Detection of mild cognitive impairment in type 2 diabetes mellitus based on machine learning using privileged information

被引:6
作者
Xia, Shuiwei [1 ]
Zhang, Yu [2 ]
Peng, Bo [3 ,4 ]
Hu, Xianghua [1 ]
Zhou, Limin [1 ]
Chen, Chunmiao [1 ]
Lu, Chenying [1 ]
Chen, Minjiang [1 ]
Pang, Chunying [2 ]
Dai, Yakang [3 ,4 ]
Ji, Jiansong [1 ]
机构
[1] Wenzhou Med Univ, Zhejiang Univ, Lishui Cent Hosp, Affiliated Lishui Hosp,Affiliated Hosp 5,Key Lab I, Lishui 323000, Peoples R China
[2] Changchun Univ Sci & Technol, Sch Life Sci & Technol, Changchun 130000, Peoples R China
[3] Chinese Acad Sci, Suzhou Inst Biomed Engn & Technol, Suzhou 215163, Peoples R China
[4] Jinan Guoke Med Engn Technol Dev Co LTD, 25000, Jinan, Peoples R China
关键词
T2DM; Mild cognitive impairment; Functional connectivity; Privilege information; Cascaded multi =column RVFL plus; COMPUTER-AIDED DIAGNOSIS; RISK; PROGRESSION; DEMENTIA; AGE;
D O I
10.1016/j.neulet.2022.136908
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Type 2 diabetes mellitus (T2DM) patients may develop into mild cognitive impairment (MCI) or even dementia. However, there is lack of reliable machine learning model for detection MCI in T2DM patients based on machine learning method. In addition, the brain network changes associated with MCI have not been studied. The aim of this study is to develop a machine learning based algorithm to help detect MCI in T2DM. There are 164 par-ticipants were included in this study. They were divided into T2DM-MCI (n = 56), T2DM-nonMCI (n = 49), and normal controls (n = 59) according to the neuropsychological evaluation. Functional connectivity of each participant was constructed based on resting-state magnetic resonance imaging (rs-fMRI). Feature selection was used to reduce the feature dimension. Then the selected features were set into the cascaded multi-column random vector functional link network (RVFL) classifier model using privileged information. Finally, the optimal model was trained and the classification performance was obtained using the testing data. The results show that the proposed algorithm has outstanding performance compared with classic methods. The classification accuracy of 73.18 % (T2DM-MCI vs NC) and 79.42 % (T2DM-MCI vs T2DM-nonMCI) were achieved. The functional con-nectivity related to T2DM-MCI mainly distribute in the frontal lobe, temporal lobe, and central region (motor cortex), which could be used as neuroimaging biomarkers to recognize MCI in T2DM patients. This study pro-vides a machine learning model for diagnosis of MCI in T2DM patients and has potential clinical significance for timely intervention and treatment to delay the development of MCI.
引用
收藏
页数:6
相关论文
共 32 条
  • [1] Effects of Hypertension and Diabetes on Sentence Comprehension in Aging
    Cahana-Amitay, Dalia
    Albert, Martin L.
    Ojo, Emmanuel A.
    Sayers, Jesse
    Goral, Mira
    Obler, Loraine K.
    Spiro, Avron, III
    [J]. JOURNALS OF GERONTOLOGY SERIES B-PSYCHOLOGICAL SCIENCES AND SOCIAL SCIENCES, 2013, 68 (04): : 513 - 521
  • [2] Comprehensive Medical Evaluation and Assessment of Comorbidities: Standards of Medical Care in Diabetes-2019
    Cefalu, William T.
    Berg, Erika Gebel
    Saraco, Mindy
    Petersen, Matthew P.
    Uelmen, Sacha
    Robinson, Shamera
    [J]. DIABETES CARE, 2019, 42 : S34 - S45
  • [3] Risk Factors for Sarcopenia in the Elderly with Type 2 Diabetes Mellitus and the Effect of Metformin
    Chen, Fenqin
    Xu, Shuai
    Wang, Yingfang
    Chen, Feng
    Cao, Lu
    Liu, Tingting
    Huang, Ting
    Wei, Qian
    Ma, Guojing
    Zhao, Yuhong
    Wang, Difei
    [J]. JOURNAL OF DIABETES RESEARCH, 2020, 2020
  • [4] Duan LX, 2014, LECT NOTES COMPUT SC, V8674, P204, DOI 10.1007/978-3-319-10470-6_26
  • [5] Doubly Supervised Transfer Classifier for Computer-Aided Diagnosis With Imbalanced Modalities
    Han, Xiangmin
    Fei, Xiaoyan
    Wang, Jun
    Zhou, Tao
    Ying, Shihui
    Shi, Jun
    Shen, Dinggang
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2022, 41 (08) : 2009 - 2020
  • [6] Risk factors associated with the onset and progression of Alzheimer's disease: A systematic review of the evidence
    Hersi, Mona
    Irvine, Brittany
    Gupta, Pallavi
    Gomes, James
    Birkett, Nicholas
    Krewski, Daniel
    [J]. NEUROTOXICOLOGY, 2017, 61 : 143 - 187
  • [7] Early detection of type 2 diabetes mellitus using machine learning-based prediction models
    Kopitar, Leon
    Kocbek, Primoz
    Cilar, Leona
    Sheikh, Aziz
    Stiglic, Gregor
    [J]. SCIENTIFIC REPORTS, 2020, 10 (01)
  • [8] Type 2 Diabetes Mellitus May Exacerbate Gray Matter Atrophy in Patients With Early-Onset Mild Cognitive Impairment
    Li, Chang
    Zuo, Zhiwei
    Liu, Daihong
    Jiang, Rui
    Li, Yang
    Li, Haitao
    Yin, Xuntao
    Lai, Yuqi
    Wang, Jian
    Xiong, Kunlin
    [J]. FRONTIERS IN NEUROSCIENCE, 2020, 14
  • [9] Cortical thickness contributes to cognitive heterogeneity in patients with type 2 diabetes mellitus
    Li, Chang
    Li, Chuanming
    Yang, Qifang
    Wang, Bin
    Yin, Xuntao
    Zuo, Zhiwei
    Hu, Xiaofei
    Lai, Yuqi
    Wang, Jian
    [J]. MEDICINE, 2018, 97 (21)
  • [10] Altered Functional Hubs and Connectivity in Type 2 Diabetes Mellitus Without Mild Cognitive Impairment
    Li, Yifan
    Liang, Yi
    Tan, Xin
    Chen, Yuna
    Yang, Jinquan
    Zeng, Hui
    Qin, Chunhong
    Feng, Yue
    Ma, Xiaomeng
    Qiu, Shijun
    [J]. FRONTIERS IN NEUROLOGY, 2020, 11