Machine-learning based exploration of determinants of gray matter volume in the KORA-MRI study.
Cardiovascular Diseases
/ epidemiology
Case-Control Studies
Confounding Factors, Epidemiologic
Cross-Sectional Studies
Diabetes Mellitus, Type 2
/ epidemiology
Female
Follow-Up Studies
Germany
/ epidemiology
Glomerular Filtration Rate
/ physiology
Gray Matter
/ diagnostic imaging
Humans
Life Style
Linear Models
Machine Learning
Magnetic Resonance Imaging
Male
Middle Aged
Models, Neurological
Organ Size
/ physiology
Prediabetic State
/ epidemiology
Prospective Studies
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
20 05 2020
20 05 2020
Historique:
received:
01
09
2019
accepted:
16
04
2020
entrez:
21
5
2020
pubmed:
21
5
2020
medline:
15
12
2020
Statut:
epublish
Résumé
To identify the most important factors that impact brain volume, while accounting for potential collinearity, we used a data-driven machine-learning approach. Gray Matter Volume (GMV) was derived from magnetic resonance imaging (3T, FLAIR) and adjusted for intracranial volume (ICV). 93 potential determinants of GMV from the categories sociodemographics, anthropometric measurements, cardio-metabolic variables, lifestyle factors, medication, sleep, and nutrition were obtained from 293 participants from a population-based cohort from Southern Germany. Elastic net regression was used to identify the most important determinants of ICV-adjusted GMV. The four variables age (selected in each of the 1000 splits), glomerular filtration rate (794 splits), diabetes (323 splits) and diabetes duration (122 splits) were identified to be most relevant predictors of GMV adjusted for intracranial volume. The elastic net model showed better performance compared to a constant linear regression (mean squared error = 1.10 vs. 1.59, p < 0.001). These findings are relevant for preventive and therapeutic considerations and for neuroimaging studies, as they suggest to take information on metabolic status and renal function into account as potential confounders.
Identifiants
pubmed: 32433583
doi: 10.1038/s41598-020-65040-x
pii: 10.1038/s41598-020-65040-x
pmc: PMC7239887
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
8363Références
Walhovd, K. B. et al. Effects of age on volumes of cortex, white matter and subcortical structures. Neurobiology of aging 26, 1261–1270, https://doi.org/10.1016/j.neurobiolaging.2005.05.020 (2005).
doi: 10.1016/j.neurobiolaging.2005.05.020
pubmed: 16005549
Giorgio, A. et al. Age-related changes in grey and white matter structure throughout adulthood. NeuroImage 51, 943–951, https://doi.org/10.1016/j.neuroimage.2010.03.004 (2010).
doi: 10.1016/j.neuroimage.2010.03.004
pubmed: 20211265
pmcid: 2896477
Taki, Y. et al. Correlations among brain gray matter volumes, age, gender, and hemisphere in healthy individuals. PloS one 6, e22734, https://doi.org/10.1371/journal.pone.0022734 (2011).
doi: 10.1371/journal.pone.0022734
pubmed: 21818377
pmcid: 3144937
Bartzokis, G. et al. Age-related brain volume reductions in amphetamine and cocaine addicts and normal controls: implications for addiction research. Psychiatry Research: Neuroimaging 98, 93–102, https://doi.org/10.1016/S0925-4927(99)00052-9 (2000).
doi: 10.1016/S0925-4927(99)00052-9
pubmed: 10762735
Paul, C. A. et al. Association of Alcohol Consumption with Brain Volume in the Framingham Study. Archives of neurology 65, 1363–1367, https://doi.org/10.1001/archneur.65.10.1363 (2008).
doi: 10.1001/archneur.65.10.1363
pubmed: 18852353
pmcid: 2861346
Markus, M. R. P. et al. Prediabetes is associated with lower brain gray matter volume in the general population. The Study of Health in Pomerania (SHIP). Nutrition, Metabolism and Cardiovascular Diseases 27, 1114–1122, https://doi.org/10.1016/j.numecd.2017.10.007 (2017).
doi: 10.1016/j.numecd.2017.10.007
pubmed: 29162362
Gianaros, P. J., Greer, P. J., Ryan, C. M. & Jennings, J. R. Higher blood pressure predicts lower regional grey matter volume: Consequences on short-term information processing. NeuroImage 31, 754–765, https://doi.org/10.1016/j.neuroimage.2006.01.003 (2006).
doi: 10.1016/j.neuroimage.2006.01.003
pubmed: 16488626
pmcid: 2254305
Brooks, S. J. et al. Late-life obesity is associated with smaller global and regional gray matter volumes: a voxel-based morphometric study. International journal of obesity (2005) 37, 230–236, https://doi.org/10.1038/ijo.2012.13 (2013).
doi: 10.1038/ijo.2012.13
Arnardottir, N. Y. et al. Association of change in brain structure to objectively measured physical activity and sedentary behavior in older adults: Age, Gene/Environment Susceptibility-Reykjavik Study. Behavioural brain research 296, 118–124, https://doi.org/10.1016/j.bbr.2015.09.005 (2016).
