Article(id=1240633244039836657, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1240633237542851387, articleNumber=null, orderNo=null, doi=10.20043/j.cnki.MPM.202312346, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1703088000000, receivedDateStr=2023-12-21, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1773719615230, onlineDateStr=2026-03-17, pubDate=1716566400000, pubDateStr=2024-05-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773719615230, onlineIssueDateStr=2026-03-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773719615230, creator=13701087609, updateTime=1773719615230, updator=13701087609, issue=Issue{id=1240633237542851387, tenantId=1146029695717560320, journalId=1227665162245664772, year='2024', volume='51', issue='10', pageStart='1729', pageEnd='1920', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1773719613680, creator=13701087609, updateTime=1773720039302, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1240635022806405370, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1240633237542851387, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1240635022806405371, tenantId=1146029695717560320, journalId=1227665162245664772, issueId=1240633237542851387, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1889, endPage=1894, ext={EN=ArticleExt(id=1240633245663031309, articleId=1240633244039836657, tenantId=1146029695717560320, journalId=1227665162245664772, language=EN, title=Alzheimer’s disease classification based on multimodal data integration, columnId=1228016569138213037, journalTitle=Modern Preventive Medicine, columnName=Clinical Medicine and Prevention, runingTitle=null, highlight=null, articleAbstract=
Objective

To achieve the classification of Alzheimer’s disease (AD) by integrating information that utilize the complementary properties of multimodal data, and to provide references for clinical diagnosis.

Methods

A total of 872 subjects were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), with both clinical information, structural magnetic resonance imaging (sMRI) and functional magnetic resonance imaging (fMRI) scans. They were divided into the training set (612 subjects) and test set (260 subjects). Based on three unimodal data and four multimodal combinations of different modalities, we constructed the sparse Partial Least Squares-Discriminant Analysis (sPLS-DA) classification models in the training set to achieve the multi-classification. The macro-averaged precision (Macro-P), macro-averaged recall (Macro-R), macro-averaged F1 value (Macro-F1), and accuracy were used to evaluate the model performance, with the optimal combination of modalities obtained explored for their applicability in the test set.

Results

The classification performance of clinical information (Macro-P=0.781 8, Macro-R=0.804 6, Macro-F1=0.791 2, Accuracy=0.796 7) among the unimodal information was better than that of sMRI and fMRI modalities. The optimal number of potential components was 1, and the number of clinical information features was 9. Among the four multimodal combinations, the clinical information + fMRI combination had the strongest classification ability (Macro-P=0.806 2,Macro-R=0.800 6, Macro-F1=0.797 6, Accuracy=0.813 2), with the optimal number of potential components selected as 1,and the number of features were 5, while the sMRI + fMRI had the worst classification ability (Macro-P=0.401 7, Macro-R=0.398 3, Macro-F1=0.349 9, Accuracy=0.565 9).Applying the best modal combination to the test set, the model performance metrics achieved were 0.791 8 for Macro-P, 0.734 5 for Macro-R, 0.758 4 for Macro-F1, and 0.766 4(0.646 0, 0.846 5) for Accuracy.

Conclusion

The performance of the sPLS-DA classification model constructed based on each multimodal combination was higher than that of the unimodal, among which the combination of clinical information + fMRI modality had the best performance, which couldgreatly facilitate the formulation of scientific and reasonable clinical diagnosis plans.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Jing CUI, Hui YANG, Yao QIN, Du-rong CHEN, Hong-mei YU), CN=ArticleExt(id=1240633250121576745, articleId=1240633244039836657, tenantId=1146029695717560320, journalId=1227665162245664772, language=CN, title=基于多模态数据整合的阿尔茨海默病分类研究, columnId=1228016570119680182, journalTitle=现代预防医学, columnName=临床与预防, runingTitle=null, highlight=null, articleAbstract=
目的

利用多模态数据的互补特性整合信息,实现对阿尔茨海默病的分类,为临床诊断提供参考。

方法

筛选阿尔茨海默病神经影像学计划数据库中同时具有临床信息、结构磁共振成像(sMRI)和功能磁共振成像(fMRI)的受试者共872例,将其分为训练集(612例)和测试集(260例)。基于三种单模态以及四种多模态组合在训练集中构建稀疏偏最小二乘-判别分析(sparse Partial Least Squares-Discriminant Analysis,sPLS-DA)分类模型实现多分类。利用宏观平均精确率(Macro-average of Precision,Macro-P)、宏观平均召回率(Macro-average of Recall,Macro-R)、宏观平均F1值(Macro-average of F1-score,Macro-F1)、及准确率(Accuracy)评价模型性能,在测试集中探讨最优模态组合的适用性。

结果

单模态中临床信息的分类性能优于sMRI和fMRI模态(Macro-P=0.781 8,Macro-R=0.804 6,Macro-F1=0.791 2,Accuracy=0.796 7),选择的最佳潜在成分个数为1,临床信息特征数量为9。四种多模态组合中临床信息+fMRI模态组合的分类能力最强(Macro-P=0.806 2,Macro-R=0.800 6,Macro-F1=0.797 6,Accuracy=0.813 2),选择的最佳潜在成分个数为1,特征数量为5;而sMRI+fMRI的分类能力最差(Macro-P=0.401 7,Macro-R=0.398 3,Macro-F1=0.349 9,Accuracy=0.565 9)。将在训练集中得到的最佳模态组合应用于测试集,得到的模型性能指标Macro-P为0.791 8,Macro-R为0.734 5,Macro-F1为0.758 4,Accuracy为0.766 4(0.646 0,0.846 5)。

结论

基于各多模态组合构建的sPLS-DA分类模型性能均高于单模态,其中临床信息+fMRI模态组合表现最佳,可辅助制定科学合理的临床诊断方案。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
余红梅,E-mail:
, copyrightStatement=本刊刊出的所有文章不代表中华预防医学会和本刊编委会的观点,除非特别声明。, copyrightOwner=中华预防医学会和四川大学华西公共卫生学院, extLink=null, articleAbsUrl=null, sourceXml=cTejAcpIp/WexnaG4EOOeQ==, magXml=+n6o5cPZvQmne1D4B3Ozmg==, pdfUrl=null, pdf=YwLU0HlBwSMl+ojWDuMWxA==, pdfFileSize=944878, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=3GXevOdGelwAcWMMQNT2lQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=0O6hNgqWNvkLoc1s6W463A==, mapNumber=null, authorCompany=null, fund=null, authors=

崔靖(1987—),女,博士,讲师,研究方向:队列统计方法研究与应用

, authorsList=崔靖, 杨慧, 秦瑶, 陈杜荣, 余红梅)}, authors=[Author(id=1240633250859774323, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1240633251094655357, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, authorId=1240633250859774323, language=EN, stringName=Jing CUI, firstName=Jing, middleName=null, lastName=CUI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=Third Hospital of Shanxi Medical University, Taiyuan, Shanxi 030032, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1240633251195318663, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, authorId=1240633250859774323, language=CN, stringName=崔靖, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.山西医科大学第三医院(山西白求恩医院 山西医学科学院 同济山西医院),山西 太原 030032
2.山西医科大学公共卫生学院卫生统计学教研室, bio={"content":"

