阿尔茨海默病数字生物标志物的多维全景与人工智能模型范围综述

Alzheimer's disease digital biomarkers multidimensional landscape and AI model scoping review.

作者信息

Qi Wenhao, Zhu Xiaohong, Wang Bin, Shi Yankai, Dong Chaoqun, Shen Shiying, Li Jiaqi, Zhang Kun, He Yunfan, Zhao Mengjiao, Yao Shiyan, Dong Yongze, Shen Huajuan, Kang Junling, Lu Xiaodong, Jiang Guowei, Boots Lizzy M M, Fu Heming, Pan Li, Chen Hongkai, Yan Zhenyu, Xing Guoliang, Cao Shihua

机构信息

School of Nursing, Hangzhou Normal University, Hangzhou, China.

School of Nursing, Fujian Medical University, Fujian, China.

出版信息

NPJ Digit Med. 2025 Jun 16;8(1):366. doi: 10.1038/s41746-025-01640-z.

DOI:10.1038/s41746-025-01640-z

PMID:40523935

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12170881/

Abstract

As digital biomarkers gain traction in Alzheimer's disease (AD) diagnosis, understanding recent advancements is crucial. This review conducts a bibliometric analysis of 431 studies from five online databases: Web of Science, PubMed, Embase, IEEE Xplore, and CINAHL, and provides a scoping review of 86 artificial intelligence (AI) models. Research in this field is supported by 224 grants across 54 disciplines and 1403 institutions in 44 countries, with 2571 contributing researchers. Key focuses include motor activity, neurocognitive tests, eye tracking, and speech analysis. Classical machine learning models dominate AI research, though many lack performance reporting. Of 21 AD-focused models, the average AUC is 0.887, while 45 models for mild cognitive impairment show an average AUC of 0.821. Notably, only 2 studies incorporated external validation, and 3 studies performed model calibration. This review highlights the progress and challenges of integrating digital biomarkers into clinical practice.

摘要

随着数字生物标志物在阿尔茨海默病（AD）诊断中越来越受关注，了解其最新进展至关重要。本综述对来自Web of Science、PubMed、Embase、IEEE Xplore和CINAHL这五个在线数据库的431项研究进行了文献计量分析，并对86个人工智能（AI）模型进行了范围综述。该领域的研究得到了来自44个国家54个学科和1403个机构的224项资助，有2571名研究人员参与其中。主要研究重点包括运动活动、神经认知测试、眼动追踪和语音分析。经典机器学习模型在AI研究中占主导地位，不过许多研究缺乏性能报告。在21个针对AD的模型中，平均曲线下面积（AUC）为0.887，而45个针对轻度认知障碍的模型平均AUC为0.821。值得注意的是，只有2项研究纳入了外部验证，3项研究进行了模型校准。本综述突出了将数字生物标志物整合到临床实践中的进展和挑战。