CoChat
Sign Up
Cited by 55Dementia and Cognitive Impairment ResearchArtificial Intelligence in HealthcareNeurological Disease Mechanisms and Treatments

Machine learning-based framework for differential diagnosis between vascular dementia and Alzheimer’s disease using structural MRI features

Open access
Zheng, Yineng, Guo, Haoming, Zhang, Lijuan, Wu, Jiahui, Li, Qi, Lv, Fajin·2019·Frontiers in Neurology
DOI 10.3389/fneur.2019.01097PMC PMC6823227
Open this paper in CoChat — free accountOpen PDF

Abstract

Background and objective: Vascular dementia (VaD) and Alzheimer's disease (AD) could be characterized by the same syndrome of dementia. This study aims to assess whether multi-parameter features derived from structural MRI can serve as the informative biomarker for differential diagnosis of VaD and AD using machine learning. Methods: A total of 93 patients imaged with brain MRI including 58 AD and 35 VaD confirmed by two chief physicians were recruited in this study from June 2013 to July 2019. Automated brain tissue segmentation was performed by AccuBrain tool to extract multi-parameter volumetric measurements from different brain regions. Firstly, totally 62 structural MRI biomarkers were addressed to select significantly different features between VaD and AD for dimensionality reduction. Then, least absolute shrinkage and selection operator (LASSO) was further used to construct a feature set that is fed into a support vector machine (SVM) classifier. To ensure the unbiased evaluation of model performance, a comparative study of classification models was implemented by using different machine learning algorithms in order to determine which performs best in the application of differential diagnosis between VaD and AD. The diagnostic performance of the classification models was evaluated by the quantitative metrics derived from receiver operating characteristic curve (ROC). Results: The experimental results demonstrate that SVM with RBF model achieved an encouraging performance with sensitivity (SEN), specificity (SPE) and accuracy (ACC) values of 82.65%, 87.17% and 84.35% (AUC=0.861, 95% CI = 0.820-0.902) for the differential diagnosis between VaD and AD. The experimental results demonstrate that the proposed model achieved an encouraging performance. Conclusions: The proposed computer-aided diagnosis method highlights the potential of combing structural MRI and machine learning to support clinical decision making in distinction of VaD vs. AD.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3389/fneur.2019.01097

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • A radial basis function (RBF)-SVM model using multiparametric structural MRI features achieved sensitivity 82.65%, specificity 87.17%, and accuracy 84.35% for AD/VaD discrimination.

    “a radial basis function (RBF)-SVM model leveraging multiparametric structural MRI features achieved satisfactory AD/VaD discrimination (sensitivity: 82.65%, specificity: 87.17%, accuracy: 84.35%)”

    From Multimodal neuroimaging and AI integration in cognitive disorders: advances, challenges, and future directions for precision medicine (2026) · cites this paper as Zheng et al., 2019

    The Results (Performance Comparison; page not available) report 84.35% test-set accuracy for SVM and say the RBF kernel generally performed better than the linear kernel. The paper uses structural MRI features for AD/VaD discrimination, but our copy does not report the claimed 82.65% sensitivity or 87.17% specificity; Table 5 gives different recall values for a single experiment. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • A few studies have attempted to discern neuroimaging signatures unique to AD by contrasting them with other dementia types.

    “A few studies have attempted to discern neuroimaging signatures unique to AD by contrasting them with other dementia types31–40.”

    From AI-based differential diagnosis of dementia etiologies on multimodal data (2024) · cites this paper as [32]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 36 · Cited by 55