崔靖(1987—),女,博士,讲师,研究方向:队列统计方法研究与应用

"}, bioImg=null, bioContent=

崔靖(1987—),女,博士,讲师,研究方向:队列统计方法研究与应用

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1240633250377429314, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=1., ext=[AuthorCompanyExt(id=1240633250385817926, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250377429314, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Third Hospital of Shanxi Medical University, Taiyuan, Shanxi 030032, China), AuthorCompanyExt(id=1240633250394206533, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250377429314, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.山西医科大学第三医院(山西白求恩医院 山西医学科学院 同济山西医院),山西 太原 030032)]), AuthorCompany(id=1240633250507452752, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=2., ext=[AuthorCompanyExt(id=1240633250524229972, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250507452752, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西医科大学公共卫生学院卫生统计学教研室)])]), Author(id=1240633251300176276, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1240633251421811101, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, authorId=1240633251300176276, language=EN, stringName=Hui YANG, firstName=Hui, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1240633251560223138, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, authorId=1240633251300176276, language=CN, stringName=杨慧, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.山西医科大学公共卫生学院卫生统计学教研室, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1240633250507452752, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=2., ext=[AuthorCompanyExt(id=1240633250524229972, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250507452752, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西医科大学公共卫生学院卫生统计学教研室)])]), Author(id=1240633251631526314, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1240633251719606709, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, authorId=1240633251631526314, language=EN, stringName=Yao QIN, firstName=Yao, middleName=null, lastName=QIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1240633251820270011, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, authorId=1240633251631526314, language=CN, stringName=秦瑶, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.山西医科大学公共卫生学院卫生统计学教研室, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1240633250507452752, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=2., ext=[AuthorCompanyExt(id=1240633250524229972, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250507452752, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西医科大学公共卫生学院卫生统计学教研室)])]), Author(id=1240633251950293445, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1240633252088705483, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, authorId=1240633251950293445, language=EN, stringName=Du-rong CHEN, firstName=Du-rong, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1240633252214534608, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, authorId=1240633251950293445, language=CN, stringName=陈杜荣, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.山西医科大学公共卫生学院卫生统计学教研室, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1240633250507452752, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=2., ext=[AuthorCompanyExt(id=1240633250524229972, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250507452752, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西医科大学公共卫生学院卫生统计学教研室)])]), Author(id=1240633252340363739, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yu@sxmu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1240633252466192872, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, authorId=1240633252340363739, language=EN, stringName=Hong-mei YU, firstName=Hong-mei, middleName=null, lastName=YU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, 4, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1240633252554273262, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, authorId=1240633252340363739, language=CN, stringName=余红梅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, 4, address=2.山西医科大学公共卫生学院卫生统计学教研室
3.重大疾病风险评估山西省重点实验室
4.煤炭环境致病与防治教育部重点实验室, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1240633250507452752, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=2., ext=[AuthorCompanyExt(id=1240633250524229972, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250507452752, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西医科大学公共卫生学院卫生统计学教研室)]), AuthorCompany(id=1240633250650059101, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=3., ext=[AuthorCompanyExt(id=1240633250654253406, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250650059101, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.重大疾病风险评估山西省重点实验室)]), AuthorCompany(id=1240633250759111015, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=4., ext=[AuthorCompanyExt(id=1240633250767499625, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250759111015, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.煤炭环境致病与防治教育部重点实验室)])])], keywords=[Keyword(id=1240633252701073912, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, orderNo=1, keyword=Alzheimer’s disease), Keyword(id=1240633252847874563, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, orderNo=2, keyword=Multimodal), Keyword(id=1240633254349435404, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, orderNo=3, keyword=Magnetic resonance imaging), Keyword(id=1240633254454293015, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, orderNo=4, keyword=Multi-classification), Keyword(id=1240633254542373407, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, orderNo=5, keyword=Sparse partial least squares-discriminant analysis), Keyword(id=1240633254664008233, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, orderNo=1, keyword=阿尔茨海默病), Keyword(id=1240633254777254451, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, orderNo=2, keyword=多模态), Keyword(id=1240633254894694974, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, orderNo=3, keyword=磁共振成像), Keyword(id=1240633254982775365, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, orderNo=4, keyword=多分类), Keyword(id=1240633255075050059, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, orderNo=5, keyword=稀疏偏最小二乘-判别分析)], refs=[Reference(id=1240633256849240761, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2022, volume=35, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Ren RJ, Qi JL, Lin SH, journalName=General Psychiatry, refType=null, unstructuredReference=Ren RJ, Qi JL, Lin SH, et al. The China alzheimer report 2022[J]. General Psychiatry, 2022, 35(1): e100751., articleTitle=The China alzheimer report 2022, refAbstract=null), Reference(id=1240633257079927487, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2022, volume=14, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Zhang Z, Zhao YH, Bian Y, journalName=Frontiers in Aging Neuroscience, refType=null, unstructuredReference=Zhang Z, Zhao YH, Bian Y. A role of socioeconomic status in cognitive impairment among older adults in Macau: a decomposition approach[J]. Frontiers in Aging Neuroscience, 2022, 14: 804307., articleTitle=A role of socioeconomic status in cognitive impairment among older adults in Macau: a decomposition approach, refAbstract=null), Reference(id=1240633257176396484, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2022, volume=49, issue=22, pageStart=4045, pageEnd=4051, 4089, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=韩红娟, 陈杜荣, 秦瑶, journalName=现代预防医学, refType=null, unstructuredReference=韩红娟,陈杜荣,秦瑶,等.基于Stacking集成策略的阿尔茨海默病诊断模型研究[J].现代预防医学202249(22):4045-4051, 4089., articleTitle=基于Stacking集成策略的阿尔茨海默病诊断模型研究, refAbstract=null), Reference(id=1240633257268671177, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2022, volume=49, issue=22, pageStart=4045, pageEnd=4051, 4089, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Han HJ, Chen DR, Qin Y, journalName=Modern Preventive Medicine, refType=null, unstructuredReference=Han HJ, Chen DR, Qin Y, et al. Multi-classification diagnosis of Alzheimer’s disease based on stacking ensemble strategy[J]. Modern Preventive Medicine, 2022, 49(22): 4045-4051, 4089., articleTitle=Multi-classification diagnosis of Alzheimer’s disease based on stacking ensemble strategy, refAbstract=null), Reference(id=1240633257344168652, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2021, volume=20, issue=6, pageStart=484, pageEnd=496, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=Dubois B, Villain N, Frisoni GB, journalName=The Lancet. Neurology, refType=null, unstructuredReference=Dubois B, Villain N, Frisoni GB, et al. Clinical diagnosis of Alzheimer’s disease: recommendations of the international working group[J]. The Lancet. Neurology, 2021, 20(6): 484-496., articleTitle=Clinical diagnosis of Alzheimer’s disease: recommendations of the international working group, refAbstract=null), Reference(id=1240633258812175056, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2022, volume=23, issue=2, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=Stahlschmidt SR, Ulfenborg B, Synnergren J, journalName=Briefings in Bioinformatics, refType=null, unstructuredReference=Stahlschmidt SR, Ulfenborg B, Synnergren J. Multimodal deep learning for biomedical data fusion: a review[J]. Briefings in Bioinformatics, 2022, 23(2): bbab569., articleTitle=Multimodal deep learning for biomedical data fusion: a review, refAbstract=null), Reference(id=1240633258908644054, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2023, volume=5, issue=4, pageStart=351, pageEnd=362, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=Steyaert S, Pizurica M, Nagaraj D, journalName=Nature Machine Intelligence, refType=null, unstructuredReference=Steyaert S, Pizurica M, Nagaraj D, et al. Multimodal data fusion for cancer biomarker discovery with deep learning[J]. Nature Machine Intelligence, 2023, 5(4): 351-362., articleTitle=Multimodal data fusion for cancer biomarker discovery with deep learning, refAbstract=null), Reference(id=1240633259030278872, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2021, volume=113, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=Liu W, Wang JY, journalName=Applied Soft Computing, refType=null, unstructuredReference=Liu W, Wang JY. Recursive elimination–election algorithms for wrapper feature selection[J]. Applied Soft Computing, 2021, 113(Part B): 107956., articleTitle=Recursive elimination–election algorithms for wrapper feature selection, refAbstract=null), Reference(id=1240633259139330780, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=5, pageStart=1847, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=Velarde-Alvarado P, Gonzalez H, Martínez-Peláez R, journalName=Sensors, refType=null, unstructuredReference=Velarde-Alvarado P, Gonzalez H, Martínez-Peláez R, et al. A novel framework for generating personalized network datasets for NIDS based on traffic aggregation[J]. Sensors, 2022, 22(5): 1847., articleTitle=A novel framework for generating personalized network datasets for NIDS based on traffic aggregation, refAbstract=null), Reference(id=1240633259248382688, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2022, volume=98, issue=11, pageStart=e1114, pageEnd=e1123, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=Iraniparast M, Shi YD, Wu Y, journalName=Neurology, refType=null, unstructuredReference=Iraniparast M, Shi YD, Wu Y, et al. Cognitive reserve and mild cognitive impairment: predictors and rates of reversion to intact cognition vs progression to dementia[J]. Neurology, 2022, 98(11): e1114-e1123., articleTitle=Cognitive reserve and mild cognitive impairment: predictors and rates of reversion to intact cognition vs progression to dementia, refAbstract=null), Reference(id=1240633259323880161, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2022, volume=25, issue=9, pageStart=1070, pageEnd=1076, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=韩红娟, 秦瑶, 陈杜荣, journalName=中国全科医学, refType=null, unstructuredReference=韩红娟,秦瑶,陈杜荣,等.