机器学习转变为阿尔茨海默病导致的退化MCI的预测模型-一项为期两年的随访调查。

IF 1.8 4区 医学 Q3 CLINICAL NEUROLOGY
Xiaohui Zhao, Haijing Sui, Chengong Yan, Min Zhang, Haihan Song, Xueyuan Liu, Juan Yang
{"title":"机器学习转变为阿尔茨海默病导致的退化MCI的预测模型-一项为期两年的随访调查。","authors":"Xiaohui Zhao,&nbsp;Haijing Sui,&nbsp;Chengong Yan,&nbsp;Min Zhang,&nbsp;Haihan Song,&nbsp;Xueyuan Liu,&nbsp;Juan Yang","doi":"10.2174/1567205020666221019122049","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>The aim of the present work was to investigate the features of the elderly population aged ≥65 yrs and with deteriorative mild cognitive impairment (MCI) due to Alzheimer's disease (AD) to establish a prediction model.</p><p><strong>Methods: </strong>A total of 105 patients aged ≥65 yrs and with MCI were followed up, with a collection of 357 features, which were derived from the demographic characteristics, hematological indicators (serum Aβ1-40, Aβ1-42, P-tau and MCP-1 levels, APOE gene), and multimodal brain Magnetic Resonance Imaging (MRI) imaging indicators of 116 brain regions (ADC, FA and CBF values). Cognitive function was followed up for 2 yrs. Based on the Python platform Anaconda, 105 patients were randomly divided into a training set (70%) and a test set (30%) by analyzing all features through a random forest algorithm, and a prediction model was established for the form of rapidly deteriorating MCI.</p><p><strong>Results: </strong>Of the 105 patients enrolled, 41 deteriorated, and 64 did not come within 2 yrs. Model 1 was established based on demographic characteristics, hematological indicators and multi-modal MRI image features, the accuracy of the training set being 100%, the accuracy of the test set 64%, sensitivity 50%, specificity 67%, and AUC 0.72. Model 2 was based on the first five features (APOE4 gene, FA value of left fusiform gyrus, FA value of left inferior temporal gyrus, FA value of left parahippocampal gyrus, ADC value of right calcarine fissure as surrounding cortex), the accuracy of the training set being 100%, the accuracy of the test set 85%, sensitivity 91%, specificity 80% and AUC 0.96. Model 3 was based on the first four features of Model 1, the accuracy of the training set is 100%, the accuracy of the test set 97%, sensitivity100%, specificity 95% and AUC 0.99. Model 4 was based on the first three characteristics of Model 1, the accuracy of the training set being 100%, the accuracy of the test set 94%, sensitivity 92%, specificity 94% and AUC 0.96. Model 5 was based on the hematological characteristics, the accuracy of the training set is 100%, the accuracy of the test set 91%, sensitivity 100%, specificity 88% and AUC 0.97. The models based on the demographic characteristics, imaging characteristics FA, CBF and ADC values had lower sensitivity and specificity.</p><p><strong>Conclusion: </strong>Model 3, which has four important predictive characteristics, can predict the rapidly deteriorating MCI due to AD in the community.</p>","PeriodicalId":10810,"journal":{"name":"Current Alzheimer research","volume":"19 10","pages":"708-715"},"PeriodicalIF":1.8000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Machine-Based Learning Shifting to Prediction Model of Deteriorative MCI Due to Alzheimer's Disease - A Two-Year Follow-Up Investigation.\",\"authors\":\"Xiaohui Zhao,&nbsp;Haijing Sui,&nbsp;Chengong Yan,&nbsp;Min Zhang,&nbsp;Haihan Song,&nbsp;Xueyuan Liu,&nbsp;Juan Yang\",\"doi\":\"10.2174/1567205020666221019122049\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>The aim of the present work was to investigate the features of the elderly population aged ≥65 yrs and with deteriorative mild cognitive impairment (MCI) due to Alzheimer's disease (AD) to establish a prediction model.</p><p><strong>Methods: </strong>A total of 105 patients aged ≥65 yrs and with MCI were followed up, with a collection of 357 features, which were derived from the demographic characteristics, hematological indicators (serum Aβ1-40, Aβ1-42, P-tau and MCP-1 levels, APOE gene), and multimodal brain Magnetic Resonance Imaging (MRI) imaging indicators of 116 brain regions (ADC, FA and CBF values). Cognitive function was followed up for 2 yrs. Based on the Python platform Anaconda, 105 patients were randomly divided into a training set (70%) and a test set (30%) by analyzing all features through a random forest algorithm, and a prediction model was established for the form of rapidly deteriorating MCI.</p><p><strong>Results: </strong>Of the 105 patients enrolled, 41 deteriorated, and 64 did not come within 2 yrs. Model 1 was established based on demographic characteristics, hematological indicators and multi-modal MRI image features, the accuracy of the training set being 100%, the accuracy of the test set 64%, sensitivity 50%, specificity 67%, and AUC 0.72. Model 2 was based on the first five features (APOE4 gene, FA value of left fusiform gyrus, FA value of left inferior temporal gyrus, FA value of left parahippocampal gyrus, ADC value of right calcarine fissure as surrounding cortex), the accuracy of the training set being 100%, the accuracy of the test set 85%, sensitivity 91%, specificity 80% and AUC 0.96. Model 3 was based on the first four features of Model 1, the accuracy of the training set is 100%, the accuracy of the test set 97%, sensitivity100%, specificity 95% and AUC 0.99. Model 4 was based on the first three characteristics of Model 1, the accuracy of the training set being 100%, the accuracy of the test set 94%, sensitivity 92%, specificity 94% and AUC 0.96. Model 5 was based on the hematological characteristics, the accuracy of the training set is 100%, the accuracy of the test set 91%, sensitivity 100%, specificity 88% and AUC 0.97. The models based on the demographic characteristics, imaging characteristics FA, CBF and ADC values had lower sensitivity and specificity.</p><p><strong>Conclusion: </strong>Model 3, which has four important predictive characteristics, can predict the rapidly deteriorating MCI due to AD in the community.</p>\",\"PeriodicalId\":10810,\"journal\":{\"name\":\"Current Alzheimer research\",\"volume\":\"19 10\",\"pages\":\"708-715\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2022-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Current Alzheimer research\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.2174/1567205020666221019122049\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Current Alzheimer research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2174/1567205020666221019122049","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 1