doi: 10.1016/j.bbr.2015.09.005
pubmed: 26363425
Zou, H. & Hastie, T. Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 67, 301–320, https://doi.org/10.1111/j.1467-9868.2005.00503.x (2005).
doi: 10.1111/j.1467-9868.2005.00503.x
Holle, R., Happich, M., Lowel, H. & Wichmann, H. E. KORA–a research platform for population based health research. Gesundheitswesen (Bundesverband der Arzte des Offentlichen Gesundheitsdienstes (Germany)) 67(Suppl 1), S19–25, https://doi.org/10.1055/s-2005-858235 (2005).
doi: 10.1055/s-2005-858235
Bamberg, F. et al. Subclinical Disease Burden as Assessed by Whole-Body MRI in Subjects With Prediabetes, Subjects With Diabetes, and Normal Control Subjects From the General Population: The KORA-MRI Study. Diabetes 66, 158–169, https://doi.org/10.2337/db16-0630 (2017).
doi: 10.2337/db16-0630
pubmed: 27999110
Beller, E. et al. T1-MPRAGE and T2-FLAIR segmentation of cortical and subcortical brain regions-an MRI evaluation study. Neuroradiology, https://doi.org/10.1007/s00234-018-2121-2 (2018).
Smith, S. M. Fast robust automated brain extraction. Hum Brain Mapp 17, 143–155, https://doi.org/10.1002/hbm.10062 (2002).
doi: 10.1002/hbm.10062
pubmed: 12391568
Tzourio-Mazoyer, N. et al. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. NeuroImage 15, 273–289, https://doi.org/10.1006/nimg.2001.0978 (2002).
doi: 10.1006/nimg.2001.0978
pubmed: 11771995
Jenkinson, M., Bannister, P., Brady, M. & Smith, S. Improved optimization for the robust and accurate linear registration and motion correction of brain images. Neuroimage 17, 825–841 (2002).
doi: 10.1006/nimg.2002.1132
Zhang, C. et al. Sex and Age Effects of Functional Connectivity in Early Adulthood. Brain Connect 6, 700–713, https://doi.org/10.1089/brain.2016.0429 (2016).
doi: 10.1089/brain.2016.0429
pubmed: 27527561
pmcid: 5105352
Buckner, R. L. et al. A unified approach for morphometric and functional data analysis in young, old, and demented adults using automated atlas-based head size normalization: reliability and validation against manual measurement of total intracranial volume. NeuroImage 23, 724–738, https://doi.org/10.1016/j.neuroimage.2004.06.018 (2004).
doi: 10.1016/j.neuroimage.2004.06.018
pubmed: 15488422
Hansen, T. I., Brezova, V., Eikenes, L., Haberg, A. & Vangberg, T. R. How Does the Accuracy of Intracranial Volume Measurements Affect Normalized Brain Volumes? Sample Size Estimates Based on 966 Subjects from the HUNT MRI Cohort. AJNR Am J Neuroradiol 36, 1450–1456, https://doi.org/10.3174/ajnr.A4299 (2015).
doi: 10.3174/ajnr.A4299
pubmed: 25857759
Dwyer, D. B., Falkai, P. & Koutsouleris, N. Machine learning approaches for clinical psychology and psychiatry. Annual review of clinical psychology 14, 91–118 (2018).
doi: 10.1146/annurev-clinpsy-032816-045037
Fan, J. & Li, R. Variable selection via nonconcave penalized likelihood and its oracle properties. Journal of the American statistical Association 96, 1348–1360 (2001).
doi: 10.1198/016214501753382273
van Buuren, S. & Groothuis-Oudshoorn, K. mice: Multivariate Imputation by Chained Equations in R. Journal of Statistical Software 45, 1–67, https://doi.org/10.18637/jss.v045.i03 (2011).
doi: 10.18637/jss.v045.i03
Friedman, J., Hastie, T. & Tibshirani, R. Regularization paths for generalized linear models via coordinate descent. Journal of statistical software 33, 1 (2010).
doi: 10.18637/jss.v033.i01
Rudberg, S., Persson, B. & Dahlquist, G. Increased glomerular filtration rate as a predictor of diabetic nephropathy - An 8-year prospective study. Kidney International 41, 822–828, https://doi.org/10.1038/ki.1992.126 (1992).
doi: 10.1038/ki.1992.126
pubmed: 1513104
Kurella, M., Chertow, G. M., Luan, J. & Yaffe, K. Cognitive Impairment in Chronic Kidney Disease. Journal of the American Geriatrics Society 52, 1863–1869, https://doi.org/10.1111/j.1532-5415.2004.52508.x (2004).
doi: 10.1111/j.1532-5415.2004.52508.x
pubmed: 15507063
Martinez-Vea, A. et al. Silent cerebral white matter lesions and their relationship with vascular risk factors in middle-aged predialysis patients with CKD. American journal of kidney diseases: the official journal of the National Kidney Foundation 47, 241–250, https://doi.org/10.1053/j.ajkd.2005.10.029 (2006).