轻度认知障碍患者的双向转归研究[J].中国全科医学202225(9):1070-1076., articleTitle=轻度认知障碍患者的双向转归研究, refAbstract=null), Reference(id=1240633259420349157, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2022, volume=25, issue=9, pageStart=1070, pageEnd=1076, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=Han HJ, Qin Y, Chen DR, journalName=Chinese General Practice, refType=null, unstructuredReference=Han HJ, Qin Y, Chen DR, et al. Progression and reversion of mild cognitiveimpairment:a study using data from the uniform data set[J]. Chinese General Practice, 2022, 25(9): 1070-1076., articleTitle=Progression and reversion of mild cognitiveimpairment:a study using data from the uniform data set, refAbstract=null), Reference(id=1240633259529401064, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2023, volume=38, issue=1, pageStart=185, pageEnd=193, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=Padala SP, Newhouse PA, journalName=Metabolic Brain Disease, refType=null, unstructuredReference=Padala SP, Newhouse PA. Blood-based biomarkers in Alzheimer’s disease: a mini-review[J]. Metabolic Brain Disease, 2023, 38(1): 185-193., articleTitle=Blood-based biomarkers in Alzheimer’s disease: a mini-review, refAbstract=null), Reference(id=1240633259655230190, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2018, volume=14, issue=4, pageStart=535, pageEnd=562, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=Jack CRJ, Bennett DA, Blennow K, journalName=Alzheimer’s & Dementia: the Journal of the Alzheimer’s Association, refType=null, unstructuredReference=Jack CRJ, Bennett DA,Blennow K, et al. NIA-AA research framework: toward a biological definition of alzheimer’s disease[J]. Alzheimer’s & Dementia: the Journal of the Alzheimer’s Association, 2018, 14(4): 535-562., articleTitle=NIA-AA research framework: toward a biological definition of alzheimer’s disease, refAbstract=null), Reference(id=1240633259776865007, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2023, volume=9, issue=3, pageStart=435, pageEnd=439, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=赵倩, 冯金玉, 洪兆晨, journalName=循证护理, refType=null, unstructuredReference=赵倩,冯金玉,洪兆晨,等.轻度认知功能障碍早期筛查量表的研究进展[J].循证护理20239(3):435-439., articleTitle=轻度认知功能障碍早期筛查量表的研究进展, refAbstract=null), Reference(id=1240633259877528307, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2023, volume=9, issue=3, pageStart=435, pageEnd=439, url=null, language=null, rfNumber=[13], rfOrder=15, authorNames=Zhao Q, Feng JY, Hong ZC, journalName=Chinese Evidence-Based Nursing, refType=null, unstructuredReference=Zhao Q,Feng JY, Hong ZC, et al. Research progress of early screening scale for mild cognitive impairment[J]. Chinese Evidence-Based Nursing, 2023, 9(3): 435-439., articleTitle=Research progress of early screening scale for mild cognitive impairment, refAbstract=null), Reference(id=1240633259965608693, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2023, volume=22, issue=5, pageStart=433, pageEnd=444, url=null, language=null, rfNumber=[14], rfOrder=16, authorNames=陈晓春, 贾建平, 郭起浩, journalName=中华神经医学杂志, refType=null, unstructuredReference=陈晓春,贾建平,郭起浩,等.前驱期阿尔茨海默病的简易筛查中国专家共识(2023年版)[J].中华神经医学杂志202322(5):433-444., articleTitle=前驱期阿尔茨海默病的简易筛查中国专家共识(2023年版), refAbstract=null), Reference(id=1240633260045300474, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2023, volume=22, issue=5, pageStart=433, pageEnd=444, url=null, language=null, rfNumber=[14], rfOrder=17, authorNames=Chen XC, Jia JP, Guo QH, journalName=Chinese Journal of Neuromedicine, refType=null, unstructuredReference=Chen XC,Jia JP, Guo QH, et al. Chinese expert consensus on brief screening of prodromal Alzheimer’s disease(2023)[J]. Chinese Journal of Neuromedicine, 2023, 22(5): 433-444., articleTitle=Chinese expert consensus on brief screening of prodromal Alzheimer’s disease(2023), refAbstract=null), Reference(id=1240633260129186554, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2021, volume=11, issue=1, pageStart=2660, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=18, authorNames=El-Sappagh S, Alonso JM, Islam SMR, journalName=Scientific Reports, refType=null, unstructuredReference=El-Sappagh S, Alonso JM, Islam SMR, et al. A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease[J]. Scientific Reports, 2021, 11(1): 2660., articleTitle=A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease, refAbstract=null), Reference(id=1240633260238238463, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=19, authorNames=Chen ZH, Chen KL, Li YX, journalName=Human Brain Mapping, refType=null, unstructuredReference=Chen ZH, Chen KL, Li YX, et al. Structural, static, and dynamic functional MRI predictors for conversion from mild cognitive impairment to Alzheimer’s disease: Inter-cohort validation of Shanghai Memory Study and ADNI[J]. Human Brain Mapping, 2024, 45(1): e26529., articleTitle=Structural, static, and dynamic functional MRI predictors for conversion from mild cognitive impairment to Alzheimer’s disease: Inter-cohort validation of Shanghai Memory Study and ADNI, refAbstract=null), Reference(id=1240633260355678977, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2016, volume=27, issue=2, pageStart=131, pageEnd=134, url=null, language=null, rfNumber=[17], rfOrder=20, authorNames=李瑜霞, 李永秋, 孙宇, journalName=中国临床医学影像杂志, refType=null, unstructuredReference=李瑜霞,李永秋,孙宇,等.源于阿尔茨海默病的轻度认知障碍患者脑结构及静息态功能磁共振研究进展[J].中国临床医学影像杂志201627(2):131-134., articleTitle=源于阿尔茨海默病的轻度认知障碍患者脑结构及静息态功能磁共振研究进展, refAbstract=null), Reference(id=1240633260460536579, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2016, volume=27, issue=2, pageStart=131, pageEnd=134, url=null, language=null, rfNumber=[17], rfOrder=21, authorNames=Li YX, Li YQ, Sun Y, journalName=Journal ofChina Clinic Medical Imaging, refType=null, unstructuredReference=Li YX, Li YQ, Sun Y, et al. Structural and resting state functional MRI characteristics of patients with mild cognitive impairment due to Alzheimer’s disease[J]. Journal ofChina Clinic Medical Imaging, 2016, 27(2): 131-134., articleTitle=Structural and resting state functional MRI characteristics of patients with mild cognitive impairment due to Alzheimer’s disease, refAbstract=null), Reference(id=1240633260577977094, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2016, volume=2016, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=22, authorNames=Creavin ST, Wisniewski S, Noel-Storr AH, journalName=Cochrane Database of Systematic Reviews: Online, refType=null, unstructuredReference=Creavin ST, Wisniewski S, Noel-Storr AH, et al. Mini-Mental state examination (MMSE) for the detection of dementia in clinically unevaluated People aged 65 and over in community and primary care populations[J]. Cochrane Database of Systematic Reviews: Online, 2016, 2016(1): CD011145., articleTitle=Mini-Mental state examination (MMSE) for the detection of dementia in clinically unevaluated People aged 65 and over in community and primary care populations, refAbstract=null), Reference(id=1240633260703806215, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2024, volume=15, issue=1, pageStart=173, pageEnd=178, url=null, language=null, rfNumber=[19], rfOrder=23, authorNames=何雨洁, 闫少珍, 卢洁, journalName=磁共振成像, refType=null, unstructuredReference=何雨洁,闫少珍,卢洁.静息态功能磁共振对阿尔茨海默病早期诊断的研究进展[J].磁共振成像202415(1):173-178., articleTitle=静息态功能磁共振对阿尔茨海默病早期诊断的研究进展, refAbstract=null), Reference(id=1240633260783497994, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, doi=null, pmid=null, pmcid=null, year=2024, volume=15, issue=1, pageStart=173, pageEnd=178, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=He YJ, Yan SZ, Lu J, journalName=Chinese Journal of Magnetic Resonance Imaging, refType=null, unstructuredReference=He YJ, Yan SZ, Lu J. Research advance on resting-state functional magnetic resonance imaging in the early diagnosis of Alzheimer’s disease[J]. Chinese Journal of Magnetic Resonance Imaging, 2024, 15(1): 173-178., articleTitle=Research advance on resting-state functional magnetic resonance imaging in the early diagnosis of Alzheimer’s disease, refAbstract=null)], funds=[Fund(id=1240633256501113509, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, awardId=81973154,82273742, language=CN, fundingSource=国家自然科学基金资助项目(81973154,82273742), fundOrder=null, country=null), Fund(id=1240633256622748332, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, awardId=202103021223242, language=CN, fundingSource=山西省基础研究计划自由探索类青年项目(202103021223242), fundOrder=null, country=null), Fund(id=1240633256715023023, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, awardId=2023KY406, language=CN, fundingSource=山西省研究生教育创新项目(2023KY406), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1240633250377429314, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=1., ext=[AuthorCompanyExt(id=1240633250385817926, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250377429314, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Third Hospital of Shanxi Medical University, Taiyuan, Shanxi 030032, China), AuthorCompanyExt(id=1240633250394206533, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250377429314, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.山西医科大学第三医院(山西白求恩医院 山西医学科学院 同济山西医院),山西 太原 030032)]), AuthorCompany(id=1240633250507452752, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=2., ext=[AuthorCompanyExt(id=1240633250524229972, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250507452752, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西医科大学公共卫生学院卫生统计学教研室)]), AuthorCompany(id=1240633250650059101, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=3., ext=[AuthorCompanyExt(id=1240633250654253406, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250650059101, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.重大疾病风险评估山西省重点实验室)]), AuthorCompany(id=1240633250759111015, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, xref=4., ext=[AuthorCompanyExt(id=1240633250767499625, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, companyId=1240633250759111015, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.煤炭环境致病与防治教育部重点实验室)])], figs=[ArticleFig(id=1240633255213462103, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, label=Fig.1, caption=The determination of principal component number and selected features of unimodal data, figureFileSmall=VOeVNgvNKGY6ZGwZDydB6A==, figureFileBig=3GXevOdGelwAcWMMQNT2lQ==, tableContent=null), ArticleFig(id=1240633255314125405, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, label=图1, caption=各单模态主成分数和特征数量的确定

