Random-Forest-Algorithm-Based Applications of the Basic Characteristics and Serum and Imaging Biomarkers to Diagnose Mild Cognitive Impairment

Mild cognitive impairment (MCI) is considered the early stage of Alzheimer's Disease (AD). The purpose of our study was to analyze the basic characteristics and serum and imaging biomarkers for the diagnosis of MCI patients as a more objective and accurate approach. The Montreal Cognitive Test...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Current Alzheimer research Ročník 19; číslo 1; s. 76
Hlavní autori: Yang, Juan, Sui, Haijing, Jiao, Ronghong, Zhang, Min, Zhao, Xiaohui, Wang, Lingling, Deng, Wenping, Liu, Xueyuan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United Arab Emirates 01.01.2022
Predmet:
ISSN:1875-5828, 1875-5828
On-line prístup:Zistit podrobnosti o prístupe
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Mild cognitive impairment (MCI) is considered the early stage of Alzheimer's Disease (AD). The purpose of our study was to analyze the basic characteristics and serum and imaging biomarkers for the diagnosis of MCI patients as a more objective and accurate approach. The Montreal Cognitive Test was used to test 119 patients aged ≥65. Such serum biomarkers were detected as preprandial blood glucose, triglyceride, total cholesterol, Aβ1-40, Aβ1-42, and P-tau. All the subjects were scanned with 1.5T MRI (GE Healthcare, WI, USA) to obtain DWI, DTI, and ASL images. DTI was used to calculate the anisotropy fraction (FA), DWI was used to calculate the apparent diffusion coefficient (ADC), and ASL was used to calculate the cerebral blood flow (CBF). All the images were then registered to the SPACE of the Montreal Neurological Institute (MNI). In 116 brain regions, the medians of FA, ADC, and CBF were extracted by automatic anatomical labeling. The basic characteristics included gender, education level, and previous disease history of hypertension, diabetes, and coronary heart disease. The data were randomly divided into training sets and test ones. The recursive random forest algorithm was applied to the diagnosis of MCI patients, and the recursive feature elimination (RFE) method was used to screen the significant basic features and serum and imaging biomarkers. The overall accuracy, sensitivity, and specificity were calculated, respectively, and so were the ROC curve and the area under the curve (AUC) of the test set. When the variable of the MCI diagnostic model was an imaging biomarker, the training accuracy of the random forest was 100%, the correct rate of the test was 86.23%, the sensitivity was 78.26%, and the specificity was 100%. When combining the basic characteristics, the serum and imaging biomarkers as variables of the MCI diagnostic model, the training accuracy of the random forest was found to be 100%; the test accuracy was 97.23%, the sensitivity was 94.44%, and the specificity was 100%. RFE analysis showed that age, Aβ1-40, and cerebellum_4_6 were the most important basic feature, serum biomarker, imaging biomarker, respectively. Imaging biomarkers can effectively diagnose MCI. The diagnostic capacity of the basic trait biomarkers or serum biomarkers for MCI is limited, but their combination with imaging biomarkers can improve the diagnostic capacity, as indicated by the sensitivity of 94.44% and the specificity of 100% in our model. As a machine learning method, a random forest can help diagnose MCI effectively while screening important influencing factors.
