicl.2023.103405. Epub 2023 Apr 17.