我们的网站为什么显示成这样？

可能因为您的浏览器不支持样式，您可以更新您的浏览器到最新版本，以获取对此功能的支持，访问下面的网站，获取关于浏览器的信息：

|本期目录/Table of Contents|

基于Stacking集成策略的阿尔茨海默病诊断模型研究(PDF)

《现代预防医学》[ISSN:1003-8507/CN:51-1365/R]

期数:
2022年22期
页码:
4045-4051
栏目:
流行病与统计方法
出版日期:
2022-11-30

文章信息/Info

Title:
Multi-classification diagnosis of Alzheimer’s disease based on Stacking ensemble strategy
作者:
韩红娟1; 2; 陈杜荣1; 秦瑶1; 张荣1; 白文琳1; 崔靖1; 马艺菲1; 刘龙1; 余红梅1; 3
1. 山西医科大学公共卫生学院卫生统计学教研室，山西 太原 030001；
2. 山西医科大学基础医学院数学教研室，山西 太原 030001；
3. 重大疾病风险评估山西省重点实验室，山西 太原 030001
Author(s):
HAN Hong-juan*;  CHEN Du-rong;  QIN Yao;  ZHANG Rong;  BAI Wen-lin;  CUI Jing;  MA Yi-fei;  LIU Long;  YU Hong-mei
*Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, Shanxi 030001, China
关键词:
阿尔茨海默病; 显著记忆障碍; 轻度认知障碍; 多分类
Keywords:
Alzheimer’s disease;  Significant memory concern;  Mild cognitive impairment;  Multi-classification
分类号:
R749.16
DOI:
10.20043/j.cnki.MPM.202205662
文献标识码:
A
摘要:
目的 针对阿尔茨海默病（AD）相关临床人群，包括认知正常（CN）、显著记忆障碍（SMC）、早期轻度认知障碍（EMCI）、晚期轻度认知障碍（LMCI）和AD进行多分类研究，以期实现AD计算机辅助诊断。方法 基于阿尔茨海默病神经影像学计划（ADNI）数据库中2 006例受试者（436例NC，261例SMC，323例EMCI，606例LMCI和380例AD），采用LASSO方法进行特征选择，SMOTE过采样方法处理类别不平衡问题，采用支持向量机、随机森林、逻辑回归和K近邻作为初级学习器，逻辑回归作为次级学习器，加权投票集成策略构建Stacking多分类诊断模型。结果 较于以上四种初级学习器，本研究构建的Stacking集成模型分类效果较好，稳定性高，在NC vs 非NC，SMC vs 非SMC，EMCI vs 非EMCI和LMCI vs AD之间分类准确率、召回率、F1 Score均值均在92%以上，AUC均值均在0.97以上。结论 本研究构建的AD多分类Stacking集成策略，具有较好的分类性能，可科学指导AD的预防与控制，为临床医生提供自动化的AD临床辅助诊断。
Abstract:
Objective To construct an Alzheimer’s disease (AD) auxiliary diagnosis model to classify normal cognition (NC), significant memory concern (SMC), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), and AD. Methods The data we used were from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) with a total of 2 006 participants (436 NC, 261 SMC, 323 EMCI, 606 LMCI, and 380 AD). LASSO was utilized to screen subsets of features, and SMOTE oversampling was used to address class imbalance problem of data. We built a multi-classification model using the Stacking ensemble strategy in which the support vector machine, random forest, logistic regression, and K-nearest neighbor were used as base learners and logistic regression were used as meta learners. Results Compared with four base classifiers, the Stacking ensemble model constructed in this study had the best classification effect and showed stable model performance. The mean of accuracy, recall, and F1 Score of NC vs non-NC, SMC vs non-SMC, EMCI vs non-EMCI, and LMCI vs AD were all above 92%, and the mean of AUC values were above 0.97. Conclusion The Stacking ensemble strategy of multi-classification has good classification performance, which can guide the prevention and control of AD scientifically and provide physicians with automatic clinical diagnosis of AD.