AbstractList Mild cognitive impairment (MCI) is considered the early stage of Alzheimer's Disease (AD). The purpose of our study was to analyze the basic characteristics and serum and imaging biomarkers for the diagnosis of MCI patients as a more objective and accurate approach.BACKGROUNDMild cognitive impairment (MCI) is considered the early stage of Alzheimer's Disease (AD). The purpose of our study was to analyze the basic characteristics and serum and imaging biomarkers for the diagnosis of MCI patients as a more objective and accurate approach.The Montreal Cognitive Test was used to test 119 patients aged ≥65. Such serum biomarkers were detected as preprandial blood glucose, triglyceride, total cholesterol, Aβ1-40, Aβ1-42, and P-tau. All the subjects were scanned with 1.5T MRI (GE Healthcare, WI, USA) to obtain DWI, DTI, and ASL images. DTI was used to calculate the anisotropy fraction (FA), DWI was used to calculate the apparent diffusion coefficient (ADC), and ASL was used to calculate the cerebral blood flow (CBF). All the images were then registered to the SPACE of the Montreal Neurological Institute (MNI). In 116 brain regions, the medians of FA, ADC, and CBF were extracted by automatic anatomical labeling. The basic characteristics included gender, education level, and previous disease history of hypertension, diabetes, and coronary heart disease. The data were randomly divided into training sets and test ones. The recursive random forest algorithm was applied to the diagnosis of MCI patients, and the recursive feature elimination (RFE) method was used to screen the significant basic features and serum and imaging biomarkers. The overall accuracy, sensitivity, and specificity were calculated, respectively, and so were the ROC curve and the area under the curve (AUC) of the test set.METHODSThe Montreal Cognitive Test was used to test 119 patients aged ≥65. Such serum biomarkers were detected as preprandial blood glucose, triglyceride, total cholesterol, Aβ1-40, Aβ1-42, and P-tau. All the subjects were scanned with 1.5T MRI (GE Healthcare, WI, USA) to obtain DWI, DTI, and ASL images. DTI was used to calculate the anisotropy fraction (FA), DWI was used to calculate the apparent diffusion coefficient (ADC), and ASL was used to calculate the cerebral blood flow (CBF). All the images were then registered to the SPACE of the Montreal Neurological Institute (MNI). In 116 brain regions, the medians of FA, ADC, and CBF were extracted by automatic anatomical labeling. The basic characteristics included gender, education level, and previous disease history of hypertension, diabetes, and coronary heart disease. The data were randomly divided into training sets and test ones. The recursive random forest algorithm was applied to the diagnosis of MCI patients, and the recursive feature elimination (RFE) method was used to screen the significant basic features and serum and imaging biomarkers. The overall accuracy, sensitivity, and specificity were calculated, respectively, and so were the ROC curve and the area under the curve (AUC) of the test set.When the variable of the MCI diagnostic model was an imaging biomarker, the training accuracy of the random forest was 100%, the correct rate of the test was 86.23%, the sensitivity was 78.26%, and the specificity was 100%. When combining the basic characteristics, the serum and imaging biomarkers as variables of the MCI diagnostic model, the training accuracy of the random forest was found to be 100%; the test accuracy was 97.23%, the sensitivity was 94.44%, and the specificity was 100%. RFE analysis showed that age, Aβ1-40, and cerebellum_4_6 were the most important basic feature, serum biomarker, imaging biomarker, respectively.RESULTSWhen the variable of the MCI diagnostic model was an imaging biomarker, the training accuracy of the random forest was 100%, the correct rate of the test was 86.23%, the sensitivity was 78.26%, and the specificity was 100%. When combining the basic characteristics, the serum and imaging biomarkers as variables of the MCI diagnostic model, the training accuracy of the random forest was found to be 100%; the test accuracy was 97.23%, the sensitivity was 94.44%, and the specificity was 100%. RFE analysis showed that age, Aβ1-40, and cerebellum_4_6 were the most important basic feature, serum biomarker, imaging biomarker, respectively.Imaging biomarkers can effectively diagnose MCI. The diagnostic capacity of the basic trait biomarkers or serum biomarkers for MCI is limited, but their combination with imaging biomarkers can improve the diagnostic capacity, as indicated by the sensitivity of 94.44% and the specificity of 100% in our model. As a machine learning method, a random forest can help diagnose MCI effectively while screening important influencing factors.CONCLUSIONImaging biomarkers can effectively diagnose MCI. The diagnostic capacity of the basic trait biomarkers or serum biomarkers for MCI is limited, but their combination with imaging biomarkers can improve the diagnostic capacity, as indicated by the sensitivity of 94.44% and the specificity of 100% in our model. As a machine learning method, a random forest can help diagnose MCI effectively while screening important influencing factors.
Mild cognitive impairment (MCI) is considered the early stage of Alzheimer's Disease (AD). The purpose of our study was to analyze the basic characteristics and serum and imaging biomarkers for the diagnosis of MCI patients as a more objective and accurate approach. The Montreal Cognitive Test was used to test 119 patients aged ≥65. Such serum biomarkers were detected as preprandial blood glucose, triglyceride, total cholesterol, Aβ1-40, Aβ1-42, and P-tau. All the subjects were scanned with 1.5T MRI (GE Healthcare, WI, USA) to obtain DWI, DTI, and ASL images. DTI was used to calculate the anisotropy fraction (FA), DWI was used to calculate the apparent diffusion coefficient (ADC), and ASL was used to calculate the cerebral blood flow (CBF). All the images were then registered to the SPACE of the Montreal Neurological Institute (MNI). In 116 brain regions, the medians of FA, ADC, and CBF were extracted by automatic anatomical labeling. The basic characteristics included gender, education level, and previous disease history of hypertension, diabetes, and coronary heart disease. The data were randomly divided into training sets and test ones. The recursive random forest algorithm was applied to the diagnosis of MCI patients, and the recursive feature elimination (RFE) method was used to screen the significant basic features and serum and imaging biomarkers. The overall accuracy, sensitivity, and specificity were calculated, respectively, and so were the ROC curve and the area under the curve (AUC) of the test set. When the variable of the MCI diagnostic model was an imaging biomarker, the training accuracy of the random forest was 100%, the correct rate of the test was 86.23%, the sensitivity was 78.26%, and the specificity was 100%. When combining the basic characteristics, the serum and imaging biomarkers as variables of the MCI diagnostic model, the training accuracy of the random forest was found to be 100%; the test accuracy was 97.23%, the sensitivity was 94.44%, and the specificity was 100%. RFE analysis showed that age, Aβ1-40, and cerebellum_4_6 were the most important basic feature, serum biomarker, imaging biomarker, respectively. Imaging biomarkers can effectively diagnose MCI. The diagnostic capacity of the basic trait biomarkers or serum biomarkers for MCI is limited, but their combination with imaging biomarkers can improve the diagnostic capacity, as indicated by the sensitivity of 94.44% and the specificity of 100% in our model. As a machine learning method, a random forest can help diagnose MCI effectively while screening important influencing factors.
