Improved perfusion pattern score association with type 2 diabetes severity using machine learning pipeline: Pilot study.
Aged
Aged, 80 and over
Brain
/ diagnostic imaging
Brain Mapping
Cognition Disorders
/ complications
Cross-Sectional Studies
Diabetes Mellitus, Type 2
/ complications
Female
Humans
Imaging, Three-Dimensional
Insulin Resistance
Linear Models
Longitudinal Studies
Machine Learning
Magnetic Resonance Imaging
Male
Middle Aged
Perfusion
Pilot Projects
Prospective Studies
Severity of Illness Index
machine learning
perfusion diabetes pattern score
type 2 diabetes mellitus
Journal
Journal of magnetic resonance imaging : JMRI
ISSN: 1522-2586
Titre abrégé: J Magn Reson Imaging
Pays: United States
ID NLM: 9105850
Informations de publication
Date de publication:
03 2019
03 2019
Historique:
received:
01
01
2018
accepted:
26
06
2018
pubmed:
7
8
2018
medline:
29
7
2020
entrez:
7
8
2018
Statut:
ppublish
Résumé
Type 2 diabetes mellitus (T2DM) is associated with alterations in the blood-brain barrier, neuronal damage, and arterial stiffness, thus affecting cerebral metabolism and perfusion. There is a need to implement machine-learning methodologies to identify a T2DM-related perfusion pattern and possible relationship between the pattern and cognitive performance/disease severity. To develop a machine-learning pipeline to investigate the method's discriminative value between T2DM patients and normal controls, the T2DM-related network pattern, and association of the pattern with cognitive performance/disease severity. A cross-sectional study and prospective longitudinal study with a 2-year time interval. Seventy-three subjects (41 T2DM patients and 32 controls) aged 50-85 years old at baseline, and 42 subjects (19 T2DM and 23 controls) aged 53-88 years old at 2-year follow-up. 3T pseudocontinuous arterial spin-labeling MRI. Machine-learning-based pipeline (principal component analysis, feature selection, and logistic regression classifier) to generate the T2DM-related network pattern and the individual scores associated with the pattern. Linear regression analysis with gray matter volume and education years as covariates. The machine-learning-based method is superior to the widely used univariate group comparison method with increased test accuracy, test area under the curve, test positive predictive value, adjusted McFadden's R square of 4%, 12%, 7%, and 24%, respectively. The pattern-related individual scores are associated with diabetes severity variables, mobility, and cognitive performance at baseline (P < 0.05, |r| > 0.3). More important, the longitudinal change of individual pattern scores is associated with the longitudinal change of HbA1c (P = 0.0053, r = 0.64), and baseline cholesterol (P = 0.037, r = 0.51). The individual perfusion diabetes pattern score is a highly promising perfusion imaging biomarker for tracing the disease progression of individual T2DM patients. Further validation is needed from a larger study. 1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;49:834-844.
Sections du résumé
BACKGROUND
Type 2 diabetes mellitus (T2DM) is associated with alterations in the blood-brain barrier, neuronal damage, and arterial stiffness, thus affecting cerebral metabolism and perfusion. There is a need to implement machine-learning methodologies to identify a T2DM-related perfusion pattern and possible relationship between the pattern and cognitive performance/disease severity.
PURPOSE
To develop a machine-learning pipeline to investigate the method's discriminative value between T2DM patients and normal controls, the T2DM-related network pattern, and association of the pattern with cognitive performance/disease severity.
STUDY TYPE
A cross-sectional study and prospective longitudinal study with a 2-year time interval.
POPULATION
Seventy-three subjects (41 T2DM patients and 32 controls) aged 50-85 years old at baseline, and 42 subjects (19 T2DM and 23 controls) aged 53-88 years old at 2-year follow-up.
FIELD STRENGTH/SEQUENCE
3T pseudocontinuous arterial spin-labeling MRI.
ASSESSMENT
Machine-learning-based pipeline (principal component analysis, feature selection, and logistic regression classifier) to generate the T2DM-related network pattern and the individual scores associated with the pattern.
STATISTICAL TESTS
Linear regression analysis with gray matter volume and education years as covariates.
RESULTS
The machine-learning-based method is superior to the widely used univariate group comparison method with increased test accuracy, test area under the curve, test positive predictive value, adjusted McFadden's R square of 4%, 12%, 7%, and 24%, respectively. The pattern-related individual scores are associated with diabetes severity variables, mobility, and cognitive performance at baseline (P < 0.05, |r| > 0.3). More important, the longitudinal change of individual pattern scores is associated with the longitudinal change of HbA1c (P = 0.0053, r = 0.64), and baseline cholesterol (P = 0.037, r = 0.51).
