Robust Discovery of Mild Cognitive Impairment Subtypes and Their Risk of Alzheimer's Disease Conversion Using Unsupervised Machine Learning and Gaussian Mixture Modeling

doi:10.2174/1567205018666210831145825

摘要

背景：阿尔茨海默病 (AD) 是一种不可逆的、进行性的脑部疾病，会缓慢破坏记忆力和思维能力。在早期阶段正确预测阿尔茨海默病诊断的能力可以帮助医生对治疗计划做出更明智的临床决策。目标：本研究旨在确定无监督发现轻度认知障碍 (MCI) 受试者的潜在类别是否有助于发现不同的前驱 AD 阶段和/或具有低 MCI 到 AD 转换风险的受试者。方法：总共 18 个与 MCI 到 AD 转换过程相关的特征导致 681 名早期 MCI 受试者的识别。受试者被分为训练 (70%) 和验证 (30%) 组。使用共识聚类分析训练集中的受试者，并使用高斯混合模型 (GMM) 来描述潜在类别。发现的 GMM 预测了验证集的潜在类别。最后，为每个发现的类别计算描述性统计数据、转换率和优势比 (OR)。结果：通过共识聚类，我们在 MCI 科目中发现了三个不同的聚类。这三个集群与低风险（OR = 0.12, 95%CI = 0.04 to 0.3|）、中风险（OR = 1.33, 95%CI = 0.75 to 2.37）和高风险（OR = 3.02,从 MCI 转换为 AD 的 95%CI = 1.64 到 5.57），高风险和低风险组高度对比。因此，前驱 AD 受试者仅出现在两个集群中。结论：我们通过共识聚类成功地发现了 MCI 受试者中具有不同 MCI 到 AD 转换风险的三个不同的潜在类别。发现的两个类别可能代表阿尔茨海默病的两种不同的前驱表现。