Author Jiao, Ronghong
Liu, Xueyuan
Wang, Lingling
Yang, Juan
Sui, Haijing
Deng, Wenping
Zhao, Xiaohui
Zhang, Min
Author_xml – sequence: 1
  givenname: Juan
  surname: Yang
  fullname: Yang, Juan
  organization: Department of Neurology, Shanghai Pudong New Area People's Hospital,Shanghai, 201299, China
– sequence: 2
  givenname: Haijing
  surname: Sui
  fullname: Sui, Haijing
  organization: Department of Radiology, Shanghai Pudong New Area People's Hospital, Shanghai, People's Republic of China
– sequence: 3
  givenname: Ronghong
  surname: Jiao
  fullname: Jiao, Ronghong
  organization: Department of Clinical Laboratory, Shanghai Pudong New Area People's Hospital, Shanghai, People's Republic of China
– sequence: 4
  givenname: Min
  surname: Zhang
  fullname: Zhang, Min
  organization: hcit.ai Co., Shanghai, People's Republic of China
– sequence: 5
  givenname: Xiaohui
  surname: Zhao
  fullname: Zhao, Xiaohui
  organization: hcit.ai Co., Shanghai, People's Republic of China
– sequence: 6
  givenname: Lingling
  surname: Wang
  fullname: Wang, Lingling
  organization: Department of Neurology, Shanghai Pudong New Area People's Hospital, Shanghai, People's Republic of China
– sequence: 7
  givenname: Wenping
  surname: Deng
  fullname: Deng, Wenping
  organization: Huawei Technology Co., Ltd Co, Shanghai, People's Republic of China
– sequence: 8
  givenname: Xueyuan
  surname: Liu
  fullname: Liu, Xueyuan
  organization: Department of Neurology, Shanghai Pudong New Area People's Hospital,Shanghai, 201299, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35088670$$D View this record in MEDLINE/PubMed
BookMark eNpNkN1KAzEQhYNUtFZfQeKdN6tJ9i-5bKvVQkXw53pJk9ltcDdZk6zgS_jMLlrBm5kD5-MMZ07QxDoLCF1QcsVomV3TvCgZyQkVRVEwRijjlBHBygM0pbzMk5wzPvmnj9BxmhPOi5JM0deTtNp1ycp5CDGZt43zJu66ZCEDaDzv-9YoGY2zAbsaxx3g0TEKL3fSSxXBmxCNCniMwc_gh-5HrTvZGNvghXGd9G_gA44O3xjZWBcAP5hW46VrrInmA0a6l8Z3YOMpOqxlG-Bsv2fodXX7srxPNo936-V8k6gspzGRElIuVFYywTOdqnEITSkQ4CLVwIusThnVBIiQQBQTtdacp1zmXJSgtmyGLn9ze-_eh7F51ZmgoG2lBTeEihVsPMDSNBvR8z06bDvQVe_NWOmz-vsh-waK83Zj
CitedBy_id crossref_primary_10_1097_MD_0000000000034979
crossref_primary_10_3389_fnhum_2024_1378896
crossref_primary_10_3390_jdad2030028
crossref_primary_10_1136_bmjopen_2023_075466
crossref_primary_10_3389_fpsyt_2023_1266548
crossref_primary_10_1016_j_gerinurse_2025_103530
crossref_primary_10_1186_s12880_025_01645_w
crossref_primary_10_4103_NI_Neurol_India_D_23_00014
crossref_primary_10_1186_s12920_024_01995_4
crossref_primary_10_2196_59370
ContentType Journal Article
Copyright Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.net.
