Suppr超能文献

用于检测帕金森病前驱期的多模态诊断工具和先进数据模型:一项范围综述

Multimodal diagnostic tools and advanced data models for detection of prodromal Parkinson's disease: a scoping review.

作者信息

Serag Ibrahim, Azzam Ahmed Y, Hassan Amr K, Diab Rehab Adel, Diab Mohamed, Hefnawy Mahmoud Tarek, Ali Mohamed Ahmed, Negida Ahmed

机构信息

Faculty of Medicine, Mansoura University, Mansoura, Egypt.

Faculty of Medicine, October 6 University, Giza, Egypt.

出版信息

BMC Med Imaging. 2025 Mar 28;25(1):103. doi: 10.1186/s12880-025-01620-5.

Abstract

BACKGROUND

Parkinson's Disease (PD) is a progressive neurodegenerative disorder characterized by the loss of dopaminergic neurons in the substantia nigra pars compacta. PD is diagnosed by a combination of motor symptoms including bradykinesia, resting tremors, rigidity and postural instability. Prodromal PD is the stage preceding the onset of classic motor symptoms of PD. The diagnosis of prodromal PD remains challenging despite many available diagnostic modalities.

AIM

This scoping review aims to investigate and explore the current diagnostic modalities used to detect prodromal PD, focusing particularly on multimodal imaging analysis and AI-based approaches.

METHODS

We adhered to the PRISMA-SR guidelines for scoping reviews. We conducted a comprehensive literature search at multiple databases such as PubMed, Scopus, Web of Science, and the Cochrane Library from inception to July 2024, using keywords related to prodromal PD and diagnostic modalities. We included studies based on predefined inclusion and exclusion criteria and performed data extraction using a standardized form.

RESULTS

The search included 9 studies involving 567 patients with prodromal PD and 35,643 control. Studies utilized various diagnostic approaches including neuroimaging techniques and AI-driven models. sensitivity ranging from 43 to 84% and specificity up to 96%. Neuroimaging and AI technologies showed promising results in identifying early pathological changes and predicting PD onset. The highest specificity was achieved by neuromelanin-sensitive imaging model, while highest sensitivity was achieved by standard 10-s electrocardiogram (ECG) + Machine learning model.

CONCLUSION

Advanced diagnostic modalities such as AI-driven models and multimodal neuroimaging revealed promising results in early detection of prodromal PD. However, their clinical application as screening tool for prodromal PD is limited because of the lack of validation. Future research should be directed towards using Multimodal imaging in diagnosing and screening for prodromal PD.

CLINICAL TRIAL NUMBER

Not applicable.

摘要

背景

帕金森病(PD)是一种进行性神经退行性疾病,其特征是黑质致密部多巴胺能神经元丧失。PD通过运动症状的组合进行诊断,包括运动迟缓、静止性震颤、僵硬和姿势不稳。前驱期PD是PD典型运动症状出现之前的阶段。尽管有许多可用的诊断方法,但前驱期PD的诊断仍然具有挑战性。

目的

本范围综述旨在调查和探索用于检测前驱期PD的当前诊断方法,特别关注多模态成像分析和基于人工智能的方法。

方法

我们遵循PRISMA-SR范围综述指南。我们在多个数据库(如PubMed、Scopus、Web of Science和Cochrane图书馆)中进行了全面的文献检索,检索时间从数据库创建到2024年7月,使用与前驱期PD和诊断方法相关的关键词。我们根据预定义的纳入和排除标准纳入研究,并使用标准化表格进行数据提取。

结果

该检索纳入了9项研究,涉及567例前驱期PD患者和35643例对照。研究采用了各种诊断方法,包括神经成像技术和人工智能驱动的模型。敏感性范围为43%至84%,特异性高达96%。神经成像和人工智能技术在识别早期病理变化和预测PD发病方面显示出有前景的结果。对神经黑色素敏感的成像模型实现了最高的特异性,而标准10秒心电图(ECG)+机器学习模型实现了最高的敏感性。

结论

人工智能驱动的模型和多模态神经成像等先进诊断方法在前驱期PD的早期检测中显示出有前景的结果。然而,由于缺乏验证,它们作为前驱期PD筛查工具的临床应用受到限制。未来的研究应致力于使用多模态成像诊断和筛查前驱期PD。

临床试验编号

不适用。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/45e2/11951780/83dc6c411780/12880_2025_1620_Fig1_HTML.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验