Predicting mild cognitive impairment progression to Alzheimer’s disease based on machine learning analysis of cortical morphological features

Aging Clinical and Experimental Research - Tập 35 - Trang 1721-1730 - 2023
Wei Wang1,2, Jiaxuan Peng1, Jie Hou1, Zhongyu Yuan1, Wutao Xie2, Guohe Mao3, Yaling Pan4, Yuan Shao4, Zhenyu Shu4
1Jinzhou Medical University Postgraduate Education Base (Zhejiang Provincial People’s Hospital, People’s Hospital of Hangzhou Medical College), Hangzhou, China
2Department of Radiology, The First Affiliated Hospital of Chongqing Medical and Pharmaceutical College, Chongqing, China
3Banan Hospital of Chongqing Medical University, Chongqing, China
4Center for Rehabilitation Medicine, Department of Radiology, Zhejiang Provincial People’s Hospital, Affiliated People’s Hospital, Hangzhou Medical College, Hangzhou City, China

Tóm tắt

To establish a model for predicting mild cognitive impairment (MCI) progression to Alzheimer's disease (AD) using morphological features extracted from a joint analysis of voxel-based morphometry (VBM) and surface-based morphometry (SBM). We analyzed data from 121 MCI patients from the Alzheimer's Disease Neuroimaging Initiative, 32 of whom progressed to AD during a 4-year follow-up period and were classified as the progression group, while the remaining 89 were classified as the non-progression group. Patients were divided into a training set (n = 84) and a testing set (n = 37). Morphological features measured by VBM and SBM were extracted from the cortex of the training set and dimensionally reduced to construct morphological biomarkers using machine learning methods, which were combined with clinical data to build a multimodal combinatorial model. The model's performance was evaluated using receiver operating characteristic curves on the testing set. The Alzheimer's Disease Assessment Scale (ADAS) score, apolipoprotein E (APOE4), and morphological biomarkers were independent predictors of MCI progression to AD. The combinatorial model based on the independent predictors had an area under the curve (AUC) of 0.866 in the training set and 0.828 in the testing set, with sensitivities of 0.773 and 0.900 and specificities of 0.903 and 0.747, respectively. The number of MCI patients classified as high-risk for progression to AD was significantly different from those classified as low-risk in the training set, testing set, and entire dataset, according to the combinatorial model (P < 0.05). The combinatorial model based on cortical morphological features can identify high-risk MCI patients likely to progress to AD, potentially providing an effective tool for clinical screening.