DATA CONCLUSION
The individual perfusion diabetes pattern score is a highly promising perfusion imaging biomarker for tracing the disease progression of individual T2DM patients. Further validation is needed from a larger study.
LEVEL OF EVIDENCE
1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;49:834-844.
Identifiants
pubmed: 30079560
doi: 10.1002/jmri.26256
pmc: PMC6456911
mid: NIHMS1016850
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
834-844Subventions
Organisme : NIA NIH HHS
ID : R01 AG028076
Pays : United States
Organisme : NIDDK NIH HHS
ID : R01 DK103902
Pays : United States
Organisme : NCRR NIH HHS
ID : UL1 RR025758
Pays : United States
Organisme : NCATS NIH HHS
ID : UL1 TR001102
Pays : United States
Informations de copyright
© 2018 International Society for Magnetic Resonance in Medicine.
Références
J Ayub Med Coll Abbottabad. 2010 Oct-Dec;22(4):74-7
pubmed: 22455266
Diabetes Care. 2006 Jul;29(7):1529-34
pubmed: 16801574
Hum Brain Mapp. 2014 Sep;35(9):4916-31
pubmed: 24700485
Psychoneuroendocrinology. 2013 Nov;38(11):2493-501
pubmed: 23786881
Neurobiol Aging. 2017 Dec;60:192-202
pubmed: 28992987
J Trop Pediatr. 2015 Apr;61(2):126-30
pubmed: 25624391
Diabetes Care. 2011 Nov;34(11):2438-41
pubmed: 21926285
Magn Reson Med. 2008 Dec;60(6):1488-97
pubmed: 19025913
Proc Natl Acad Sci U S A. 2005 Jul 5;102(27):9673-8
pubmed: 15976020
Stroke. 2012 Jun;43(6):1542-7
pubmed: 22492519
Clin Interv Aging. 2014 Jun 28;9:1011-9
pubmed: 25061284
Lancet Neurol. 2008 Feb;7(2):184-90
pubmed: 18207116
Diabetes Care. 2007 May;30(5):1193-9
pubmed: 17290035
Diabetologia. 1985 Jul;28(7):412-9
pubmed: 3899825
Neuroimage. 2009 Mar;45(1 Suppl):S199-209
pubmed: 19070668
PLoS One. 2013 Nov 08;8(11):e77949
pubmed: 24250789
J Nucl Med. 2014 May;55(5):759-64
pubmed: 24652830
Clin Neuropsychol. 1999 Aug;13(3):348-58
pubmed: 10726605
Sci Rep. 2016 Dec;6(1):10
pubmed: 27920431
Nucl Med Commun. 2000 Jan;21(1):19-29
pubmed: 10717898
Diabetes. 2012 Sep;61(9):2375-9
pubmed: 22664957
Medicine (Baltimore). 2015 Dec;94(48):e2231
pubmed: 26632913
Diabetologia. 2005 Dec;48(12):2460-9
pubmed: 16283246
Brain Res. 2009 Jul 14;1280:186-94
pubmed: 19463794
Bosn J Basic Med Sci. 2014 Nov 09;14(4):185-90
pubmed: 25428668
Nucl Med Commun. 1994 Jun;15(6):455-60
pubmed: 8078642
Neuroimage. 2004 Jan;21(1):46-57
pubmed: 14741641
J Neurol Neurosurg Psychiatry. 2003 Jan;74(1):70-6
pubmed: 12486269
Circ J. 2011;75(5):1042-8
pubmed: 21441696
J Cereb Blood Flow Metab. 2015 Jan;35(1):95-102
pubmed: 25315860
Neuroimage. 2005 Jul 1;26(3):839-51
pubmed: 15955494
Clin Interv Aging. 2017 May 02;12:745-752
pubmed: 28496312
J Diabetes Complications. 2012 May-Jun;26(3):205-9
pubmed: 22520398
Diabetologia. 2008 Jul;51(7):1321-6
pubmed: 18488188
Magn Reson Med. 1998 Sep;40(3):383-96
pubmed: 9727941
Sci Rep. 2015 Jun 08;5:11148
pubmed: 26053355
Arch Neurol. 2011 Jan;68(1):51-7
pubmed: 20837822