A Transcriptomics-Based Machine Learning Model Discriminating Mild Cognitive Impairment and the Prediction of Conversion to Alzheimer's Disease.

Publisher: MDPI Country of Publication: Switzerland NLM ID: 101600052 Publication Model: Electronic Cited Medium: Internet ISSN: 2073-4409 (Electronic) Linking ISSN: 20734409 NLM ISO Abbreviation: Cells Subsets: MEDLINE

Original Publication: Basel, Switzerland : MDPI

Alzheimer Disease*/genetics ; Alzheimer Disease*/diagnosis ; Alzheimer Disease*/metabolism ; Cognitive Dysfunction*/genetics ; Cognitive Dysfunction*/diagnosis ; Machine Learning* ; Disease Progression* ; Transcriptome*/genetics ; Biomarkers*/metabolism; Humans ; Female ; Male ; Aged ; Aged, 80 and over ; Gene Expression Profiling

The clinical spectrum of Alzheimer's disease (AD) ranges dynamically from asymptomatic and mild cognitive impairment (MCI) to mild, moderate, or severe AD. Although a few disease-modifying treatments, such as lecanemab and donanemab, have been developed, current therapies can only delay disease progression rather than halt it entirely. Therefore, the early detection of MCI and the identification of MCI patients at high risk of progression to AD remain urgent unmet needs in the super-aged era. This study utilized transcriptomics data from cognitively unimpaired (CU) individuals, MCI, and AD patients in the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort and leveraged machine learning models to identify biomarkers that differentiate MCI from CU and also distinguish AD from MCI individuals. Furthermore, Cox proportional hazards analysis was conducted to identify biomarkers predictive of the progression from MCI to AD. Our machine learning models identified a unique set of gene expression profiles capable of achieving an area under the curve (AUC) of 0.98 in distinguishing those with MCI from CU individuals. A subset of these biomarkers was also found to be significantly associated with the risk of progression from MCI to AD. A linear mixed model demonstrated that plasma tau phosphorylated at threonine 181 (pTau181) and neurofilament light chain (NFL) exhibit the prognostic value in predicting cognitive decline longitudinally. These findings underscore the potential of integrating machine learning (ML) with transcriptomic profiling in the early detection and prognostication of AD. This integrated approach could facilitate the development of novel diagnostic tools and therapeutic strategies aimed at delaying or preventing the onset of AD in at-risk individuals. Future studies should focus on validating these biomarkers in larger, independent cohorts and further investigating their roles in AD pathogenesis.

J Alzheimers Dis. 2021;82(s1):S109-S126. (PMID: 33325385)
Alzheimers Dement. 2011 May;7(3):270-9. (PMID: 21514249)
Genome Biol. 2014;15(12):550. (PMID: 25516281)
Front Dement. 2023;2:. (PMID: 38895707)
Nat Med. 1997 Sep;3(9):1016-20. (PMID: 9288729)
N Engl J Med. 2023 Jan 5;388(1):9-21. (PMID: 36449413)
Nat Rev Neurol. 2021 Nov;17(11):689-701. (PMID: 34522039)
Psychol Bull. 1993 Nov;114(3):552-566. (PMID: 8272470)
Lancet Neurol. 2020 May;19(5):422-433. (PMID: 32333900)
Alzheimers Res Ther. 2020 Nov 10;12(1):145. (PMID: 33172501)
Nat Med. 2019 Feb;25(2):277-283. (PMID: 30664784)
Proc Natl Acad Sci U S A. 2018 Feb 6;115(6):E1289-E1298. (PMID: 29358399)
Int J Mol Sci. 2022 Aug 11;23(16):. (PMID: 36012242)
Dement Geriatr Cogn Dis Extra. 2013 Sep 28;3(1):320-32. (PMID: 24174927)
Neurology. 2018 Aug 28;91(9):e867-e877. (PMID: 30054439)
JAMA Neurol. 2019 Jul 1;76(7):791-799. (PMID: 31009028)
Cells. 2024 Jun 22;13(13):. (PMID: 38994939)
Brain Imaging Behav. 2012 Dec;6(4):502-16. (PMID: 22782295)
Cochrane Database Syst Rev. 2021 Jul 27;7:CD010783. (PMID: 34313331)
Alzheimers Res Ther. 2020 Jul 16;12(1):87. (PMID: 32677993)
Alzheimers Dement. 2007 Jul;3(3):186-91. (PMID: 19595937)
Nat Commun. 2023 Mar 25;14(1):1670. (PMID: 36966157)
Alzheimers Dement. 2022 Dec;18(12):2493-2508. (PMID: 35142026)
Br J Psychiatry. 2006 Nov;189:399-404. (PMID: 17077428)
Lancet Public Health. 2022 Feb;7(2):e105-e125. (PMID: 34998485)
Front Aging Neurosci. 2021 Dec 01;13:711524. (PMID: 34924992)
Neurol Ther. 2022 Jun;11(2):553-569. (PMID: 35286590)
J Mol Neurosci. 2013 Sep;51(1):138-47. (PMID: 23345083)
JAMA. 2023 Aug 8;330(6):512-527. (PMID: 37459141)
J Alzheimers Dis. 2021;82(3):921-937. (PMID: 34120907)
Brain Imaging Behav. 2012 Dec;6(4):517-27. (PMID: 22644789)
Front Cell Neurosci. 2021 Jun 22;15:652111. (PMID: 34239415)
Genes (Basel). 2020 Jun 26;11(6):. (PMID: 32604772)
Biology (Basel). 2020 Aug 28;9(9):. (PMID: 32872134)
Proc Natl Acad Sci U S A. 2005 Oct 25;102(43):15545-50. (PMID: 16199517)
Neurobiol Aging. 2019 Dec;84:98-108. (PMID: 31522136)
Nat Med. 2020 Mar;26(3):379-386. (PMID: 32123385)
Front Immunol. 2022 Sep 09;13:986346. (PMID: 36159817)
Cell Syst. 2021 Sep 22;12(9):873-884.e4. (PMID: 34171228)
Alzheimers Dement. 2015 Jul;11(7):792-814. (PMID: 26194313)
Neurology. 1984 Jul;34(7):939-44. (PMID: 6610841)
J Alzheimers Dis. 2019;72(1):1-14. (PMID: 31561377)
Front Neurosci. 2020 Apr 09;14:233. (PMID: 32327964)
J Alzheimers Dis. 2016 Oct 18;54(4):1671-1686. (PMID: 27636840)
Genome Biol. 2005;6(2):R16. (PMID: 15693945)
Ageing Res Rev. 2023 Sep;90:102022. (PMID: 37490963)
Mol Neurobiol. 2019 Jan;56(1):406-434. (PMID: 29705945)
Front Psychiatry. 2022 Sep 23;13:960648. (PMID: 36213927)
Am J Public Health. 1998 Sep;88(9):1337-42. (PMID: 9736873)
J Biomed Sci. 2023 Oct 2;30(1):83. (PMID: 37784171)
Alzheimers Dement. 2020 Sep;16(9):1213-1223. (PMID: 32755048)

A0121-23-2335 National IT industry Promotion Agency; RS-2024-00348897 National Research Foundation of Korea

Keywords: Alzheimer’s disease (AD); MCI-to-AD conversion; RNA sequencing; biomarkers; gene expression; machine learning; mild cognitive impairment (MCI); transcriptomics

0 (Biomarkers)

Date Created: 20241127 Date Completed: 20241127 Latest Revision: 20250402

20250407

PMC11593234

10.3390/cells13221920

39594668