注:实线overall表示总体错误率;虚线BER表示平衡错误率;Comp表示主成分数;max.dist、centroids.dist、mahalanobis.dist表示不同类型的预测距离,分别对应最大距离,质心距离,马氏距离。A、B、C分别为临床信息、sMRI、fMRI模态的主成分数选择图示;D、E、F分别为临床信息、sMRI、fMRI模态的特征选择数量图示。

, figureFileSmall=VOeVNgvNKGY6ZGwZDydB6A==, figureFileBig=3GXevOdGelwAcWMMQNT2lQ==, tableContent=null), ArticleFig(id=1240633255519646320, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, label=Fig.2, caption=The determination of principal component number and selected features of multimodal data, figureFileSmall=9ALCtCHgeH1dr427WrW25A==, figureFileBig=eHQen/5oEjO7Spcg/l8owA==, tableContent=null), ArticleFig(id=1240633255624503924, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, label=图2, caption=各多模态组合主成分数和特征数量的确定

注:实线overall表示总体错误率;虚线BER表示平衡错误率;Comp表示主成分数;max.dist、entroids.dist、mahalanobis.dist表示不同类型的预测距离,分别对应最大距离,质心距离,马氏距离。A、B、C、D分别为临床信息+sMRI、临床信息+fMRI、sMRI+fMRI、临床信息+sMRI+fMRI模态组合的主成分数选择图示;E、F、G、H为临床信息+sMRI、临床信息+fMRI、sMRI+fMRI、临床信息+sMRI+fMRI模态组合的特征选择数量图示。

, figureFileSmall=9ALCtCHgeH1dr427WrW25A==, figureFileBig=eHQen/5oEjO7Spcg/l8owA==, tableContent=null), ArticleFig(id=1240633255729361525, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, label=Table 1, caption=

Neuropsychological testing scales

, figureFileSmall=null, figureFileBig=null, tableContent=
中文名称英文名称
阿尔茨海默病评定量表-认知分量表条目11ADAS-Cog11(Alzheimer’s Disease Assessment Scale-Cognition 11 items)
阿尔茨海默病评定量表-认知分量表条目13ADAS-Cog13(Alzheimer’s Disease Assessment Scale-Cognition 13 items)
阿尔茨海默病评定量表-任务4(单词识别)ADASQ4(Score from Task 4 (Word Recognition) of the Alzheimer’s Disease Assessment Scale)
瑞氏听觉和语言学习测试-即时回忆RAVLT-immediate(Rey’s Auditory VerbalLearning Test_Immediate Recall)
瑞氏听觉和语言学习测试-学习成绩RAVLT-learning(Rey’s Auditory Verbal Learning Test_Learning)
瑞氏听觉和语言学习测试-遗忘RAVLT-forgetting(Rey’s Auditory Verbal LearninTest_Forgetting)
瑞氏听觉和语言学习测试-遗忘百分比RAVLT-perc-forgetting(Rey’s Auditory Verbal Learning Test_Percent Forgetting)
延迟召回LDELTOTAL(Delayed total recall)
连线试验-BTRABSCOR(Trail Making Test Part B Time)
功能活动量表FAQ(Functional Activities Questionnaire)
蒙特利尔认知评估量表MoCA(Montreal Cognitive Assessment)
改进的临床前阿尔茨海默病认知数字测试组合mPACCdigit(Modified Preclinical Alzheimer Cognitive Composite with Digit Symbol Substitution)
改进的临床前阿尔茨海默病认知试验测试组合mPACCtrailsB(Modified Preclinical Alzheimer Cognitive Composite with Trails B)
日常认知测试参与者报告EcogPtTotal(Everyday Cognition-Participant Self-Report)
日常认知测试研究报告EcogSPTotal(Everyday Cognition-Study Partner-Report)
), ArticleFig(id=1240633255825830525, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, label=表1, caption=

神经心理测试量表

, figureFileSmall=null, figureFileBig=null, tableContent=
中文名称英文名称
阿尔茨海默病评定量表-认知分量表条目11ADAS-Cog11(Alzheimer’s Disease Assessment Scale-Cognition 11 items)
阿尔茨海默病评定量表-认知分量表条目13ADAS-Cog13(Alzheimer’s Disease Assessment Scale-Cognition 13 items)
阿尔茨海默病评定量表-任务4(单词识别)ADASQ4(Score from Task 4 (Word Recognition) of the Alzheimer’s Disease Assessment Scale)
瑞氏听觉和语言学习测试-即时回忆RAVLT-immediate(Rey’s Auditory VerbalLearning Test_Immediate Recall)
瑞氏听觉和语言学习测试-学习成绩RAVLT-learning(Rey’s Auditory Verbal Learning Test_Learning)
瑞氏听觉和语言学习测试-遗忘RAVLT-forgetting(Rey’s Auditory Verbal LearninTest_Forgetting)
瑞氏听觉和语言学习测试-遗忘百分比RAVLT-perc-forgetting(Rey’s Auditory Verbal Learning Test_Percent Forgetting)
延迟召回LDELTOTAL(Delayed total recall)
连线试验-BTRABSCOR(Trail Making Test Part B Time)
功能活动量表FAQ(Functional Activities Questionnaire)
蒙特利尔认知评估量表MoCA(Montreal Cognitive Assessment)
改进的临床前阿尔茨海默病认知数字测试组合mPACCdigit(Modified Preclinical Alzheimer Cognitive Composite with Digit Symbol Substitution)
改进的临床前阿尔茨海默病认知试验测试组合mPACCtrailsB(Modified Preclinical Alzheimer Cognitive Composite with Trails B)
日常认知测试参与者报告EcogPtTotal(Everyday Cognition-Participant Self-Report)
日常认知测试研究报告EcogSPTotal(Everyday Cognition-Study Partner-Report)
), ArticleFig(id=1240633255926493826, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, label=Table 2, caption=

Clinical information situations of the various classes of subjects in the training set [n(%) / M(P25, P75)]

