Share：
Share this content in WeChat
X
[Chinese][PDF]112081
• Technical Article •
A machine learning model for early diagnosis of Alzheimer's disease
YAO Lili  FAN Zhao 

Cite this article as: Yao LL, Fan Z. A machine learning model for early diagnosis of Alzheimer's disease[J]. Chin J Magn Reson Imaging, 2021, 12(6): 78-82. DOI:10.12015/issn.1674-8034.2021.06.015.


[Abstract] Objective Machine learning algorithm was used to classify the progression of Alzheimer's disease (AD) and provide an auxiliary tool for clinical early diagnosis of AD. Materials andMethods The progression of AD was divided into four groups, including normal cognitive subjects, early mild cognitive impairment, late mild cognitive impairment and AD. Structure magnetic resonance imaging (sMRI) datas were collected from these subjects. In addition, Age, sex, education level and Mini-Mental State Examination (MMSE) scores were also collected. Then, L1-regularized support vector machine (L1-SVM) algorithm was used to select the features that contributed the most to the classification group based on the two datasets respectively. The extracted feature subsets were classified in the back propagation (BP) neural network model, and compared with Logistic regression, random forest and support vector machine (SVM). The accuracy of the four models was compared with the ten fold cross validation method. The specificity, sensitivity and area under receiver operating characteristic curve (AUC) values of the optimal combination model were given.Results The feature sets with three demographic indicators and MMSE score were better than that with only sMRI feature set. The classification accuracy of BP neural network algorithm combined with L1-SVM feature selection algorithm was better than other machine learning models, especially in the process of transforming from normal cognitive function to AD. The accuracy of BP neural network was as high as 98.90%, sensitivity was 98.75%, AUC was 1.00. There were slight differences among different classification groups.Conclusions The combined model of L1-SVM and BP neural network can be used for the early diagnosis of AD, and the relevant characteristic data of each stage of AD progressive transformation provide the basis for clinical basic research and pathological changes.
[Keywords] machine learning；structural magnetic resonance imaging；Alzheimer's disease；L1 regularization；back propagation；neural network

YAO Lili1   FAN Zhao2*  

1 School of Basic Medicine, Shanxi Medical University, Taiyuan 030001, China

2 Translational Medicine Research Center of Shanxi Medical University, Taiyuan 030001, China

Fan Z, E-mail: fanzhao316@163.com

Conflicts of interest   None.

This work was part of International Cooperation Project of Key Research and Development Program of Shanxi Province (No. 201803D421068) and Shanxi Province Returned Scholars' Science and Technology Activities Selected Funding Project (No. 619017).
Received  2020-12-13
Accepted  2021-03-08
DOI: 10.12015/issn.1674-8034.2021.06.015
Cite this article as: Yao LL, Fan Z. A machine learning model for early diagnosis of Alzheimer's disease[J]. Chin J Magn Reson Imaging, 2021, 12(6): 78-82. DOI:10.12015/issn.1674-8034.2021.06.015.

1
Gauler J, James B, Johnson T, et al. Alzheimer's disease facts and figures[J]. Alzheimers Dement, 2018, 14(3): 367-429. DOI: 10.1016/j.jalz.2018.02.001.
2
Reitz C, Mayeux R. Alzheimer's disease: Epidemiology, diagnostic criteria, risk factors and biomarkers[J]. Biochem Pharmacol, 2014, 88(4): 640-651. DOI: 10.1016/j.bcp.2013.12.024.
3
Moira M, Clarissa F, Jorge J, et al. Predicting and tracking short term disease progression in amnestic mild cognitive impairment patients with prodromal Alzheimer's disease: Structural brain biomarkers[J]. J Alzheimer's Dis, 2018, 69(1): 3-14. DOI: 10.3233/JAD-180152.
4
Hui K, Ooi C, Lim M, et al. An improved wrapper-based feature selection method for machinery fault diagnosis[J]. PLoS One, 2017, 12(12): 0189143. DOI: 10.1371/journal.pone.0189143.
5
Gaonkar B, Shinohara R, Davatzikos C. Interpreting support vector machine models for multivariate group wise analysis in neuroimaging[J]. Med Image Anal, 2015, 24(1): 190-204. DOI: 10.1016/j.media.2015.06.008.
6
Chai H, Liang Y, Wang S, et al. A novel logistic regression model combining semi-supervised learning and active learning for disease classification[J]. Sci Rep, 2018, 8(1): 13009. DOI: 10.1038/s41598-018-31395-5.
7
Hongliu C, Simon B, Robert S, et al. Random forest dissimilarity based multi-view learning for Radiomics application[J]. Pattern Recognition, 2019, 88: 185-197. DOI: 10.1016/j.patcog.2018.11.011.
8
Shen Y, Liu Z, Ott J, et al. Support vector machines with L1 penalty for detecting gene-gene interactions[J]. Int J Data Min Bioinform, 2012, 6(5): 463-470. DOI: 10.1504/ijdmb.2012.049300.
9
Steiert B, Timmer J, Kreutz C. L1 regularization facilitates detection of cell type-specific parameters in dynamical systems[J]. Bioinformatics, 2016, 32(17): 718-726. DOI: 10.1093/bioinformatics/btw461.
10
Hu FY, Wang L, Wang SS, et al. A human body posture recognition algorithm based on BP neural network for wireless body area networks[J]. China Communications, 2016, 13(8): 198-208. DOI: 10.1109/cc.2016.7563723.
11
Deng Q. A BP neural network optimisation method based on dynamical regularization[J]. J Control Decision, 2019, 6(2): 111-121. DOI: 10.1080/23307706.2017.1419837.
12
Gertje EC, Pluta J, Das S, et al. Clinical application of automatic segmentation of medial temporal lobe subregions in prodromal and dementia-level Alzheimer's disease[J]. J Alzheimers Dis, 2016, 54(3): 1027-1037. DOI: 10.3233/JAD-160014.
13
Fan Z, Li C. Classification of the course of Alzheimer's disease based on machine learning[J]. Chin J Med Imaging, 2019, 27(10): 792-795. DOI: 10.3969/j.issn.1005-5185.2019.10.019.
14
Dhikav V, Duraisamy S, Anand KS. Hippocampal volumes among older Indian adults: Comparison with Alzheimer's disease and mild cognitive impairment[J]. Ann Indian Acad Neurol, 2016, 19(2): 195-200. DOI: 10.4103/0972-2327.176863.
15
Vasta R, Augimeri A, Cerasa A, et al. For the Alzheimer's disease neuroimaging I. hippocampal subfield atrophies in converted and not-converted mild cognitive impairments patients by a markov random fields algorithm[J]. Curr Alzheimer Res, 2016, 13(5): 566-574. DOI: 10.2174/1567205013666160120151457.
16
Altaf T, Anwar SM, Gul N, et al. Multi-class Alzheimer's disease classification using image and clinical features[J]. Biomed Signal Process, 2018, 43(5): 64-74. DOI: 10.1016/j.bspc.2018.02.019.
17
Catani M, Dellacqua F, Thiebautde SM. A revised limbic system model for memory, emotion and behaviour[J]. Neurosci Biobehav Rev, 2013, 37(8): 1724-1737. DOI: 10.1016/j.neubiorev.2013.07.001.
18
Qi XD. Classification of Alzheimer's disease course based on brain MRI and machine learning[D]. Taiyuan: Shanxi Med Univ, 2018.

PREV Acupuncture changes the functional connectivity of the right insula in asthma: A fMRI study
NEXT The value of identifying benign and malignant breast lesions based on the texture feature of Tirm sequence combined with time-intensity curve
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn