arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.01690cs.CLcs.LG
收藏

基于信息损失的语言学轻度认知障碍检测

Linguistic-Based Mild Cognitive Impairment Detection Using Informative Loss

Ritchie School of Engineering and Computer Science(工程与计算机科学里奇学院);DreamFace Technologies LLC(DreamFace科技有限责任公司);Massachusetts General Hospital(麻省总医院);Prince Sattam Bin Abdulaziz University(萨塔姆·本·阿卜杜勒阿齐兹王子大学)

Ali Pourramezan Fard, Mohammad H. Mahoor, Muath Alsuhaibani, Hiroko H. Dodgec

AI总结:

本文提出基于NLP和Transformer的框架,通过InfoLoss损失函数分析视频访谈转录文本,以84.75%的AUC区分老年人轻度认知障碍与正常认知。

摘要:

本文提出了一种利用自然语言处理(NLP)技术的深度学习方法,用于区分老年人的轻度认知障碍(MCI)和正常认知(NC)状况。我们提出了一个框架,分析从I-CONECT研究项目中收集的视频访谈生成的转录文本,该项目是一项旨在通过视频聊天改善认知功能的随机对照试验。我们提出的NLP框架由两个基于Transformer的模块组成,即句子嵌入(SE)和句子交叉注意力(SCA)。首先,SE模块捕获每个句子内单词之间的上下文关系。随后,SCA模块从一系列句子中提取时间特征。然后,多层感知器(MLP)使用该特征将受试者分类为MCI或NC。为了构建稳健的模型,我们提出了一种新颖的损失函数,称为InfoLoss,该函数通过观察每个句子序列来考虑熵的减少,最终提高分类准确性。我们使用I-CONNECT数据集进行的全面模型评估结果表明,我们的框架能够以84.75%的平均曲线下面积区分MCI和NC。

英文摘要:

This paper presents a deep learning method using Natural Language Processing (NLP) techniques, to distinguish between Mild Cognitive Impairment (MCI) and Normal Cognitive (NC) conditions in older adults. We propose a framework that analyzes transcripts generated from video interviews collected within the I-CONECT study project, a randomized controlled trial aimed at improving cognitive functions through video chats. Our proposed NLP framework consists of two Transformer-based modules, namely Sentence Embedding (SE) and Sentence Cross Attention (SCA). First, the SE module captures contextual relationships between words within each sentence. Subsequently, the SCA module extracts temporal features from a sequence of sentences. This feature is then used by a Multi-Layer Perceptron (MLP) for the classification of subjects into MCI or NC. To build a robust model, we propose a novel loss function, called InfoLoss, that considers the reduction in entropy by observing each sequence of sentences to ultimately enhance the classification accuracy. The results of our comprehensive model evaluation using the I-CONECT dataset show that our framework can distinguish between MCI and NC with an average area under the curve of 84.75%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