, figureFileSmall=null, figureFileBig=null, tableContent=
特征NC(n=311)MCI(n=210)AD(n=91)H值(χ2值)P
性别14.9730.001
127(40.84)122(58.10)44(48.35)
184(59.16)88(41.90)47(51.65)
年龄(岁)72.30(67.40,78.00)74.60(68.92,79.43)76.50(71.52,83.33)19.279<0.001
受教育年限(年)17(16,18)16(14,18)16(14,18)18.099<0.001
婚姻状态4.4720.107
已婚218(70.10)153(72.86)74(81.32)
单身93(19.90)57(27.14)17(18.68)
APOEε444.795<0.001
0201(64.63)119(56.67)28(30.77)
1103(33.12)79(37.62)49(53.85)
27(2.25)12(5.71)14(15.38)
ADAS11得分5.00(3.33,7.00)9.33(6.67,12.67)21.33(17.00,27.00)301.611<0.001
ADAS13得分8.00(5.33,11.00)14.84(10.25,19.00)31.67(27.00,38.00)306.504<0.001
ADASQ4得分2(1,4)5(3,7)10(8,10)244.495<0.001
RAVLT_immediate得分46(39,54)33(27,42)22(17,27)257.428<0.001
RAVLT_learning得分6(4,8)4(2,6)1(0,3)174.535<0.001
RAVLT_forgetting得分3(2,5)5(3,6)4(3,6)38.293<0.001
RAVLT_perc_forgetting得分28.57(13.33,50.00)57.14(36.36,86.16)100.00(90.75,100.00)209.450<0.001
LDELTOTAL得分13.00(11.00,16.00)8.00(4.75,11.00)0.00(0.00,2.00)310.582<0.001
TRABSCOR得分69.00(52.00,93.00)92.50(69.00,137.25)190.00(134.00,300.00)160.237<0.001
FAQ得分0(0,0)1(0,4)17(12,23)380.069<0.001
MOCA得分26(24,28)23(21,25)17(13,20)256.611<0.001
mPACCdigit得分0.73(-1.61,2.36)-4.85(-8.92,-1.58)-17.73(-21.23,-13.49)324.403<0.001
mPACCtrailsB得分0.61(-1.48,2.23)-4.75(-7.71,-1.31)-14.81(-18.33,-11.57)321.777<0.001
EcogPtTotal得分1.27(1.13,1.51)1.70(1.41,2.32)1.74(1.37,2.51)128.923<0.001
EcogSPTotal得分1.09(1.00,1.24)1.60(1.30,2.08)3.03(2.47,3.44)332.258<0.001
), ArticleFig(id=1240633256035545734, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, label=表2, caption=

训练集中各类研究对象的临床信息情况[n(%) / M(P25, P75)]

, figureFileSmall=null, figureFileBig=null, tableContent=
特征NC(n=311)MCI(n=210)AD(n=91)H值(χ2值)P
性别14.9730.001
127(40.84)122(58.10)44(48.35)
184(59.16)88(41.90)47(51.65)
年龄(岁)72.30(67.40,78.00)74.60(68.92,79.43)76.50(71.52,83.33)19.279<0.001
受教育年限(年)17(16,18)16(14,18)16(14,18)18.099<0.001
婚姻状态4.4720.107
已婚218(70.10)153(72.86)74(81.32)
单身93(19.90)57(27.14)17(18.68)
APOEε444.795<0.001
0201(64.63)119(56.67)28(30.77)
1103(33.12)79(37.62)49(53.85)
27(2.25)12(5.71)14(15.38)
ADAS11得分5.00(3.33,7.00)9.33(6.67,12.67)21.33(17.00,27.00)301.611<0.001
ADAS13得分8.00(5.33,11.00)14.84(10.25,19.00)31.67(27.00,38.00)306.504<0.001
ADASQ4得分2(1,4)5(3,7)10(8,10)244.495<0.001
RAVLT_immediate得分46(39,54)33(27,42)22(17,27)257.428<0.001
RAVLT_learning得分6(4,8)4(2,6)1(0,3)174.535<0.001
RAVLT_forgetting得分3(2,5)5(3,6)4(3,6)38.293<0.001
RAVLT_perc_forgetting得分28.57(13.33,50.00)57.14(36.36,86.16)100.00(90.75,100.00)209.450<0.001
LDELTOTAL得分13.00(11.00,16.00)8.00(4.75,11.00)0.00(0.00,2.00)310.582<0.001
TRABSCOR得分69.00(52.00,93.00)92.50(69.00,137.25)190.00(134.00,300.00)160.237<0.001
FAQ得分0(0,0)1(0,4)17(12,23)380.069<0.001
MOCA得分26(24,28)23(21,25)17(13,20)256.611<0.001
mPACCdigit得分0.73(-1.61,2.36)-4.85(-8.92,-1.58)-17.73(-21.23,-13.49)324.403<0.001
mPACCtrailsB得分0.61(-1.48,2.23)-4.75(-7.71,-1.31)-14.81(-18.33,-11.57)321.777<0.001
EcogPtTotal得分1.27(1.13,1.51)1.70(1.41,2.32)1.74(1.37,2.51)128.923<0.001
EcogSPTotal得分1.09(1.00,1.24)1.60(1.30,2.08)3.03(2.47,3.44)332.258<0.001
), ArticleFig(id=1240633256098460300, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, label=Table 3, caption=

Evaluation metrics for unimodal-based sPLS-DA models

, figureFileSmall=null, figureFileBig=null, tableContent=
单模态Macro-PMacro-RMacro-F1Accuracy(95%CI
临床信息0.781 80.804 60.791 20.796 7(0.730 8,0.852 6)
sMRI0.356 90.338 30.263 90.494 5(0.419 7,0.569 5)
fMRI0.688 20.438 50.421 90.549 5(0.474 1,0.623 1)
), ArticleFig(id=1240633256182346387, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, label=表3, caption=

基于单模态的sPLS-DA模型评价指标

, figureFileSmall=null, figureFileBig=null, tableContent=
单模态Macro-PMacro-RMacro-F1Accuracy(95%CI
临床信息0.781 80.804 60.791 20.796 7(0.730 8,0.852 6)
sMRI0.356 90.338 30.263 90.494 5(0.419 7,0.569 5)
fMRI0.688 20.438 50.421 90.549 5(0.474 1,0.623 1)
), ArticleFig(id=1240633256287203991, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=EN, label=Table 4, caption=

Evaluation metrics of sPLS-DA model based on different multimodal combinations

, figureFileSmall=null, figureFileBig=null, tableContent=
模态组合Macro-PMacro-RMacro-F1Accuracy(95%CI
临床信息+sMRI0.786 00.809 30.795 90.802 2(0.736 8,0.857 4)
临床信息+fMRI0.806 20.800 60.797 60.813 2(0.748 9,0.867 0)
sMRI+fMRI0.401 70.398 30.349 90.565 9(0.490 6,0.639 1)
临床信息+sMRI+fMRI0.793 00.805 50.796 80.804 4(0.740 8,0.859 4)
), ArticleFig(id=1240633256375284382, tenantId=1146029695717560320, journalId=1227665162245664772, articleId=1240633244039836657, language=CN, label=表4, caption=

基于不同多模态组合的sPLS-DA模型评价指标

, figureFileSmall=null, figureFileBig=null, tableContent=
模态组合Macro-PMacro-RMacro-F1Accuracy(95%CI
临床信息+sMRI0.786 00.809 30.795 90.802 2(0.736 8,0.857 4)
临床信息+fMRI0.806 20.800 60.797 60.813 2(0.748 9,0.867 0)
sMRI+fMRI0.401 70.398 30.349 90.565 9(0.490 6,0.639 1)
临床信息+sMRI+fMRI0.793 00.805 50.796 80.804 4(0.740 8,0.859 4)
)], attaches=null, journal=Journal(id=1227664546253402114, delFlag=0, nameCn=现代预防医学, nameEn=Modern Preventive Medicine, nameHistory1=null, nameHistory2=null, issn=1003-8507, eissn=null, cn=51-1365/R, coden=null, periodic=3, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=IeiuPXEZi6AA+k0VfvoiOQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Modern Preventive Medicine, journalRemark=null, publicationField=null, createdTime=1770627636734, updatedTime=1770628902248, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=M, firstLetterEn=M, subjectCode=Life Sciences, subjectName=null, subjectCodeEn=Life Sciences, subjectNameEn=null, picCn=IeiuPXEZi6AA+k0VfvoiOQ==, picEn=/9iTl8/ndms4tBz1fL28Pg==, jcr=null, cjcr=null, exts=[JournalExt(id=1227669854342280188, language=CN, name=现代预防医学, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770628902278, updatedTime=1770628902278, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://xdyfyxzz.paperopen.com/#/regist, submissionEditorUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionReviewUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1227669854396806141, language=EN, name=Modern Preventive Medicine, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770628902291, updatedTime=1770628902291, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://xdyfyxzz.paperopen.com/#/regist, submissionEditorUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionReviewUrl=http://xdyfyxzz.paperopen.com/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1227665162245664772, websiteList=[Website(id=1227687234141352800, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227665162245664772, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/xdyfyx/CN, language=CN, createTime=1770633045945, createBy=18614031015, updateTime=1770633090526, updateBy=18614031015, name=现代预防医学-中文, tplId=1146099689490845704, title=现代预防医学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1227687735088051072, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=articleTextType, value=kx, createTime=1770633165380, updateTime=1770633165380, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735071273853, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=banner, value=null, createTime=1770633165376, updateTime=1770633165376, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735113216899, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=grayFlag, value=0, createTime=1770633165386, updateTime=1770633165386, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735062885244, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=logo, value=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/file/pic?fileId=/XB5plC0xuykmQnycvtyrw==, createTime=1770633165374, updateTime=1770633165374, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735125799813, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=minRunFlag, value=0, createTime=1770633165389, updateTime=1770633165389, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735083856767, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/file/pic, createTime=1770633165379, updateTime=1770633165379, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735121605508, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=silenceFlag, value=0, createTime=1770633165388, updateTime=1770633165388, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735079662462, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770633165378, updateTime=1770633165378, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735096439681, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=themeColor, value=null, createTime=1770633165382, updateTime=1770633165382, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687735104828290, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234141352800, code=themeStyle, value=null, createTime=1770633165384, updateTime=1770633165384, creator=18614031015, updator=18614031015)]), Website(id=1227687234338485094, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227665162245664772, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/xdyfyx/EN, language=EN, createTime=1770633045992, createBy=18614031015, updateTime=1770633115374, updateBy=18614031015, name=现代预防医学-英文, tplId=1146101810881728533, title=Modern Preventive Medicine, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1227687709129507332, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=articleTextType, value=kx, createTime=1770633159191, updateTime=1770633159191, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709108535809, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=banner, value=null, createTime=1770633159186, updateTime=1770633159186, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709167256071, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=grayFlag, value=0, createTime=1770633159200, updateTime=1770633159200, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709095952896, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=logo, value=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/file/pic?fileId=/XB5plC0xuykmQnycvtyrw==, createTime=1770633159183, updateTime=1770633159183, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709179838985, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=minRunFlag, value=0, createTime=1770633159203, updateTime=1770633159203, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709121118723, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/file/pic, createTime=1770633159189, updateTime=1770633159189, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709171450376, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=silenceFlag, value=0, createTime=1770633159201, updateTime=1770633159201, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709112730114, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770633159187, updateTime=1770633159187, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709133701637, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=themeColor, value=null, createTime=1770633159192, updateTime=1770633159192, creator=18614031015, updator=18614031015), WebsiteProps(id=1227687709154673158, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1227687234338485094, code=themeStyle, value=null, createTime=1770633159197, updateTime=1770633159197, creator=18614031015, updator=18614031015)])], journalTitle=现代预防医学, weixinUrl=null, journalUrl=http://xdyfyxzz.paperopen.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Modern Preventive Medicine, journalPhotoCn=IeiuPXEZi6AA+k0VfvoiOQ==, journalPhotoEn=/9iTl8/ndms4tBz1fL28Pg==, journalFirstLetter=M, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/10.20043/j.cnki.MPM.202312346, detailUrlEn=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/10.20043/j.cnki.MPM.202312346, pdfUrlCn=https://castjournals.cast.org.cn/joweb/xdyfyx/CN/PDF/10.20043/j.cnki.MPM.202312346, pdfUrlEn=https://castjournals.cast.org.cn/joweb/xdyfyx/EN/PDF/10.20043/j.cnki.MPM.202312346, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于多模态数据整合的阿尔茨海默病分类研究
收藏切换
PDF下载
崔靖 1, 2 , 杨慧 2 , 秦瑶 2 , 陈杜荣 2 , 余红梅 2, 3, 4
现代预防医学 | 临床与预防 2024,51(10): 1889-1894
收起
收藏切换
现代预防医学 | 临床与预防 2024, 51(10): 1889-1894
基于多模态数据整合的阿尔茨海默病分类研究
全屏
崔靖1, 2, 杨慧2, 秦瑶2, 陈杜荣2, 余红梅2, 3, 4
作者信息
  • 1.山西医科大学第三医院(山西白求恩医院 山西医学科学院 同济山西医院),山西 太原 030032
  • 2.山西医科大学公共卫生学院卫生统计学教研室
  • 3.重大疾病风险评估山西省重点实验室
  • 4.煤炭环境致病与防治教育部重点实验室
  • 崔靖(1987—),女,博士,讲师,研究方向:队列统计方法研究与应用

通讯作者:

余红梅,E-mail:
Alzheimer’s disease classification based on multimodal data integration
Jing CUI1, 2, Hui YANG2, Yao QIN2, Du-rong CHEN2, Hong-mei YU2, 3, 4
Affiliations
  • Third Hospital of Shanxi Medical University, Taiyuan, Shanxi 030032, China
出版时间: 2024-05-25 doi: 10.20043/j.cnki.MPM.202312346
文章导航
收藏切换
目的

利用多模态数据的互补特性整合信息,实现对阿尔茨海默病的分类,为临床诊断提供参考。

方法

筛选阿尔茨海默病神经影像学计划数据库中同时具有临床信息、结构磁共振成像(sMRI)和功能磁共振成像(fMRI)的受试者共872例,将其分为训练集(612例)和测试集(260例)。基于三种单模态以及四种多模态组合在训练集中构建稀疏偏最小二乘-判别分析(sparse Partial Least Squares-Discriminant Analysis,sPLS-DA)分类模型实现多分类。利用宏观平均精确率(Macro-average of Precision,Macro-P)、宏观平均召回率(Macro-average of Recall,Macro-R)、宏观平均F1值(Macro-average of F1-score,Macro-F1)、及准确率(Accuracy)评价模型性能,在测试集中探讨最优模态组合的适用性。

结果

单模态中临床信息的分类性能优于sMRI和fMRI模态(Macro-P=0.781 8,Macro-R=0.804 6,Macro-F1=0.791 2,Accuracy=0.796 7),选择的最佳潜在成分个数为1,临床信息特征数量为9。四种多模态组合中临床信息+fMRI模态组合的分类能力最强(Macro-P=0.806 2,Macro-R=0.800 6,Macro-F1=0.797 6,Accuracy=0.813 2),选择的最佳潜在成分个数为1,特征数量为5;而sMRI+fMRI的分类能力最差(Macro-P=0.401 7,Macro-R=0.398 3,Macro-F1=0.349 9,Accuracy=0.565 9)。将在训练集中得到的最佳模态组合应用于测试集,得到的模型性能指标Macro-P为0.791 8,Macro-R为0.734 5,Macro-F1为0.758 4,Accuracy为0.766 4(0.646 0,0.846 5)。

结论

基于各多模态组合构建的sPLS-DA分类模型性能均高于单模态,其中临床信息+fMRI模态组合表现最佳,可辅助制定科学合理的临床诊断方案。

阿尔茨海默病  /  多模态  /  磁共振成像  /  多分类  /  稀疏偏最小二乘-判别分析
Objective

To achieve the classification of Alzheimer’s disease (AD) by integrating information that utilize the complementary properties of multimodal data, and to provide references for clinical diagnosis.

Methods

A total of 872 subjects were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), with both clinical information, structural magnetic resonance imaging (sMRI) and functional magnetic resonance imaging (fMRI) scans. They were divided into the training set (612 subjects) and test set (260 subjects). Based on three unimodal data and four multimodal combinations of different modalities, we constructed the sparse Partial Least Squares-Discriminant Analysis (sPLS-DA) classification models in the training set to achieve the multi-classification. The macro-averaged precision (Macro-P), macro-averaged recall (Macro-R), macro-averaged F1 value (Macro-F1), and accuracy were used to evaluate the model performance, with the optimal combination of modalities obtained explored for their applicability in the test set.

Results

The classification performance of clinical information (Macro-P=0.781 8, Macro-R=0.804 6, Macro-F1=0.791 2, Accuracy=0.796 7) among the unimodal information was better than that of sMRI and fMRI modalities. The optimal number of potential components was 1, and the number of clinical information features was 9. Among the four multimodal combinations, the clinical information + fMRI combination had the strongest classification ability (Macro-P=0.806 2,Macro-R=0.800 6, Macro-F1=0.797 6, Accuracy=0.813 2), with the optimal number of potential components selected as 1,and the number of features were 5, while the sMRI + fMRI had the worst classification ability (Macro-P=0.401 7, Macro-R=0.398 3, Macro-F1=0.349 9, Accuracy=0.565 9).Applying the best modal combination to the test set, the model performance metrics achieved were 0.791 8 for Macro-P, 0.734 5 for Macro-R, 0.758 4 for Macro-F1, and 0.766 4(0.646 0, 0.846 5) for Accuracy.

Conclusion

The performance of the sPLS-DA classification model constructed based on each multimodal combination was higher than that of the unimodal, among which the combination of clinical information + fMRI modality had the best performance, which couldgreatly facilitate the formulation of scientific and reasonable clinical diagnosis plans.

