{"title":"基于 Rs-fMRI 的机器学习模型在区分轻度认知障碍和阿尔茨海默病方面的应用价值:系统综述和荟萃分析。","authors":"Chentong Wang, Li Zhou, Feng Zhou, Tingting Fu","doi":"10.1007/s10072-024-07731-1","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Various machine learning (ML) models based on resting-state functional MRI (Rs-fMRI) have been developed to facilitate differential diagnosis of mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, the diagnostic accuracy of such models remains understudied. Therefore, we conducted this systematic review and meta-analysis to explore the diagnostic accuracy of Rs-fMRI-based radiomics in differentiating MCI from AD.</p><p><strong>Methods: </strong>PubMed, Embase, Cochrane, and Web of Science were searched from inception up to February 8, 2024, to identify relevant studies. Meta-analysis was conducted using a bivariate mixed-effects model, and sub-group analyses were carried out by the types of ML tasks (binary classification and multi-class classification tasks).</p><p><strong>Findings: </strong>In total, 23 studies, comprising 5,554 participants were enrolled in the study. In the binary classification tasks (twenty studies), the diagnostic accuracy of the ML model for AD was 0.99 (95%CI: 0.34 ~ 1.00), with a sensitivity of 0.94 (95%CI: 0.89 ~ 0.97) and a specificity of 0.98 (95%CI: 0.95 ~ 1.00). In the multi-class classification tasks (six studies), the diagnostic accuracy of the ML model was 0.98 (95%CI: 0.98 ~ 0.99) for NC, 0.96 (95%CI: 0.96 ~ 0.96) for early mild cognitive impairment (EMCI), 0.97 (95%CI: 0.96 ~ 0.97) for late mild cognitive impairment (LMCI), and 0.95 (95%CI: 0.95 ~ 0.95) for AD.</p><p><strong>Conclusions: </strong>The Rs-fMRI-based ML model can be adapted to multi-class classification tasks. Therefore, multi-center studies with large samples are needed to develop intelligent application tools to promote the development of intelligent ML models for disease diagnosis.</p>","PeriodicalId":19191,"journal":{"name":"Neurological Sciences","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The application value of Rs-fMRI-based machine learning models for differentiating mild cognitive impairment from Alzheimer's disease: a systematic review and meta-analysis.\",\"authors\":\"Chentong Wang, Li Zhou, Feng Zhou, Tingting Fu\",\"doi\":\"10.1007/s10072-024-07731-1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Various machine learning (ML) models based on resting-state functional MRI (Rs-fMRI) have been developed to facilitate differential diagnosis of mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, the diagnostic accuracy of such models remains understudied. Therefore, we conducted this systematic review and meta-analysis to explore the diagnostic accuracy of Rs-fMRI-based radiomics in differentiating MCI from AD.</p><p><strong>Methods: </strong>PubMed, Embase, Cochrane, and Web of Science were searched from inception up to February 8, 2024, to identify relevant studies. Meta-analysis was conducted using a bivariate mixed-effects model, and sub-group analyses were carried out by the types of ML tasks (binary classification and multi-class classification tasks).</p><p><strong>Findings: </strong>In total, 23 studies, comprising 5,554 participants were enrolled in the study. In the binary classification tasks (twenty studies), the diagnostic accuracy of the ML model for AD was 0.99 (95%CI: 0.34 ~ 1.00), with a sensitivity of 0.94 (95%CI: 0.89 ~ 0.97) and a specificity of 0.98 (95%CI: 0.95 ~ 1.00). In the multi-class classification tasks (six studies), the diagnostic accuracy of the ML model was 0.98 (95%CI: 0.98 ~ 0.99) for NC, 0.96 (95%CI: 0.96 ~ 0.96) for early mild cognitive impairment (EMCI), 0.97 (95%CI: 0.96 ~ 0.97) for late mild cognitive impairment (LMCI), and 0.95 (95%CI: 0.95 ~ 0.95) for AD.</p><p><strong>Conclusions: </strong>The Rs-fMRI-based ML model can be adapted to multi-class classification tasks. Therefore, multi-center studies with large samples are needed to develop intelligent application tools to promote the development of intelligent ML models for disease diagnosis.</p>\",\"PeriodicalId\":19191,\"journal\":{\"name\":\"Neurological Sciences\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2024-09-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neurological Sciences\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s10072-024-07731-1\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neurological Sciences","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10072-024-07731-1","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0
