Detection of mild cognitive impairment in type 2 diabetes mellitus based on machine learning using privileged information. (20th November 2022)

• Record Type: Journal Article
• Authors: Xia, Shuiwei; Zhang, Yu; Peng, Bo; Hu, Xianghua; Zhou, Limin; Chen, Chunmiao; Lu, Chenying; Chen, Minjiang; Pang, Chunying; Dai, Yakang; Ji, Jiansong
• Is Part Of: Neuroscience letters. Volume 791(2022)
• Publication Date: 2022-11-20
• Subjects: T2DM -- Mild cognitive impairment -- Functional connectivity -- Privilege information -- Cascaded multi=column RVFL+; Neurology -- Periodicals; Neurology -- Periodicals; Research -- Periodicals; Neurologie -- Périodiques; Neuroanatomie -- Périodiques; Neuropharmacologie -- Périodiques; Neurophysiologie -- Périodiques; Neurology; Periodicals; Electronic journals; 617.48
• DOI: 10.1016/j.neulet.2022.136908
• Languages: English
• ISSNs: 0304-3940

Abstract

Highlights: The aim of this study is to develop a machine learning based algorithm to help detect MCI in T2DM. Functional connectivity of each participant is constructed and feature selection is used to reduce the feature dimension. Privileged information is used to constructed the cascaded classifier model. Self-paced learning (SPL) is used to assign sample weights, which helps optimize the process in training the classifier model. Abstract: 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 participants 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 connectivity 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 provides 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.