摘要

目的:探讨≥65岁老年人群阿尔茨海默病(AD)所致退行性轻度认知障碍(MCI)的特征,建立预测模型。方法:对105例年龄≥65岁的MCI患者进行随访,收集人口统计学特征、血清学指标(血清A - β1-40、A - β1-42、P-tau和MCP-1水平、APOE基因)和116个脑区多模态脑磁共振成像(MRI)成像指标(ADC、FA和CBF值)357项特征。认知功能随访2年。基于Python平台Anaconda,通过随机森林算法对各特征进行分析,将105例患者随机分为训练集(70%)和测试集(30%),建立MCI快速恶化形式的预测模型。结果:入组的105例患者中,41例病情恶化,64例2年内未痊愈。模型1根据人口学特征、血液学指标和多模态MRI图像特征建立,训练集准确率100%,测试集准确率64%,灵敏度50%,特异度67%,AUC 0.72。模型2基于前5个特征(APOE4基因、左侧梭状回FA值、左侧颞下回FA值、左侧海马旁回FA值、右侧骨裂为周围皮层ADC值),训练集准确率为100%,测试集准确率为85%,灵敏度91%,特异性80%,AUC为0.96。模型3基于模型1的前四个特征,训练集的准确率为100%,测试集的准确率为97%,灵敏度为100%,特异性为95%,AUC为0.99。模型4基于模型1的前三个特征,训练集的准确率为100%,测试集的准确率为94%,灵敏度为92%,特异性为94%,AUC为0.96。模型5基于血液学特征,训练集准确率为100%,测试集准确率为91%,灵敏度为100%,特异性为88%,AUC为0.97。基于人口统计学特征、影像学特征FA、CBF和ADC值的模型敏感性和特异性较低。结论:模型3具有4个重要的预测特征,可以预测社区中AD导致的MCI快速恶化。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Machine-Based Learning Shifting to Prediction Model of Deteriorative MCI Due to Alzheimer's Disease - A Two-Year Follow-Up Investigation.