摘要
背景:目前已开发出多种基于静息态功能磁共振成像(Rs-fMRI)的机器学习(ML)模型,以促进轻度认知障碍(MCI)和阿尔茨海默病(AD)的鉴别诊断。然而,此类模型的诊断准确性仍未得到充分研究。因此,我们进行了这项系统综述和荟萃分析,以探讨基于 Rs-fMRI 的放射组学在区分 MCI 和 AD 方面的诊断准确性:方法:我们检索了PubMed、Embase、Cochrane和Web of Science上从开始到2024年2月8日的相关研究。采用双变量混合效应模型进行了元分析,并根据ML任务的类型(二元分类和多类分类任务)进行了分组分析:共有 23 项研究、5554 名参与者参与了研究。在二元分类任务(20 项研究)中,ML 模型对 AD 的诊断准确率为 0.99(95%CI:0.34 ~ 1.00),灵敏度为 0.94(95%CI:0.89 ~ 0.97),特异性为 0.98(95%CI:0.95 ~ 1.00)。在多类分类任务(6 项研究)中,ML 模型对 NC 的诊断准确率为 0.98(95%CI:0.98 ~ 0.99),对早期轻度认知障碍(EMCI)的诊断准确率为 0.96(95%CI:0.96 ~ 0.96),对晚期轻度认知障碍(LMCI)的诊断准确率为 0.97(95%CI:0.96 ~ 0.97),对 AD 的诊断准确率为 0.95(95%CI:0.95 ~ 0.95):基于 Rs-fMRI 的 ML 模型可适用于多类分类任务。结论:基于Rs-fMRI的ML模型可适用于多类分类任务,因此需要多中心、大样本的研究来开发智能应用工具,以促进疾病诊断智能ML模型的发展。
The application value of Rs-fMRI-based machine learning models for differentiating mild cognitive impairment from Alzheimer's disease: a systematic review and meta-analysis.
Background: Various machine learning (ML) models based on resting-state functional MRI (Rs-fMRI) have been developed to facilitate differential diagnosis of mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, the diagnostic accuracy of such models remains understudied. Therefore, we conducted this systematic review and meta-analysis to explore the diagnostic accuracy of Rs-fMRI-based radiomics in differentiating MCI from AD.
Methods: PubMed, Embase, Cochrane, and Web of Science were searched from inception up to February 8, 2024, to identify relevant studies. Meta-analysis was conducted using a bivariate mixed-effects model, and sub-group analyses were carried out by the types of ML tasks (binary classification and multi-class classification tasks).
Findings: In total, 23 studies, comprising 5,554 participants were enrolled in the study. In the binary classification tasks (twenty studies), the diagnostic accuracy of the ML model for AD was 0.99 (95%CI: 0.34 ~ 1.00), with a sensitivity of 0.94 (95%CI: 0.89 ~ 0.97) and a specificity of 0.98 (95%CI: 0.95 ~ 1.00). In the multi-class classification tasks (six studies), the diagnostic accuracy of the ML model was 0.98 (95%CI: 0.98 ~ 0.99) for NC, 0.96 (95%CI: 0.96 ~ 0.96) for early mild cognitive impairment (EMCI), 0.97 (95%CI: 0.96 ~ 0.97) for late mild cognitive impairment (LMCI), and 0.95 (95%CI: 0.95 ~ 0.95) for AD.
Conclusions: The Rs-fMRI-based ML model can be adapted to multi-class classification tasks. Therefore, multi-center studies with large samples are needed to develop intelligent application tools to promote the development of intelligent ML models for disease diagnosis.
期刊介绍:
Neurological Sciences is intended to provide a medium for the communication of results and ideas in the field of neuroscience. The journal welcomes contributions in both the basic and clinical aspects of the neurosciences. The official language of the journal is English. Reports are published in the form of original articles, short communications, editorials, reviews and letters to the editor. Original articles present the results of experimental or clinical studies in the neurosciences, while short communications are succinct reports permitting the rapid publication of novel results. Original contributions may be submitted for the special sections History of Neurology, Health Care and Neurological Digressions - a forum for cultural topics related to the neurosciences. The journal also publishes correspondence book reviews, meeting reports and announcements.