Research works printed but not linked: 33

  1. [1]Wu YT Fratiglioni L Matthews FE Lobo A Breteler MMB Skoog I. Dementia in western Europe: epidemiological evidence and implications for policy making. Lancet Neurol. (2016) 15: 116– 24. 10.1016/S1474-4422(15)00092-7 26300044 · DOI
  2. [2]Leontino B Annachiara CJNR Vascular cognitive disorder. A biological and clinical overview. Neurochem Res. (2010) 35: 1933– 8. 10.1007/s11064-010-0346-5 21127967 · DOI
  3. [5]Cheng Y Bai FN. The association of tau with mitochondrial dysfunction in Alzheimer's disease. Front Neurosci. (2018) 12: 163. 10.3389/fnins.2018.00163 29623026 PMC5874499 · DOI · Paper page
  4. [6]Jellinger KA. The enigma of vascular cognitive disorder and vascular dementia. Acta Neuropathol. (2007) 113: 349– 88. 10.1007/s00401-006-0185-2 17285295 · DOI
  5. [7]Hall B Mak E Cervenka S Aigbirhio FI Rowe JB O'Brien JTJARR. In vivo tau PET imaging in dementia: Pathophysiology, radiotracer quantification, and a systematic review of clinical findings. Ageing Res Rev. (2017) 36: 50– 63. 10.1016/j.arr.2017.03.002 28315409 · DOI · Paper page
  6. [8]Mark Y Xie SX Kling MA Toledo JB Wolk DA Lee EB Cerebrovascular atherosclerosis correlates with Alzheimer pathology in neurodegenerative dementias, Brain. (2012) 135: 3749– 56. 10.1093/brain/aws271 23204143 PMC3577102 · DOI
  7. [9]Velayudhan L Proitsi P Westman E Muehlboeck JS Mecocci P Vellas B. Entorhinal cortex thickness predicts cognitive decline in Alzheimer's disease. J Alzheimers Dis. (2013) 33: 755– 66. 10.3233/JAD-2012-121408 23047370 · DOI
  8. [10]Pich EM Jeromin A Frisoni GB Hill D Lockhart A Schmidt ME Therapy, Imaging as a biomarker in drug discovery for Alzheimer's disease: is MRI a suitable technology? (2014) 6: 51 10.1186/alzrt276 PMC4255417 25484927 · DOI
  9. [11]Gómezsancho M Tohka J Gómezverdejo VJMRI Comparison of feature representations in MRI-based MCI-to-AD conversion prediction. Magn Reson Imaging. (2018) 50: 84– 95. 10.1016/j.mri.2018.03.003 29530541 · DOI
  10. [12]Leandrou S Petroudi S Kyriacou PA Reyes-Aldasoro CC Pattichis CSJIRiBE. Quantitative MRI brain studies in mild cognitive impairment and Alzheimer's disease: a methodological review. IEEE Rev Biomed Eng. (2018) 11: 97– 111. 10.1109/RBME.2018.2796598 29994606 · DOI
  11. [13]Hu K Wang Y Chen K Hou L Zhang XJN Multi-scale features extraction from baseline structure MRI for MCI patient classification and AD early diagnosis. Neurocomputing. (2016) 175: 132– 45. 10.1016/j.neucom.2015.10.043 · DOI
  12. [14]Tierney MC Fisher RH Lewis AJ Zorzitto ML Snow WG Reid DW. The NINCDS-ADRDA Work Group criteria for the clinical diagnosis of probable Alzheimer's disease: a clinicopathologic study of 57 cases. Neurology. (1988) 38: 359– 64. 10.1212/WNL.38.3.359 3347338 · DOI · Paper page
  13. [15]Ashburner J Friston KJ. Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation. Neuroimage. (2011) 55: 954– 67. 10.1016/j.neuroimage.2010.12.049 21216294 PMC3221052 · DOI
  14. [16]Abrigo J Shi L Luo Y Chen Q Chu WCW Mok VCT. Standardization of hippocampus volumetry using automated brain structure volumetry tool for an initial Alzheimer's disease imaging biomarker. Acta Radiol. (2018) 60: 769– 76. 10.1177/0284185118795327 30185071 · DOI
  15. [17]Ruxton GDJBE The unequal variance t-test is an underused alternative to Student's t-test and the Mann–Whitney U test. Behav Ecol. (2010) 17: 688– 90. 10.1093/beheco/ark016 · DOI · Paper page
  16. [18]Cortes C Vapnik V Support vector networks. Mach Learn. (1995) 20: 273– 97. 10.1007/BF00994018 · DOI · Paper page
  17. [19]Chang CC Lin CJ LIBSVM: a library for support vector machines. ACM Transact Intellig Syst Technol. (2011) 2: 27 10.1145/1961189.1961199 · DOI · Paper page
  18. [20]Khazaee A Ebrahimzadeh A Babajani-Feremi AJBBR. Classification of patients with MCI and AD from healthy controls using directed graph measures of resting-state fMRI. Behav Brain Res. (2017) 322: 339– 50. 10.1016/j.bbr.2016.06.043 27345822 · DOI
  19. [21]Sørensen L Igel C Pai A Balas I Anker C Lillholm M. Differential diagnosis of mild cognitive impairment and Alzheimer's disease usingstructural MRI cortical thickness, hippocampal shape, hippocampal texture, and volumetry−. Neuroimage Clin. (2017) 13: 470– 82. 10.1016/j.nicl.2016.11.025 28119818 PMC5237821 · DOI · Paper page
  20. [22]Benedict C Grillo CAJFiN. Insulin resistance as a therapeutic target in the treatment of Alzheimer's disease: a state-of-the-art review. Front Neurosci. (2018) 12: 215. 10.3389/fnins.2018.00215 29743868 PMC5932355 · DOI