doi: 10.1053/j.ajkd.2005.10.029
Takahashi, W., Tsukamoto, Y., Takizawa, S., Kawada, S. & Takagi, S. Relationship Between Chronic Kidney Disease and White Matter Hyperintensities on Magnetic Resonance Imaging. Journal of Stroke and Cerebrovascular Diseases 21, 18–23, https://doi.org/10.1016/j.jstrokecerebrovasdis.2010.03.015 (2012).
doi: 10.1016/j.jstrokecerebrovasdis.2010.03.015
pubmed: 20833078
Khatri, M. et al. Chronic kidney disease is associated with white matter hyperintensity volume: the Northern Manhattan Study (NOMAS). Stroke 38, 3121–3126 (2007).
doi: 10.1161/STROKEAHA.107.493593
Zhang, L. J. et al. Predominant gray matter volume loss in patients with end-stage renal disease: a voxel-based morphometry study. Metabolic brain disease 28, 647–654 (2013).
doi: 10.1007/s11011-013-9438-7
Wu, G., Lin, L., Zhang, Q. & Wu, J. Brain gray matter changes in type 2 diabetes mellitus: A meta-analysis of whole-brain voxel-based morphometry study. Journal of diabetes and its complications 31, 1698–1703, https://doi.org/10.1016/j.jdiacomp.2017.09.001 (2017).
doi: 10.1016/j.jdiacomp.2017.09.001
pubmed: 29033311
Brownlee, M., Vlassara, H. & Cerami, A. Nonenzymatic glycosylation and the pathogenesis of diabetic complications. Annals of internal medicine 101, 527–537 (1984).
doi: 10.7326/0003-4819-101-4-527
Barrett, E. J. et al. Diabetic Microvascular Disease: An Endocrine Society Scientific Statement. The. Journal of clinical endocrinology and metabolism 102, 4343–4410, https://doi.org/10.1210/jc.2017-01922 (2017).
doi: 10.1210/jc.2017-01922
pubmed: 29126250
Kleinridders, A., Ferris, H. A., Cai, W. & Kahn, C. R. Insulin Action in Brain Regulates Systemic Metabolism and Brain Function. Diabetes 63, 2232, https://doi.org/10.2337/db14-0568 (2014).
doi: 10.2337/db14-0568
pubmed: 24931034
pmcid: 4066341
Moran, C. et al. Brain Atrophy in Type 2 Diabetes: Regional distribution and influence on cognition. Diabetes Care 36, 4036–4042, https://doi.org/10.2337/dc13-0143 (2013).
doi: 10.2337/dc13-0143
pubmed: 23939539
pmcid: 3836136
Kharabian Masouleh, S. et al. Gray matter structural networks are associated with cardiovascular risk factors in healthy older adults. Journal of cerebral blood flow and metabolism: official journal of the International Society of Cerebral Blood Flow and Metabolism, 271678x17729111, https://doi.org/10.1177/0271678x17729111 (2017).
Meusel, L. A. et al. A systematic review of type 2 diabetes mellitus and hypertension in imaging studies of cognitive aging: time to establish new norms. Frontiers in Aging Neuroscience 6, 148, https://doi.org/10.3389/fnagi.2014.00148 (2014).
doi: 10.3389/fnagi.2014.00148
pubmed: 25071557
pmcid: 4085499
Baron, J. C. et al. In Vivo Mapping of Gray Matter Loss with Voxel-Based Morphometry in Mild Alzheimer’s Disease. NeuroImage 14, 298–309, https://doi.org/10.1006/nimg.2001.0848 (2001).
doi: 10.1006/nimg.2001.0848
pubmed: 11467904
Schuster, C. et al. Gray Matter Volume Decreases in Elderly Patients with Schizophrenia: A Voxel-based Morphometry Study. Schizophrenia Bulletin 38, 796–802, https://doi.org/10.1093/schbul/sbq150 (2012).
doi: 10.1093/schbul/sbq150
pubmed: 21205677
Lorbeer, R. et al. Lack of association of MRI determined subclinical cardiovascular disease with dizziness and vertigo in a cross-sectional population-based study. PloS one 12, e0184858, https://doi.org/10.1371/journal.pone.0184858 (2017).
doi: 10.1371/journal.pone.0184858
pubmed: 28910373
pmcid: 5599022
Vandenbroucke, J. P., Broadbent, A. & Pearce, N. Causality and causal inference in epidemiology: the need for a pluralistic approach. International Journal of Epidemiology 45, 1776–1786, https://doi.org/10.1093/ije/dyv341 (2016).
doi: 10.1093/ije/dyv341
pubmed: 26800751
pmcid: 5841832
Lawlor, D. A., Tilling, K. & Davey Smith, G. Triangulation in aetiological epidemiology. International Journal of Epidemiology 45, 1866–1886, https://doi.org/10.1093/ije/dyw314 (2017).
doi: 10.1093/ije/dyw314
pmcid: 5841843
Sudlow, C. et al. UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PLoS medicine 12, e1001779 (2015).
doi: 10.1371/journal.pmed.1001779