1.中山大学外国语学院,广东 广州 510275
2.中山大学航空航天学院,广东 深圳 518107
王欣(1991年生),女;研究方向:应用语言学;E-mail:wangx736@mail.sysu.edu.cn
纸质出版日期:2023-11-25,
网络出版日期:2023-09-21,
收稿日期:2023-07-18,
录用日期:2023-07-30
扫 描 看 全 文
王欣,陈泽森.基于神经网络的多特征轻度认知功能障碍检测模型[J].中山大学学报(自然科学版),2023,62(06):107-115.
WANG Xin,CHEN Zesen.A neural network-based multi-feature detection model for mild cognitive impairment[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2023,62(06):107-115.
王欣,陈泽森.基于神经网络的多特征轻度认知功能障碍检测模型[J].中山大学学报(自然科学版),2023,62(06):107-115. DOI: 10.13471/j.cnki.acta.snus.2023B049.
WANG Xin,CHEN Zesen.A neural network-based multi-feature detection model for mild cognitive impairment[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2023,62(06):107-115. DOI: 10.13471/j.cnki.acta.snus.2023B049.
轻度认知功能障是介于正常衰老和老年痴呆之间的一种中间状态,是老年痴呆诊疗的关键阶段。因此,针对潜在MCI老年人群进行早期检测和干预,有望延缓语言认知障碍及老年痴呆的发生。本文利用患者在语言学表现变化明显的特点,提出了一种基于神经网络的多特征轻度认知障碍检测模型。在提取自然会话中的语言学特征的基础上,融合LDA模型的T-W矩阵与受试者资料等多特征信息,形成TextCNN网络的输入张量,构建基于语言学特征的神经网络检测模型。该模型在DementiaBank数据集上达到了0.93的准确率、1.00的灵敏度、0.8的特异度和0.9的精度,有效提高了利用自然会话对老年语言认知障碍检测的准确率。
Mild cognitive impairment (MCI) is both an intermediate state between normal aging and Alzheimer's disease and the key stage in the diagnosis of Alzheimer's disease. Therefore, early detection and treatment for potential elderly can delay the occurrence of dementia. In this study, a neural network-based multi-feature detection model for mild cognitive impairment was proposed, which exploits the characteristics of patients with obvious changes in linguistic performance. The model is based on extracting the linguistic features in natural speech and integrating the T-W matrix of the LDA model with the subject data and other multi-feature information as the input tensor of the TextCNN network. It achieved an accuracy of 0.93, a sensitivity of 1.00, a specificity of 0.8, and a precision of 0.9 on the DementiaBank dataset, which effectively improved the accuracy of cognitive impairment detection in the elderly by using natural speech.
轻度认知功能障碍自然会话神经网络模型多特征分析会话分析
mild cognitive impairmentnatural speechneural network modelmulti-feature detectionspeech analysis
董瑞,杨雅婷,蒋同海, 2020. 融合多种语言学特征的维吾尔语神经网络命名实体识别[J]. 计算机应用与软件, 37(5):183-188.
鄂海红,张文静,肖思琪,等, 2019. 深度学习实体关系抽取研究综述[J]. 软件学报, 30(6):1793-1818.
黄立鹤,杨晶晶, 2022. 阿尔茨海默病老年人篇章语用障碍指标构建及测定问题[J]. 外语教学,43(2):16-22.
黄立鹤,2022. 老龄化与老年语言学引论[M].上海:上海外语教育出版社.
李妍,周爱红,赵丽娜,等, 2019. 轻度阿尔茨海默病患者自发语言特点研究[J]. 中华神经科杂志, 52(3):177-183.
刘红艳, 2014. 基于语料库的老年性痴呆患者找词困难研究[J]. 解放军外国语学院学报, 37(1):42-52.
刘建鹏,赵俊海,杜慧芳, 2017. 基于语料挖掘的阿尔茨海默症患者话语深层正式度研究[J].解放军外国语学院学报, 40(3):36-44.
冉永平,李欣芳, 2017. 临床语用学视角下语用障碍的交叉研究[J].外国语(上海外国语大学学报),40(2):28-38.