Objective: The aim of the present work was to investigate the features of the elderly population aged ≥65 yrs and with deteriorative mild cognitive impairment (MCI) due to Alzheimer's disease (AD) to establish a prediction model.

Methods: A total of 105 patients aged ≥65 yrs and with MCI were followed up, with a collection of 357 features, which were derived from the demographic characteristics, hematological indicators (serum Aβ1-40, Aβ1-42, P-tau and MCP-1 levels, APOE gene), and multimodal brain Magnetic Resonance Imaging (MRI) imaging indicators of 116 brain regions (ADC, FA and CBF values). Cognitive function was followed up for 2 yrs. Based on the Python platform Anaconda, 105 patients were randomly divided into a training set (70%) and a test set (30%) by analyzing all features through a random forest algorithm, and a prediction model was established for the form of rapidly deteriorating MCI.

Results: Of the 105 patients enrolled, 41 deteriorated, and 64 did not come within 2 yrs. Model 1 was established based on demographic characteristics, hematological indicators and multi-modal MRI image features, the accuracy of the training set being 100%, the accuracy of the test set 64%, sensitivity 50%, specificity 67%, and AUC 0.72. Model 2 was based on the first five features (APOE4 gene, FA value of left fusiform gyrus, FA value of left inferior temporal gyrus, FA value of left parahippocampal gyrus, ADC value of right calcarine fissure as surrounding cortex), the accuracy of the training set being 100%, the accuracy of the test set 85%, sensitivity 91%, specificity 80% and AUC 0.96. Model 3 was based on the first four features of Model 1, the accuracy of the training set is 100%, the accuracy of the test set 97%, sensitivity100%, specificity 95% and AUC 0.99. Model 4 was based on the first three characteristics of Model 1, the accuracy of the training set being 100%, the accuracy of the test set 94%, sensitivity 92%, specificity 94% and AUC 0.96. Model 5 was based on the hematological characteristics, the accuracy of the training set is 100%, the accuracy of the test set 91%, sensitivity 100%, specificity 88% and AUC 0.97. The models based on the demographic characteristics, imaging characteristics FA, CBF and ADC values had lower sensitivity and specificity.

Conclusion: Model 3, which has four important predictive characteristics, can predict the rapidly deteriorating MCI due to AD in the community.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Current Alzheimer research
Current Alzheimer research 医学-神经科学
CiteScore
4.00
自引率
4.80%
发文量
64
审稿时长
4-8 weeks
期刊介绍: Current Alzheimer Research publishes peer-reviewed frontier review, research, drug clinical trial studies and letter articles on all areas of Alzheimer’s disease. This multidisciplinary journal will help in understanding the neurobiology, genetics, pathogenesis, and treatment strategies of Alzheimer’s disease. The journal publishes objective reviews written by experts and leaders actively engaged in research using cellular, molecular, and animal models. The journal also covers original articles on recent research in fast emerging areas of molecular diagnostics, brain imaging, drug development and discovery, and clinical aspects of Alzheimer’s disease. Manuscripts are encouraged that relate to the synergistic mechanism of Alzheimer''s disease with other dementia and neurodegenerative disorders. Book reviews, meeting reports and letters-to-the-editor are also published. The journal is essential reading for researchers, educators and physicians with interest in age-related dementia and Alzheimer’s disease. Current Alzheimer Research provides a comprehensive ''bird''s-eye view'' of the current state of Alzheimer''s research for neuroscientists, clinicians, health science planners, granting, caregivers and families of this devastating disease.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信