Tài liệu tham khảo

Kang L, Jiang J, Huang J et al (2020) Identifying early mild cognitive impairment by multi-modality MRI-based deep learning. Front Aging Neurosci 12:206 Tang L, Wu X, Liu H et al (2021) Individualized prediction of early Alzheimer’s disease based on magnetic resonance imaging radiomics, clinical, and laboratory examinations: a 60-month follow-up study. J Magn Reson Imaging 54:1647–1657 Gomersall T, Smith SK, Blewett C et al (2017) It’s definitely not Alzheimer’s: perceived benefits and drawbacks of a mild cognitive impairment diagnosis. Br J Health Psychol 22:786–804 Gao Y, Wee CY, Kim M et al (2015) MCI identification by joint learning on multiple MRI data. Med Image Comput Comput Assist Interv 9350:78–85 Fjell AM, Walhovd KB (2010) Structural brain changes in aging: courses, causes and cognitive consequences. Rev Neurosci 21:187–221 Schmitter D, Roche A, Maréchal B et al (2014) An evaluation of volume-based morphometry for prediction of mild cognitive impairment and Alzheimer’s disease. Neuroimage Clin 7:7–17 Mechelli A, Crinion JT, Noppeney U et al (2004) Neurolinguistics: structural plasticity in the bilingual brain. Nature 431:757 Goto M, Abe O, Hagiwara A et al (2022) Advantages of using both voxel- and surface-based morphometry in cortical morphology analysis: a review of various applications. Magn Reson Med Sci 21:41–57 Ma Z, Jing B, Li Y et al (2020) Identifying mild cognitive impairment with random forest by integrating multiple MRI morphological metrics. J Alzheimers Dis 73:991–1002 Lee G, Nho K, Kang B et al (1952) Predicting Alzheimer’s disease progression using multi-modal deep learning approach. Sci Rep 2019:9 Ashburner J, Friston KJ (2000) Voxel-based morphometry–the methods. Neuroimage 11:805–821 Dahnke R, Yotter RA, Gaser C (2013) Cortical thickness and central surface estimation. Neuroimage 15:336–348 Wu Z, Peng Y, Hong M et al (2021) Gray matter deterioration pattern during Alzheimer’s disease progression: a regions-of-interest based surface morphometry study. Front Aging Neurosci 13:593898 Long Z, Huang J, Li B et al (2018) A comparative atlas-based recognition of mild cognitive impairment with voxel-based morphometry. Front Neurosci 12:916 Den Heijer T, van der Lijn F, Koudstaal PJ et al (2010) A 10-year follow-up of hippocampal volume on magnetic resonance imaging in early dementia and cognitive decline. Brain 133:1163–1172 Núñez C, Callén A, Lombardini F et al (2020) Alzheimer’s disease neuroimaging initiative. Different cortical gyrification patterns in Alzheimer’s disease and impact on memory performance. Ann Neurol 88:67–80 Ten Kate M, Dicks E, Visser PJ et al (2018) Alzheimer’s Disease Neuroimaging Initiative. Atrophy subtypes in prodromal Alzheimer’s disease are associated with cognitive decline. Brain 141:3443–3456 Dang M, Yang C, Chen K et al (2023) Beijing aging brain rejuvenation initiative, for the Alzheimer’s disease neuroimaging initiative. Hippocampus-centred grey matter covariance networks predict the development and reversion of mild cognitive impairment. Alzheimers Res Ther 15:27 Garg N, Choudhry MS, Bodade RM (2023) A review on Alzheimer’s disease classification from normal controls and mild cognitive impairment using structural MR images. J Neurosci Methods 384:109745 Cho H, Choi JY, Lee SH et al (2017) Excessive tau accumulation in the parieto-occipital cortex characterizes early-onset Alzheimer’s disease. Neurobiol Aging 53:103–111 Takahashi T, Sasabayashi D, Takayanagi Y et al (2022) Gross anatomical features of the insular cortex in schizophrenia and schizotypal personality disorder: potential relationships with vulnerability, illness stages, and clinical subtypes. Front Psychiatry 13:1050712 Jones RS, Waldman AD (2004) 1H-MRS evaluation of metabolism in Alzheimer’s disease and vascular dementia. Neurol Res 26:488–495 Manero RM, Casals-Coll M, Sánchez-Benavides G et al (2014) Diagnostic validity of the Alzheimer’s disease functional assessment and change scale in mild cognitive impairment and mild to moderate Alzheimer’s disease. Dement Geriatr Cogn Disord 37:366–375 Wessels AM, Dowsett SA, Sims JR (2018) Detecting treatment group differences in Alzheimer’s disease clinical trials: a comparison of Alzheimer’s disease assessment scale—cognitive subscale (ADAS-Cog) and the clinical dementia rating—sum of boxes (CDR-SB). J Prev Alzheimers Dis 5:15–20 Ben Jemaa S, Attia Romdhane N, Bahri-Mrabet A et al (2017) An Arabic version of the cognitive subscale of the Alzheimer’s disease assessment scale (ADAS-Cog): reliability, validity, and normative data. J Alzheimers Dis 60:11–21 Blanchard JW, Akay LA, Davila-Velderrain J et al (2022) APOE4 impairs myelination via cholesterol dysregulation in oligodendrocytes. Nature 611:769–779 Shu Z, Xu Y, Shao Y et al (2020) Radiomics from magnetic resonance imaging may be used to predict the progression of white matter hyperintensities and identify associated risk factors. Eur Radiol 30:3046–3058 Hu Z, Wang Z, Jin Y et al (2023) VGG-TSwinformer: transformer-based deep learning model for early Alzheimer’s disease prediction. Comput Methods Programs Biomed 229:107291