Copyright_xml – notice: Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.net.
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.2174/1567205019666220128120927
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
EISSN 1875-5828
ExternalDocumentID 35088670
Genre Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: Fund of Shanghai Municipal Health Commission
  grantid: 202140101
– fundername: Training Program for Academic Pioneers in Pudong New Area
  grantid: PWRD2020-02
– fundername: Multi-center clinical study of graded diagnosis and treatment of early cognitive dysfunction
  grantid: 17411950100
GroupedDBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
ID FETCH-LOGICAL-c451t-aae389c472984d3c84d9d11e0e893de864f321d0e09ae0c29fdd8838a5897ecb2
IEDL.DBID 7X8
ISICitedReferencesCount 9
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000826095800007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1875-5828
IngestDate Fri Jul 11 05:59:44 EDT 2025
Thu Jan 02 22:55:13 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords algorithms
screening
mild cognitive impairment
cognitive dysfunction
Machine learning
diagnostic tool
Language English
License Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.net.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c451t-aae389c472984d3c84d9d11e0e893de864f321d0e09ae0c29fdd8838a5897ecb2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://doi.org/10.2174/1567205019666220128120927
PMID 35088670
PQID 2623892334
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2623892334
pubmed_primary_35088670
PublicationCentury 2000
PublicationDate 2022-01-01
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: 2022-01-01
  day: 01
PublicationDecade 2020
PublicationPlace United Arab Emirates
PublicationPlace_xml – name: United Arab Emirates
PublicationTitle Current Alzheimer research
PublicationTitleAlternate Curr Alzheimer Res
PublicationYear 2022
Score 2.3948119
Snippet Mild cognitive impairment (MCI) is considered the early stage of Alzheimer's Disease (AD). The purpose of our study was to analyze the basic characteristics...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 76
SubjectTerms Aged
Algorithms
Alzheimer Disease - diagnostic imaging
Biomarkers
Cognitive Dysfunction - diagnostic imaging
Humans
Magnetic Resonance Imaging - methods
Title Random-Forest-Algorithm-Based Applications of the Basic Characteristics and Serum and Imaging Biomarkers to Diagnose Mild Cognitive Impairment
URI https://www.ncbi.nlm.nih.gov/pubmed/35088670
https://www.proquest.com/docview/2623892334
Volume 19
WOSCitedRecordID wos000826095800007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEA6-EC8-8P0igtdg82ibnGRdFQVdRFT2tqRJVgu77bqt_gx_s5NsF_UgCF5CoU1p0-nky3xfZhA6Fp4M0paSJDaGCLAKklGdEZrFXFMupQp5up9u0k5Hdrvqrgm4VY2scuoTg6O2pfEx8hMG87QENMLF6eiV-KpRnl1tSmjMonkOUMZLutJu2P0GMJx4RmgRHXm1M-DuE1ippCyKfUKYJGEscEgsUiz9HVyGSeZy5b-Pt4qWG3iJWxN7WEMzrlhHH_e6sOALfRnOqiatwTP0rF-G5AymMItb3zhsXPYxQEIMZ3KD2z-zOWO4DQbn8jYMR9fDUOEIn-Xl0It8xhWuS3w-0e45fJsPLG5P1Ulw9UjnYx-L3ECPlxcP7SvS1GEgRsS0Jlo7eDcjAIdLYbmBRllKXeQA7FgnE9HnjNrIRUq7yDDVt1ZKLnUsVepMxjbRXFEWbhvhyPAs9RlvYp8iQqiM2sTaRBmTGJ1psYOOpsPbAzv35IUuXPlW9b4GeAdtTb5RbzRJyNHjHmUmabT7h957aIn5HQwhirKP5vvwl7sDtGDe67waHwYDgrZzd_sJ8F3Rkg
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Random-Forest-Algorithm-Based+Applications+of+the+Basic+Characteristics+and+Serum+and+Imaging+Biomarkers+to+Diagnose+Mild+Cognitive+Impairment&rft.jtitle=Current+Alzheimer+research&rft.au=Yang%2C+Juan&rft.au=Sui%2C+Haijing&rft.au=Jiao%2C+Ronghong&rft.au=Zhang%2C+Min&rft.date=2022-01-01&rft.issn=1875-5828&rft.eissn=1875-5828&rft.volume=19&rft.issue=1&rft.spage=76&rft_id=info:doi/10.2174%2F1567205019666220128120927&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1875-5828&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1875-5828&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1875-5828&client=summon