Alzheimer’s disease  /  Multimodal  /  Magnetic resonance imaging  /  Multi-classification  /  Sparse partial least squares-discriminant analysis
崔靖, 杨慧, 秦瑶, 陈杜荣, 余红梅. 基于多模态数据整合的阿尔茨海默病分类研究. 现代预防医学, 2024 , 51 (10) : 1889 -1894 . DOI: 10.20043/j.cnki.MPM.202312346
Jing CUI, Hui YANG, Yao QIN, Du-rong CHEN, Hong-mei YU. Alzheimer’s disease classification based on multimodal data integration[J]. Modern Preventive Medicine, 2024 , 51 (10) : 1889 -1894 . DOI: 10.20043/j.cnki.MPM.202312346
我国即将进入重度老龄化社会,这可能会导致阿尔茨海默病(Alzheimer’s Disease,AD)这一主要痴呆形式的患病率快速增长。预计到2050年,全球痴呆症患者人数将从2019年的5 500万增加至1.39亿,而目前我国60岁及以上老年人中有983万AD患者,数量居全球之首[1]。在目前没有可完全治愈或可普遍获得的治疗方法的情况下,降低患病风险是防治痴呆最可行和主动的方法。轻度认知障碍(mild cognitive impairment,MCI)是痴呆的早期预警。与正常认知(normal cognition,NC)相比,该状态人群的一个或多个认知区域会出现损害,虽不影响日常生活能力,也未达到痴呆诊断标准,但是其转化为AD的风险较高[2-3]
目前主要以患者典型临床表现、神经心理学测试、影像学、生物学、遗传学等多模态证据支持AD诊断[4]。然而,大多数研究侧重于单一模态数据模式,导致结果可能无法一致且不足以捕捉复杂疾病的异质性。多模态数据整合可以充分利用多个不同来源数据的互补特性,获得比单模态更准确、可靠和稳定的信息,从而提供更加有力的预测[5-6]。本研究基于不同单模态和不同多模态数据组合,采用稀疏偏最小二乘-判别分析算法构建对NC、MCI和AD的多分类辅助诊断模型,探索有利于诊断的最佳模态及其组合,为实现AD的早期筛查和临床诊断方案提供参考。
本研究的数据来源于阿尔茨海默病神经影像学计划(Alzheimer’s Disease Neuroimaging Initiative,ADNI)(http://adni.loni.usc.edu),该数据库包括患者基本信息、认知测试、影像、遗传学、脑脊液等数据,致力于揭示AD疾病病理机制,探索疾病临床评估标志物。研究共筛选了ADNI数据库中同时具有sMRI和fMRI数据的872例受试者,包括443例NC、300例MCI和129例AD。
本研究纳入的变量包括临床信息、结构磁共振成像(structural Magnetic Resonance Imaging,sMRI)和功能磁共振成像(functional Magnetic Resonance Imaging,fMRI)三种模态。其中临床信息包含人口学资料(年龄、性别、受教育年限和婚姻状态)、APOE(Apolipoprotein E)基因以及15种神经心理测试量表,见表1,共计20个变量。
sMRI和fMRI两模态分别从脑组织形态学特征、脑功能连接特征角度反映了与AD有关的影像学结构与功能表现。sMRI利用基于体素的形态测量学方法,计算大脑不同结构成分在单位体积内所包含体素的密度,确定90个脑区的平均灰质体积,即sMRI特征。fMRI数据利用脑功能网络连接分析方法,以各脑区作为网络节点,采用Pearson方法计算任意两个脑区的相关系数,从而反映脑区间的功能联系强度。将90个脑区之间相关系数转化为二维矩阵得到4005个fMRI特征。
由于fMRI模态经特征提取后得到的特征数远远大于研究样本数,可能带来“维度灾难”。本研究利用随机森林-递归特征消除(Random Forest-Recursive Feature Elimination,RF-RFE)方法进行特征选择[7]。基于初始fMRI特征利用Bootstrap方法抽取样本,采用向后搜索算法,每次迭代舍弃重要性末位特征后,在剩余特征集中再次建立RF算法。重复上述过程直至保留最优性能下的77个特征。
本研究利用稀疏偏最小二乘—判别分析(sparse Partial Least Squares-Discriminant Analysis,sPLS-DA)方法,通过考虑各模态变量与分类结局之间的相关性,最大化潜在成分间的协方差以提取对数据具有最佳解释能力的主成分进行回归建模。并进一步对特征权重施加Lasso惩罚,将影响较弱的特征的系数设置为零,为多模态数据整合提供稀疏性解决方案。
利用十折交叉验证评价模型性能。由于数据集的类别不平衡,本文采用对此问题敏感的宏观平均值,通过计算(n表示总类别n=3,c表示各类别NC/MCI/AD),平等对待包括少数类在内的所有类别的一般平均值,得到宏观平均精确率(Macro-average of Precision,Macro-P),宏观平均召回率(Macro-average of Recall,Macro-R)和宏观平均F1值(Macro-average of F1-score,Macro-F1),及准确率(Accuracy)指标评价模型性能[8]
采用R 4.3.1软件进行统计学分析。计数资料以频数(百分比)表示,采用χ2检验进行组间比较;偏态分布的计量资料,以MP25P75)表示,采用非参数检验进行组间比较。以P<0.05为差异有统计学意义。利用caret包实现特征选择,mixOmics包实现sPLS-DA模型构建。
本研究将整个数据集分为均衡可比的训练集(n=612)和测试集(n=260),分别进行模型构建和泛化性能检验。对训练集变量进行组间比较,发现除婚姻状态外三组间所有变量的差异均有统计学意义(P<0.05),详见表2
对各单模态信息分别采用sPLS-DA方法进行分类。图1-A为临床信息的主成分数选择图示,初步确定主成分个数ncomp=4,最小错分率下的预测距离为马氏距离。然后以四个主成分的信息对结局变量进行预测,同时对特征进行Lasso稀疏。图1-D结果显示最终成分数为1,特征数量为9时分类错误率最低。其他图示(图1):sMRI模态的最佳潜在成分个数为5,特征数量为4;fMRI模态的最佳潜在成分个数为4,特征数量为40。基于三种单模态构建的模型性能评价,可得临床信息模态的鉴别分类能力最高,fMRI次之,sMRI最差,详见表3
针对四种多模态组合分别构建sPLS-DA分类模型。从图2-B可知,临床信息+fMRI模态组合初步确定的主成分个数为2,最小错分率下的预测距离为马氏距离。图2-D结果显示,最终成分数为1,特征数量为5时分类错误率最低。其他图示(图2):临床信息+sMRI、sMRI+fMRI、临床信息+sMRI+fMRI模态组合的最佳潜在成分个数分别为1、6、1;特征数量分别为9、120、10。从表4的模型评价指标可得:临床信息+fMRI模态组合的分类能力最强,sMRI+fMRI的分类能力较差。
将在训练集中得到的最佳模态组合(临床信息+fMRI)应用于测试集中,得到的模型性能指标Macro-P=0.791 8;Macro-R=0.734 5;Macro-F1=0.758 4;Accuracy为0.766 4(0.646 0,0.846 5)。尽管此时模型的性能较低于训练集,但考虑到数据分布差异,可认为此性能差异是在合理范围内,该模型的泛化性较优。
AD的早诊早治是我们长期关注并重点研究的公共卫生和临床重大难题。MCI为介于NC和AD之间的过渡阶段,存在着逆转为NC和进展为AD的双向转归可能,是干预和延缓痴呆进展的关键窗口期[9-10]。目前AD的诊断技术多样,从“模态”角度看,多模态数据整合可以充分利用多个不同来源数据的互补特性,获得比单模态更准确、可靠和稳定的信息。因此,利用不同多模态组合识别NC、MCI和AD三阶段、探索有利于诊断的最佳组合,可避免不必要的资源消耗并提高诊断准确率。
我们利用单模态数据对人群进行分类时,发现临床信息的效果较神经影像标志物更好。其中APOEε4是已得到共识的AD致病基因,该基因的携带会增加患病风险[11]。对于已表现出不同程度认知障碍的MCI和AD状态患者,神经量表可以记录AD的各种特征,为其认知功能、日常生活能力及精神行为状态的评估提供较为客观的依据[12-13]。这与2023年发布的《前驱期阿尔茨海默病的简易筛查中国专家共识》一致,传统的神经心理测试目前仍是确定认知水平和认知障碍所处阶段的基本手段,对于提高MCI阶段的检出率和临床诊断准确率很有帮助[14]。因此,规范的神经量表不仅可以为临床诊断工作提供重要参考依据,还有助于大规模快速筛查认知障碍个体。
对于同一感兴趣大脑区域的病理变化可同时通过sMRI和fMRI分别提供脑组织形态和脑功能连接的补充信息,进一步筛查AD的高危人群。值得注意的是,临床信息+sMRI+fMRI模态组合的分类性能却低于临床信息+fMRI,这说明分类性能的提高并不完全是由于加入了更多的特征信息而引起。尽管添加更多特征可以提高模型的置信度,但同时也会增加额外的噪声,使得模型更为嘈杂,性能降低[15]。有研究将AD视为脑网络的失连接疾病,认为功能差异可能存在于阿尔茨海默病的早期阶段,甚至在出现脑萎缩和认知能力下降之前[16-17]。这与本研究的结果发现fMRI中存在着有意义的与分类相关的特征,临床信息+fMRI模态组合的分类性能更佳是一致的。可能的原因是MCI患者早期大脑解剖结构的变化并不明确,且sMRI对于发现的脑区变化如海马萎缩等并不具有疾病特异性[18]。而fMRI可以早期敏感地发现AD患者及其高危人群的大脑功能连接异常,该特征的加入可进一步提高了sMRI对AD的诊断及MCI的进展预测[19]。因此fMRI是一个有着广泛应用前景的研究领域。
本研究仍存在一些局限性:(1)本研究纳入的是从神经影像提取的结构化数据特征,相对图像数据可能缺少部分信息。(2)本文研究对象来自公共数据队列,代表高水平参与度的患者,结果外推可能存在局限。
综上,本研究利用临床信息、sMRI和fMRI数据构建不同的模态组合,基于sPLS-DA方法同时进行特征选择和新样本分类。发现临床信息的实用性较影像特征更为准确,因此加强临床信息和神经心理测试量表的操作标准化、规范化很有必要。其次,影像特征中fMRI较sMRI贡献了更有意义的信息,多模态数据组合“临床信息+fMRI”提供了更高的分类准确率。未来的研究可关注fMRI成像,以期从中寻找到新的潜在影像学标志物,提高AD诊断的准确性。
  • 国家自然科学基金资助项目(81973154,82273742)
  • 山西省基础研究计划自由探索类青年项目(202103021223242)