关键词: 阿尔茨海默病、轻度认知障碍、潜在类别分析、共识聚类、高斯混合模型、颅内容积。

« Previous

[1] 
Association As. 2018 Alzheimer’s disease facts and figures. Alzheimers Dement  2018; 14(3): 367-429.
[http://dx.doi.org/10.1016/j.jalz.2018.02.001] 
[2] 
Patterson C. World Alzheimer report 2018: The state of the art of dementia research: New frontiers. London, UK: Alzheimer’s Disease International (ADI) 2018.
[3] 
Alexiou A, Mantzavinos VD, Greig NH, Kamal MA. A Bayesian model for the prediction and early diagnosis of Alzheimer’s disease. Front Aging Neurosci  2017; 9: 77.
[http://dx.doi.org/10.3389/fnagi.2017.00077] [PMID: 28408880] 
[4] 
Bronner K, Perneczky R, McCabe R, Kurz A, Hamann J. Which medical and social decision topics are important after early diagnosis of Alzheimer’s Disease from the perspectives of people with Alzheimer’s Disease, spouses and professionals? BMC Res Notes  2016; 9(1): 149.
[http://dx.doi.org/10.1186/s13104-016-1960-3] [PMID: 26956520] 
[5] 
Frozza RL, Lourenco MV, De Felice FG. Challenges for Alzheimer’s disease therapy: Insights from novel mechanisms beyond memory defects. Front Neurosci  2018; 12: 37.
[http://dx.doi.org/10.3389/fnins.2018.00037] [PMID: 29467605] 
[6] 
Lanctôt KL, Rajaram RD, Herrmann N. Therapy for Alzheimer’s disease: How effective are current treatments? Ther Adv Neurol Disord  2009; 2(3): 163-80.
[http://dx.doi.org/10.1177/1756285609102724] [PMID: 21179526] 
[7] 
Sperling RA, Aisen PS, Beckett LA, et al. Toward defining the preclinical stages of Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease. Alzheimers Dement  2011; 7(3): 280-92.
[http://dx.doi.org/10.1016/j.jalz.2011.03.003] [PMID: 21514248] 
[8] 
Rozzini L. Conversion of amnestic mild cognitive impairment to dementia of Alzheimer type is independent to memory deterioration. Intern J Geriatric Psychiatry  2007; 22(12): 1217-22.
[http://dx.doi.org/10.1002/gps.1816] 
[9] 
Ward A, Tardiff S, Dye C, Arrighi HM. Rate of conversion from prodromal Alzheimer’s disease to Alzheimer’s dementia: A systematic review of the literature. Dement Geriatr Cogn Disord Extra  2013; 3(1): 320-32.
[http://dx.doi.org/10.1159/000354370] [PMID: 24174927] 
[10] 
Knopman DS, Petersen RC. Mild cognitive impairment and mild dementia: A clinical perspective.Mayo Clin Proc. 2014; 89(10): 1452-9.. 
[http://dx.doi.org/10.1016/j.mayocp.2014.06.019] 
[11] 
Atluri G, Padmanabhan K, Fang G, et al. Complex biomarker discovery in neuroimaging data: Finding a needle in a haystack. Neuroimage Clin  2013; 3: 123-31.
[http://dx.doi.org/10.1016/j.nicl.2013.07.004] [PMID: 24179856] 
[12] 
Bai F, Yuan Y, Shi Y, Zhang Z. Multiple genetic imaging study of the association between cholesterol metabolism and brain functional alterations in individuals with risk factors for Alzheimer’s disease. Oncotarget  2016; 7(13): 15315-28.
[http://dx.doi.org/10.18632/oncotarget.8100] [PMID: 26985771] 
[13] 
Khoury R, Ghossoub E. Diagnostic Biomarkers of Alzheimer’s Disease: A State-of-the-Art Review.  Biomarkers in Neuropsychiatry 2019; p. 100005.
[14] 
Alashwal H, El Halaby M, Crouse JJ, Abdalla A, Moustafa AA. The Application of Unsupervised Clustering Methods to Alzheimer’s Disease. Front Comput Neurosci  2019; 13: 31.
[http://dx.doi.org/10.3389/fncom.2019.00031] [PMID: 31178711] 
[15] 
Clark CM, Schneider JA, Bedell BJ, et al. Use of florbetapir-PET for imaging β-amyloid pathology. JAMA  2011; 305(3): 275-83.
[http://dx.doi.org/10.1001/jama.2010.2008] [PMID: 21245183] 
[16] 
Weiner M, Khachaturian Z. The use of MRI and PET for clinical diagnosis of dementia and investigation of cognitive impairment: A consensus report. Alzheimer’s Assoc Chicago, IL  2005; 1: 1-15.
[17] 
Prince MJ, Wu F, Guo Y, et al. The burden of disease in older people and implications for health policy and practice. Lancet  2015; 385(9967): 549-62.
[http://dx.doi.org/10.1016/S0140-6736(14)61347-7] [PMID: 25468153] 
[18] 
Ezzati A. Detecting biological heterogeneity patterns in ADNI amnestic mild cognitive impairment based on volumetric MRI. Brain Imaging Behav 2020; 14(5): 1792-1804. 