参考文献/References

[ 1 ] Xu W, Rao J, Song Y, et al. Altered functional connectivity of the basal nucleus of meynert in subjective cognitive impairment, early mild cognitive impairment, and late mild cognitive impairment[J]. Frontiers in Aging Neuroscience, 2021, 13: 671351.
[ 2 ] Edmonds CE, McDonald CR, Marshall A, et al. Early versus late MCI: Improved MCI staging using a neuropsychological approach[J]. Alzheimer’s & Dementia: the Journal of the Alzheimer’s Association, 2019, 15: 699 - 708.
[ 3 ] 彭雯洁，秦瑶，韩红娟，等．轻度认知障碍转化为阿尔茨海默病的生存分析[J]．现代预防医学，2020，47（16）：2891 - 2932．Peng WJ, Qin Y, Han HJ, et al. Survival analysis from mild cognitive impairment conversion to Alzheimer’s disease[J]. Modern Preventive Medicine, 2020, 47(16): 2891 - 2932.
[ 4 ] 汪睿彤，刘珏．阿尔茨海默病的流行病学研究进展[J]．中国慢性病预防与控制，2021，29（9）：707 - 710, 711．Wang RT, Liu J. Advances in epidemiological studies of Alzheimer’s disease[J]. Chinese Journal of Prevention and Control of Chronic Diseases, 2021, 29(9): 707 - 710, 711.
[ 5 ] Song X, Zhou F, Frangi AF, et al. Graph convolution network with similarity awareness and adaptive calibration for disease - induced deterioration prediction[J]. Medical Image Analysis, 2021, 69(3): 101947.
[ 6 ] Ronnlund M, Sundstrom A, Adolfsson R, et al.Self - Reported memory failures: associations with future dementia in a Population - Based study with Long - Term Follow - Up[J]. Journal of the American Geriatrics Society, 2015, 63(9): 1766 - 1773.
[ 7 ] 褚会敏，王金娟，潘月丽．基于机器学习算法的儿童过敏性紫癜肾损害风险预测[J]．中国预防医学杂志，2022，23（1）：62 - 67．Chu HM, Wang JJ, Pan YL. Machine learning algorithm based risk prediction for renal damage in children with henoch - schonlein purpura[J]. Chinese Preventive Medicine, 2022, 23(1): 62 - 67.
[ 8 ] Kwon H, Park J, Lee Y. Stacking ensemble technique for classifying breast cancer[J]. Healthcare Informatics Research, 2019, 25(4): 283 - 288.
[ 9 ] Becker S, Boettinger O, Sulzer P, et al. Everyday function in Alzheimer’s and Parkinson’s patients with mild cognitive impairment[J]. Journal of Alzheimer’s Disease, 2021, 79(1): 197 - 209.
[ 10 ] Tripathi R, Kumar JK, Bharath S, et al.Clinical validity of NIMHANS neuropsychological battery for elderly: A preliminary report[J]. Indian Journal of Psychiatry, 2013, 55(3): 279 - 282.
[ 11 ] Tripathi R, Marimuthu P, Varghese M, et al. Neuropsychological markers of mild cognitive impairment: A clinic based study from urban India[J]. Annals of Indian Academy of Neurology, 2015, 18(2): 177 - 180.
[ 12 ] 章权，周梁琦，邹琪，等．基于Stacking的糖尿病预测方法研究[J]．智能计算机与应用，2020，10（2）：107 - 110．Zhang Q, Zhou LQ, Zou Q, et al. Research on diabetes prediction method based on Stacking[J]. Intelligent Computer and Applications, 2020, 10(2): 107 - 110.
[ 13 ] Xiaomu T, Jie L. Comparing different algorithms for the course of Alzheimer’s disease using machine learning[J]. Annals of Palliative Medicine, 2021, 10(9): 9715 - 9724.
[ 14 ] Jia H, Wang Y, Duan Y, et al. Alzheimer’s disease classification based on image transformation and features fusion[J]. Computational and Mathematical Methods in Medicine, 2021, 2021: 9624269.
[ 15 ] 田云伟，李善玲，梅婷，等．老年人主观记忆抱怨研究进展[J]．护理学杂志，2022，37（4）：107 - 110．Tian YW, Li SL, Mei T, et al. Review on subjective memory complaints of the elderly[J]. Journal of Nursing Science, 2022, 37(4): 107 - 110.
[ 16 ] Mitchell AJ, Beaumont H, Ferguson D, et al. Risk of dementia and mild cognitive impairment in older People with subjective memory complaints: meta‐analysis[J]. Acta Psychiatrica Scandinavica, 2015, 130(6): 439 - 451.

备注/Memo

备注/Memo:
基金项目：国家自然科学基金面上项目（81973154）；山西省青年自然科学基金（201801D221399，201901D211330，20210302123 242）
作者简介：韩红娟（1981—），女，博士在读，研究方向：队列研究的统计方法及应用
通信作者：余红梅，E-mail：yu@sxmu.edu.cn
更新日期/Last Update: 2022-11-30