  • 山西省研究生教育创新项目(2023KY406)
参考文献 引证文献
排序方式:
[1]
Ren RJ, Qi JL, Lin SH, et al. The China alzheimer report 2022[J]. General Psychiatry, 2022, 35(1): e100751.
[2]
Zhang Z, Zhao YH, Bian Y. A role of socioeconomic status in cognitive impairment among older adults in Macau: a decomposition approach[J]. Frontiers in Aging Neuroscience, 2022, 14: 804307.
[3]
韩红娟,陈杜荣,秦瑶,等.基于Stacking集成策略的阿尔茨海默病诊断模型研究[J].现代预防医学202249(22):4045-4051, 4089.
Han HJ, Chen DR, Qin Y, et al. Multi-classification diagnosis of Alzheimer’s disease based on stacking ensemble strategy[J]. Modern Preventive Medicine, 2022, 49(22): 4045-4051, 4089.
[4]
Dubois B, Villain N, Frisoni GB, et al. Clinical diagnosis of Alzheimer’s disease: recommendations of the international working group[J]. The Lancet. Neurology, 2021, 20(6): 484-496.
[5]
Stahlschmidt SR, Ulfenborg B, Synnergren J. Multimodal deep learning for biomedical data fusion: a review[J]. Briefings in Bioinformatics, 2022, 23(2): bbab569.
[6]
Steyaert S, Pizurica M, Nagaraj D, et al. Multimodal data fusion for cancer biomarker discovery with deep learning[J]. Nature Machine Intelligence, 2023, 5(4): 351-362.
[7]
Liu W, Wang JY. Recursive elimination–election algorithms for wrapper feature selection[J]. Applied Soft Computing, 2021, 113(Part B): 107956.
[8]
Velarde-Alvarado P, Gonzalez H, Martínez-Peláez R, et al. A novel framework for generating personalized network datasets for NIDS based on traffic aggregation[J]. Sensors, 2022, 22(5): 1847.
[9]
Iraniparast M, Shi YD, Wu Y, et al. Cognitive reserve and mild cognitive impairment: predictors and rates of reversion to intact cognition vs progression to dementia[J]. Neurology, 2022, 98(11): e1114-e1123.
[10]
韩红娟,秦瑶,陈杜荣,等.轻度认知障碍患者的双向转归研究[J].中国全科医学202225(9):1070-1076.
Han HJ, Qin Y, Chen DR, et al. Progression and reversion of mild cognitiveimpairment:a study using data from the uniform data set[J]. Chinese General Practice, 2022, 25(9): 1070-1076.
[11]
Padala SP, Newhouse PA. Blood-based biomarkers in Alzheimer’s disease: a mini-review[J]. Metabolic Brain Disease, 2023, 38(1): 185-193.
[12]
Jack CRJ, Bennett DA,Blennow K, et al. NIA-AA research framework: toward a biological definition of alzheimer’s disease[J]. Alzheimer’s & Dementia: the Journal of the Alzheimer’s Association, 2018, 14(4): 535-562.
[13]
赵倩,冯金玉,洪兆晨,等.轻度认知功能障碍早期筛查量表的研究进展[J].循证护理20239(3):435-439.
Zhao Q,Feng JY, Hong ZC, et al. Research progress of early screening scale for mild cognitive impairment[J]. Chinese Evidence-Based Nursing, 2023, 9(3): 435-439.
[14]
陈晓春,贾建平,郭起浩,等.前驱期阿尔茨海默病的简易筛查中国专家共识(2023年版)[J].中华神经医学杂志202322(5):433-444.
Chen XC,Jia JP, Guo QH, et al. Chinese expert consensus on brief screening of prodromal Alzheimer’s disease(2023)[J]. Chinese Journal of Neuromedicine, 2023, 22(5): 433-444.
[15]
El-Sappagh S, Alonso JM, Islam SMR, et al. A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease[J]. Scientific Reports, 2021, 11(1): 2660.
[16]
Chen ZH, Chen KL, Li YX, et al. Structural, static, and dynamic functional MRI predictors for conversion from mild cognitive impairment to Alzheimer’s disease: Inter-cohort validation of Shanghai Memory Study and ADNI[J]. Human Brain Mapping, 2024, 45(1): e26529.
[17]
李瑜霞,李永秋,孙宇,等.源于阿尔茨海默病的轻度认知障碍患者脑结构及静息态功能磁共振研究进展[J].中国临床医学影像杂志201627(2):131-134.
Li YX, Li YQ, Sun Y, et al. Structural and resting state functional MRI characteristics of patients with mild cognitive impairment due to Alzheimer’s disease[J]. Journal ofChina Clinic Medical Imaging, 2016, 27(2): 131-134.
[18]
Creavin ST, Wisniewski S, Noel-Storr AH, et al. Mini-Mental state examination (MMSE) for the detection of dementia in clinically unevaluated People aged 65 and over in community and primary care populations[J]. Cochrane Database of Systematic Reviews: Online, 2016, 2016(1): CD011145.
[19]
何雨洁,闫少珍,卢洁.静息态功能磁共振对阿尔茨海默病早期诊断的研究进展[J].磁共振成像202415(1):173-178.
He YJ, Yan SZ, Lu J. Research advance on resting-state functional magnetic resonance imaging in the early diagnosis of Alzheimer’s disease[J]. Chinese Journal of Magnetic Resonance Imaging, 2024, 15(1): 173-178.
2024年第51卷第10期
PDF下载
66
28
引用本文
BibTeX
文章信息
doi: 10.20043/j.cnki.MPM.202312346
  • 接收时间:2023-12-21
  • 首发时间:2026-03-17
  • 出版时间:2024-05-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-12-21
基金
国家自然科学基金资助项目(81973154,82273742)
山西省基础研究计划自由探索类青年项目(202103021223242)
山西省研究生教育创新项目(2023KY406)
作者信息
    1.山西医科大学第三医院(山西白求恩医院 山西医学科学院 同济山西医院),山西 太原 030032
    2.山西医科大学公共卫生学院卫生统计学教研室
    3.重大疾病风险评估山西省重点实验室
    4.煤炭环境致病与防治教育部重点实验室

通讯作者:

余红梅,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/xdyfyx/CN/10.20043/j.cnki.MPM.202312346
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