[PMID: 31104279] 
[19] 
Bernell S, Howard SW. Use your words carefully: What is a chronic disease? Front Public Health  2016; 4: 159.
[http://dx.doi.org/10.3389/fpubh.2016.00159] [PMID: 27532034] 
[20] 
Avanzo M, Stancanello J, El Naqa I. Beyond imaging: The promise of radiomics. Phys Med  2017; 38: 122-39.
[http://dx.doi.org/10.1016/j.ejmp.2017.05.071] [PMID: 28595812] 
[21] 
Moscoso A, Silva-Rodríguez J, Aldrey JM, et al. Staging the cognitive continuum in prodromal Alzheimer’s disease with episodic memory. Neurobiol Aging  2019; 84: 1-8.
[http://dx.doi.org/10.1016/j.neurobiolaging.2019.07.014] [PMID: 31479859] 
[22] 
Martorelli M, Sudo FK, Charchat-Fichman H. This is not only about memory: A systematic review on neuropsychological heterogeneity in Alzheimer’s disease. Psychol Neurosci 2018; 12(2), 271-81.. 
[23] 
Gamberger D, Lavrač N, Srivatsa S, Tanzi RE, Doraiswamy PM. Identification of clusters of rapid and slow decliners among subjects at risk for Alzheimer’s disease. Sci Rep  2017; 7(1): 6763.
[http://dx.doi.org/10.1038/s41598-017-06624-y] [PMID: 28755001] 
[24] 
Fraley C, Raftery AE. MCLUST version 3: An R package for normal mixture modeling and model-based clustering. Statistics 2006.
[http://dx.doi.org/10.21236/ADA456562] 
[25] 
García-Escudero LA. A review of robust clustering methods. Adv Data Anal Classif  2010; 4(2-3): 89-109.
[http://dx.doi.org/10.1007/s11634-010-0064-5] 
[26] 
Gallegos MT, Ritter G. A robust method for cluster analysis. Ann Stat  2005; 33(1): 347-80.
[http://dx.doi.org/10.1214/009053604000000940] 
[27] 
Șenbabaoğlu Y, Michailidis G, Li JZ. Critical limitations of consensus clustering in class discovery. Sci Rep  2014; 4(1): 6207.
[http://dx.doi.org/10.1038/srep06207] [PMID: 25158761] 
[28] 
Reynolds DA. Gaussian Mixture Models.Encyclopedia of biometrics.   2009; 741.
[http://dx.doi.org/10.1007/978-0-387-73003-5_196] 
[29] 
Marinescu RV. TADPOLE Challenge: Accurate Alzheimer’s disease prediction through crowdsourced forecasting of future data. Predict Intell.  Med 2019; 11843: 1-10. 
[http://dx.doi.org/10.1007/978-3-030-32281-6_1] 
[30] 
Marinescu RV. Tadpole challenge: Prediction of longitudinal evolution in Alzheimer's disease. arXiv preprint   2018; arXiv:1805.03909
[31] 
Edmonds EC, McDonald CR, Marshall A, et al. Early versus late MCI: Improved MCI staging using a neuropsychological approach. Alzheimers Dement  2019; 15(5): 699-708.
[http://dx.doi.org/10.1016/j.jalz.2018.12.009] [PMID: 30737119] 
[32] 
Aisen PS, Petersen RC, Donohue MC, et al. Clinical Core of the Alzheimer’s Disease Neuroimaging Initiative: Progress and plans. Alzheimers Dement  2010; 6(3): 239-46.
[http://dx.doi.org/10.1016/j.jalz.2010.03.006] [PMID: 20451872] 
[33] 
Aisen PS. Exploring survival models associated with MCI to AD conversion: A machine learning approach. bioRxiv  2019; 836510.
[34] 
Isella V, Villa L, Russo A, Regazzoni R, Ferrarese C, Appollonio IM. Discriminative and predictive power of an informant report in mild cognitive impairment. J Neurol Neurosurg Psychiatry  2006; 77(2): 166-71.
[http://dx.doi.org/10.1136/jnnp.2005.069765] [PMID: 16421116] 
[35] 
Welsh M, Begg S. The Cognitive Reflection Test: Familiarity and predictive power in professionals. In: CogSci.  2017.
[36] 
Saunders AM, Strittmatter WJ, Schmechel D, et al. Association of apolipoprotein E allele epsilon 4 with late-onset familial and sporadic Alzheimer’s disease. Neurology  1993; 43(8): 1467-72.
[http://dx.doi.org/10.1212/WNL.43.8.1467] [PMID: 8350998] 
[37] 
Blacker D, Haines JL, Rodes L, et al. ApoE-4 and age at onset of Alzheimer’s disease: The NIMH genetics initiative. Neurology  1997; 48(1): 139-47.
[http://dx.doi.org/10.1212/WNL.48.1.139] [PMID: 9008509] 
[38] 
Devanand DP, Bansal R, Liu J, Hao X, Pradhaban G, Peterson BS. MRI hippocampal and entorhinal cortex mapping in predicting conversion to Alzheimer’s disease. Neuroimage  2012; 60(3): 1622-9.
[http://dx.doi.org/10.1016/j.neuroimage.2012.01.075] [PMID: 22289801] 