  21. [23]Petzold A Keir G Warren J Fox N Rossor MNJND. A systematic review and meta-analysis of CSF neurofilament protein levels as biomarkers in dementia. Neurodegener Dis. (2007) 4: 185– 94. 10.1159/000101843 17596713 · DOI
  22. [24]Mirko B Hermann E Brit M Godehard W Volker W Michael L Blood-based neurochemical diagnosis of vascular dementia: a pilot study. J Neurochem. (2010) 103: 467– 74. 10.1111/j.1471-4159.2007.04763.x 17662050 · DOI
  23. [25]Kidemetpiskač S Leko MB BlaŽeković A Langer LH Klepac N Sonicki Z Therapeutics, Evaluation of cerebrospinal fluid phosphorylated tau231 as a biomarker in the differential diagnosis of Alzheimer's disease and vascular dementia. CNS Neurosci Ther. (2018) 24: 734– 40. 10.1111/cns.12814 29453935 PMC6047904 · DOI
  24. [26]Cedazo-Minguez A Winblad BJEG. Biomarkers for Alzheimer's disease and other forms of dementia: Clinical needs, limitations and future aspects. Exp Gerontol. (2010) 45: 5– 14. 10.1016/j.exger.2009.09.008 19796673 · DOI
  25. [27]Aguilar C Westman E Muehlboeck JS Mecocci P Vellas B Tsolaki M. Different multivariate techniques for automated classification of MRI data in Alzheimer's disease and mild cognitive impairment. Psychiatry Res. (2013) 212: 89– 98. 10.1016/j.pscychresns.2012.11.005 23541334 · DOI
  26. [28]Cuingnet R Gerardin E Tessieras J Auzias G Lehéricy S Habert MO. Automatic classification of patients with Alzheimer's disease from structural MRI: a comparison of ten methods using the ADNI database. Neuroimage. (2011) 56: 766– 81. 10.1016/j.neuroimage.2010.06.013 20542124 · DOI
  27. [30]Beheshti I Demirel H Matsuda HJCiB. Classification of Alzheimer's disease and prediction of mild cognitive impairment-to-Alzheimer's conversion from structural magnetic resource imaging using feature ranking and a genetic algorithm. Comput Biol Med. (2017) 83: 109– 19. 10.1016/j.compbiomed.2017.02.011 28260614 · DOI
  28. [31]Jack CR Knopman DS Jagust WJ Petersen RC Weiner MW Aisen PS. Tracking pathophysiological processes in Alzheimer's disease: an updated hypothetical model of dynamic biomarkers. Lancet Neurol. (2013) 12: 207– 16. 10.1016/S1474-4422(12)70291-0 23332364 PMC3622225 · DOI · Paper page
  29. [32]Csernansky JG Wang L Price JL Morris JCJAD Disorders A. Correlations between antemortem hippocampal volume and postmortem neuropathology in AD subjects. Alzheimer Dis Assoc Disord. (2004) 18: 190– 5. 15592129
  30. [33]Tondelli M Wilcock GK Nichelli PJNoA. Structural MRI changes detectable up to ten years before clinical Alzheimer's disease. Neurobiol Aging. (2012) 33: 825.e825–36. 10.1016/j.neurobiolaging.2011.05.018 21782287 · DOI
  31. [34]Ozkan S Adapinar DO Elmaci NT Arslantas DJND Apraxia for differentiating Alzheimer's disease from subcortical vascular dementia and mild cognitive impairment. Neuropsychiatr Dis Treat. (2013) 2013: 947– 51. 10.2147/NDT.S47879 PMC3709829 23882142 · DOI
  32. [35]Kim TY Kim SY Kim EG Kim JW Park KW Sung SM The differences of behavioral and psychological symptoms in the patients of Alzheimer's disease and vascular dementia. Alzheimers Dementia. (2006) 2: S260– 1. 10.1016/j.jalz.2006.05.932 · DOI
  33. [36]Pan SJ Yang Q A survey on transfer learning. IEEE Trans Knowl Data Eng. (2010) 22: 1345– 59. 10.1109/TKDE.2009.191 · DOI · Paper page

Authors
Zheng, Y., Guo, H., Zhang, L., Wu, J., Li, Q., & Lv, F.
Affiliations
The Affiliated Yongchuan Hospital of Chongqing Medical University (CN)
Corresponding author
Lv, Fajin
ORCID
Venue
Frontiers in Neurology
Publisher
Frontiers Media SA
Published
2019-10-25
Volume
10
Pages
1097-1097
ISSN
1664-2295 (ISSN-L)
DOI
10.3389/fneur.2019.01097
PMC
PMC6823227
OpenAlex
W2982009528
Cited by
55
References
36
Citations by year
2026: 7 · 2025: 10 · 2024: 12 · 2023: 9 · 2022: 6 · 2021: 6 · 2020: 5
FWCI
3.39
Type
journal article
Language
en
Open access
Licence
Locations
  • Frontiers in Neurology (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Natural Science Foundation of China (31570003, 31800823)
  • Chongqing Medical University
Topics
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Life Sciences › Neuroscience › Neurology › Neurological Disease Mechanisms and Treatments
Keywords
vascular dementia, Alzheimer's disease, differential diagnosis, structural MRI, MRI biomarkers, computer-aided diagnosis, support vector machine, LASSO feature selection, brain tissue segmentation, dementia classification

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review