田金洲,王鲁宁,王荫华,等,2019. 适用于中国人群的阿尔茨海默病筛查和诊断框架[J].中华内科杂志,28(2):91-101.
温健,2022. 基于自发语音的认知衰退预测模型的研究与应用[D]. 上海:东华大学.
杨军, 2004. 口语非流利产出研究述评[J].外语教学与研究,36(4):278-284+321.
赵俊海, 2012. 阿尔茨海默症患者话语的系统功能语言学研究[D]. 重庆:西南大学.
ARAUJO N B, BARCA M L, ENGEDA K, et al, 2011. Verbal fluency in Alzheimer’s disease, Parkinson’s disease, and major depression[J]. Clinics, 66(4):623-627.
ASSOCIATION A, 2019. Alzheimer's disease facts and figures[J]. Alzheimer's & Dement, 15(3): 321-387.
BUCKNER R L, 2004. Memory and executive function in aging and AD: Multiple factors that cause decline and reserve factors that compensate[J]. Neuron, 44(1): 195-208.
BUCKS R S , SINGH S , CUERDEN J M ,et al, 2000. Analysis of spontaneous, conversational speech in dementia of Alzheimer type: Evaluation of an objective technique for analysing lexical performance[J].Aphasiology, 14(1):71-91.
CHEN W, XING X, XU X, et al, 2016. SpeechFormer: A hierarchical efficient framework incorporating the characteristics of speech[J]. https://arxiv.org/abs/2203. 03812https://arxiv.org/abs/2203.03812.
CHEN Y, 2015. Convolutional neural network for sentence classification[D]. Waterloo:University of Waterloo.
CROOT K, HODGES J R, XUEREB J, et al, 2000. Phonological and articulatory impairment in alzheimer’s disease: A case series[J]. Brain Lang, 75(2):277-309.
de La FUENTE GARCIA S, RITCHIE C W, LUZ S, 2020. Artificial intelligence, speech and language processing approaches to monitoring Alzheimer's disease: A systematic review[J]. J Alzheimers Dis, 78(4):1547-1574.
DUAN F, HUANG Z, SUN Z, et al, 2020.Topological network analysis of early Alzheimer’s disease based on resting-state EEG[J].IEEE Trans Neural Syst Rehabil Eng, 28(10):2164-2172.
FRASER K C, MELTZER J A, RUDZICZ F, 2016. Linguistic features identify Alzheimer’s disease in narrative speech[J]. J Alzheimers Dis, 49(2): 407-422.
KÖNIG A, SATT A, SORIN A, et al, 2015. Automatic speech analysis for the assessment of patients with predementia and Alzheimer's disease[J]. Alzheimer's & Dement: Diagn, Assess Dis Monit, 1(1): 112-124.
LANZI A M, SAYLOR A K, FROMM D, et al, 2023. DementiaBank: Theoretical rationale, protocol, and illustrative analyses[J]. Am J Speech-Lang Pat, 32(2): 426-438.
PRINCE M J, WIMO A, GUERCHET M, et al, 2015. World Alzheimer report 2015-the global impact of dementia: An analysis of prevalence, incidence, cost and trends[J/OL].https://www.alzint.org/u/WorldAlzheimerReport2015.pdfhttps://www.alzint.org/u/WorldAlzheimerReport2015.pdf.
SHI J, ZHENG X, LI Y, et al, 2017. Multimodal neuroimaging feature learning with multimodal stacked deep polynomial networks for diagnosis of Alzheimer's disease[J]. IEEE J Biomed Health Inform, 22(1): 173-183.
TSANTALI E, ECONOMIDIS D, TSOLAKI M, 2013. Could language deficits really differentiate mild cognitive impairment (MCI) from mild Alzheimer’s disease[J]. Arch Gerontol Geriatr, 57(3):263-270.
ZHANG L, FAN Y, JIANG J, et al, 2022. Adolescent depression detection model based on multimodal data of interview audio and text[J]. Int Journal Neural Syst, 32(11):2250045.
0
浏览量
12
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构