Deep-learning analysis of speech using mel-spectrograms for the assessment of mild cognitive impairment and Alzheimer's disease

认知障碍 听力学 二元分类 认知 诊断准确性 人工智能 特征(语言学) 计算机科学 学习迁移 曲线下面积 语音识别 考试(生物学) 接收机工作特性 认知测验 疾病 人工神经网络 模式识别(心理学) 心理学 机器学习 灵敏度(控制系统) 医学 深度学习 曲线下面积 认知训练
作者
Yun Ho Choi,Hyung-Jun Kim,Suhun Hong,Chaneun Baek,Bohyun Wang,YongSoo Shim,Yun Jeong Hong,Seonjeong Byun,In‐Uk Song,Seunghee Na,Wang-Yeon Won,S.S. Park,Seon Young Ryu,Changtae Hahn,Hae‐Eun Shin,A-Hyun Cho,Eun Ye Lim,Hyun Kook Lim,Dong Woo Kang,Hee-Jin Kim
出处
期刊:Journal of Alzheimer's Disease [IOS Press]
卷期号:109 (2): 928-939 被引量:3
标识
DOI:10.1177/13872877251401202
摘要

BackgroundSpeech abnormalities are recognized as early indicators of Alzheimer's disease (AD) and mild cognitive impairment (MCI).ObjectiveTo determine whether deep-learning models trained on mel-spectrograms of brief speech tasks can (i) discriminate individuals with MCI and AD from cognitively normal controls (NC) and (ii) estimate cognitive status with clinically useful accuracy.MethodsSpeech from 594 participants (185 NC, 231 MCI, 178 AD) was recorded through a mobile application that included 11 cognitive-linguistic tasks. Audio was converted into mel-spectrogram images and processed using a VGG16-based deep-learning model with transfer learning and fine-tuning of block 5. Task-specific feature vectors were extracted, concatenated, and used to train a deep neural network. The dataset was split into training, validation, and test sets (3:1:1), and five-split cross-validation was performed.ResultsThe model demonstrated an overall accuracy of 72.4% in classifying NC from the abnormal group (MCI and AD), with sensitivity and specificity of 72.5% and 72.2%, respectively, a balanced accuracy of 72.4%, and an AUC of 0.997. In binary classifications, the model achieved 82.9% accuracy (balanced accuracy 82.9%, AUC 0.992) for NC versus AD, 70.7% accuracy (balanced accuracy 70.3%, AUC 0.956) for NC versus MCI, and 77.5% accuracy (balanced accuracy 78.9%, AUC 0.889) for MCI versus AD. Tasks such as serial subtraction, storytelling, and picture description contributed most to classification performance, indicating their effectiveness in capturing cognitive deficits.ConclusionsMel-spectrogram-based deep-learning analysis of speech shows promise as a rapid, non-invasive, and language-independent screening tool for early cognitive impairment, with potential advantages over traditional assessments such as the Mini-Mental State Examination.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
bohe发布了新的文献求助10
1秒前
冬至完成签到 ,获得积分10
2秒前
2秒前
xirongyang完成签到,获得积分10
2秒前
充电宝的应助被玛卡采纳,获得10
2秒前
勿忘发布了新的文献求助10
2秒前
瀚子完成签到,获得积分10
3秒前
无花果的应助被芋泥啵啵采纳,获得10
3秒前
gouerde完成签到,获得积分10
3秒前
哎呀发布了新的文献求助10
3秒前
大模型的应助被HouMeng采纳,获得10
4秒前
4秒前
5秒前
5秒前
朋友发布了新的文献求助10
5秒前
6秒前
ZCTMWY发布了新的文献求助10
6秒前
星辰大海的应助被年年采纳,获得10
7秒前
nuoyefenfei发布了新的文献求助10
7秒前
7秒前
秋风的应助被徐世业采纳,获得20
8秒前
田様的应助被gouerde采纳,获得10
9秒前
369ninja发布了新的文献求助10
9秒前
thesky发布了新的文献求助10
10秒前
健忘兔子发布了新的文献求助10
10秒前
11秒前
传奇3的应助被Lu采纳,获得10
13秒前
jiawei1026完成签到,获得积分10
13秒前
初景发布了新的文献求助10
15秒前
无敌干扰素完成签到,获得积分10
15秒前
bkagyin的应助被嘎嘣脆采纳,获得10
16秒前
余香的应助被勤奋的翠绿采纳,获得10
17秒前
月见发布了新的文献求助10
17秒前
17秒前
霸气小松鼠关注了科研通微信公众号
17秒前
17秒前
123456789完成签到,获得积分10
18秒前
小马甲的应助被机智毛豆采纳,获得10
18秒前
FashionBoy的应助被psybrain9527采纳,获得10
19秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8184240
求助须知:如何正确求助?哪些是违规求助? 9573297
关于积分的说明 21830585
捐赠科研通 7781300
什么是DOI,文献DOI怎么找? 3434285
关于科研通互助平台的介绍 2558389
邀请新用户注册赠送积分活动 2480814