[39] 
Apostolova LG, Thompson PM. Mapping progressive brain structural changes in early Alzheimer’s disease and mild cognitive impairment. Neuropsychologia  2008; 46(6): 1597-612.
[http://dx.doi.org/10.1016/j.neuropsychologia.2007.10.026] [PMID: 18395760] 
[40] 
Sullivan Gail M, Feinn Richard. Using effect size—or why the P value is not enough. J Graduate medical education 43  2012; 279-82.
[41] 
Song C, Ristenpart T, Shmatikov V. Machine learning models that remember too much. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. 
[http://dx.doi.org/10.1145/3133956.3134077] 
[42] 
Scrucca L, Fop M, Murphy TB, Raftery AE. mclust 5: Clustering, classification and density estimation using Gaussian finite mixture models. R J  2016; 8(1): 289-317.
[http://dx.doi.org/10.32614/RJ-2016-021] [PMID: 27818791] 
[43] 
Maćkiewicz A, Ratajczak W. Principal components analysis (PCA). Comput Geosci  1993; 19(3): 303-42.
[http://dx.doi.org/10.1016/0098-3004(93)90090-R] 
[44] 
Bernatavičienė J. , Dzemyda G, Kurasova O, Marcinkevičius V, Medvedev V, Treigys P. Cloud Computing approach for intelligent visualization of multidimensional data.  In: Pardalos PM, Zhigljavsky A, Žilinskas J, EdsAdvances in stochastic and deterministic global optimization.  Springer 2016; pp. 73-85.
[http://dx.doi.org/10.1007/978-3-319-29975-4_5] 
[45] 
Jolliffe I. Principal component analysis. Technometrics  2003; 45(3): 276.
[http://dx.doi.org/10.1198/tech.2003.s783] 
[46] 
Topchy A, Jain AK, Punch W. Clustering ensembles: Models of consensus and weak partitions. IEEE Trans Pattern Anal Mach Intell  2005; 27(12): 1866-81.
[http://dx.doi.org/10.1109/TPAMI.2005.237] [PMID: 16355656] 
[47] 
Fred ALN, Jain AK. Combining multiple clusterings using evidence accumulation. IEEE Trans Pattern Anal Mach Intell  2005; 27(6): 835-50.
[http://dx.doi.org/10.1109/TPAMI.2005.113] [PMID: 15943417] 
[48] 
Li F. Clustering ensemble based on sample’s stability. Artif Intell  2019; 273: 37-55.
[http://dx.doi.org/10.1016/j.artint.2018.12.007] 
[49] 
Peter J, Abdulkadir A, Kaller C, et al. Subgroups of Alzheimer’s disease: Stability of empirical clusters over time. J Alzheimers Dis  2014; 42(2): 651-61.
[http://dx.doi.org/10.3233/JAD-140261] [PMID: 24927700] 
[50] 
Fraley C. , Raftery A. E., Murphy T. B. and Scrucca L. (2012) mclust Version 4 for R: Normal Mixture Modeling for Model-Based Clustering, Classification, and Density Estimation. Technical Report No. 597, Department of Statistics, University of Washington.. 
[51] 
Szumilas M. Explaining odds ratios. J Can Acad Child Adolesc Psychiatry  2010; 19(3): 227-9.
[PMID: 20842279] 
[52] 
Kassambara A. Package ‘survminer’. Drawing Survival Curves using ‘ggplot2’ 2017.
[53] 
Mantel N. Evaluation of survival data and two new rank order statistics arising in its consideration. Cancer Chemother Rep  1966; 50(3): 163-70.
[PMID: 5910392] 
[54] 
Ferreira JA. The Benjamini-Hochberg method in the case of discrete test statistics. Int J Biostat  2007; 3(1): 11.
[http://dx.doi.org/10.2202/1557-4679.1065] [PMID: 22550651] 
[55] 
Edmonds EC, Weigand AJ, Hatton SN, et al. Patterns of longitudinal cortical atrophy over 3 years in empirically derived MCI subtypes. Neurology  2020; 94(24): e2532-44.
[http://dx.doi.org/10.1212/WNL.0000000000009462] [PMID: 32393648] 
[56] 
Weiner MW, Veitch DP, Aisen PS, et al. Impact of the Alzheimer’s disease neuroimaging initiative, 2004 to 2014. Alzheimers Dement  2015; 11(7): 865-84.
[http://dx.doi.org/10.1016/j.jalz.2015.04.005] [PMID: 26194320] 

Rights & Permissions Print Cite

Article Metrics

11

1

Journal Information

For Authors

For Editors

For Reviewers

Explore Articles

Open Access

Open Access Articles

For Visitors

DOI https://dx.doi.org/10.2174/1567205018666210831145825	Print ISSN 1567-2050
Publisher Name Bentham Science Publisher	Online ISSN 1875-5828

当代阿耳茨海默病研究

使用无监督机器学习和高斯混合建模稳健发现轻度认知障碍亚型及其阿尔茨海默病转化风险

摘要

当代阿耳茨海默病研究

使用无监督机器学习和高斯混合建模稳健发现轻度认知障碍亚型及其阿尔茨海默病转化风险

摘要 Play Pause

Related Journals

Related Books

摘要