본문

서브메뉴

Detecting Cognitive Impairment From Language and Speech for Early Screening of Alzheimer's Disease Dementia With Interpretable Transformer-Based Language Models
Detecting Cognitive Impairment From Language and Speech for Early Screening of Alzheimer's...
Detecting Cognitive Impairment From Language and Speech for Early Screening of Alzheimer's Disease Dementia With Interpretable Transformer-Based Language Models

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211150953
ISBN  
9798383163184
DDC  
020
저자명  
Li, Changye.
서명/저자  
Detecting Cognitive Impairment From Language and Speech for Early Screening of Alzheimers Disease Dementia With Interpretable Transformer-Based Language Models
발행사항  
[Sl] : University of Minnesota, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
141 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
주기사항  
Advisor: Pakhomov, Serguei.
학위논문주기  
Thesis (Ph.D.)--University of Minnesota, 2024.
초록/해제  
요약Alzheimer's disease (AD) is a neurodegenerative disorder that affects the use of speech and language and is diffcult to diagnose in its early stages. Neural language models (NLMs) have delivered impressive performance on the task of discriminating between language produced by cognitively healthy individuals, and those with AD. As artificial neural networks (ANNs) grow in complexity, understanding their inner workings becomes increasingly challenging, which is particularly important in healthcare applications. The intrinsic evaluation metrics of autoregressive NLMs (e.g., predicting the next token given the context), such as perplexity (PPL), reflecting a model's "surprise" at novel input, and have been widely used to understand the behavior of NLMs. As an alternative to fitting model parameters directly, this thesis proposes a novel method by which a pre-trained transformer-based NLM, GPT-2, is paired with an artificially degraded version of itself, GPT-D, to compute the ratio between these two models' PPLs on language from cognitively healthy and impaired individuals. This technique approaches state-of-the-art (SOTA) performance on text data from a widely used "Cookie Theft" picture description task, and unlike established alternatives also generalizes well to spontaneous conversations, the degraded models generate text with characteristics known to be associated with AD, demonstrating the induction of dementia-related linguistic anomalies. The novel attention head ablation method employed in this thesis exhibits properties attributed to the concepts of cognitive and brain reserve in human brain studies, which postulate that people with more neurons in the brain and more effcient processing are more resilient to neurodegeneration. The results show that larger GPT-2 models require a disproportionately larger share of attention heads to be masked/ablated to display degradation of similar magnitude to masking in smaller models.To realize their benefits for assessment of mental status, transformer-based NLMs require verbatim transcriptions of speech from patients. While such models have shown promise in detecting cognitive impairment from language samples, the feasibility of deploying such automated tools in large-scale clinical settings depends on the ability to reliably capture and transcribe the speech input. Currently available automatic speech recognition ASR solutions have improved dramatically over the last few years but are still not perfect and can have high error rates on challenging speech, such as speech from audio data with sub-optimal recording quality. One of the key questions for successfully applying ASR technology for clinical applications is whether imperfect transcripts generated by ASR provide sufficient information for downstream tasks to operate at an acceptable level of accuracy. This thesis examines the relationship between the errors produced by several transformer-based ASR systems and their impact on downstream dementia classification. One of the key findings is that ASR errors may provide important features for this downstream classification task, resulting in better performance compared to using manual transcripts.In summary, this thesis is a step toward a better understanding of the relationships between the inner workings of generative NLMs, the language that they produce, and the deleterious effects of dementia on human speech and language characteristics. The probing methods also suggest that the attention mechanism in transformer models may present an analogue to the notions of cognitive and brain reserve and could potentially be used to model certain aspects of the progression of neurodegenerative disorders and aging. Additionally, the results presented in this thesis suggest that the ASR models and the downstream classification models react to acoustic and linguistic dementia manifestations in systematic and mutually synergistic ways, which would have significant implications for use of ASR technology.
일반주제명  
Information science
일반주제명  
Computer science
일반주제명  
Health sciences
일반주제명  
Neurosciences
키워드  
Alzheimer's disease
키워드  
Automatic speech recognition
키워드  
Natural language processing
키워드  
Artificial neural networks
기타저자  
University of Minnesota Health Informatics
기본자료저록  
Dissertations Abstracts International. 85-12B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017160302
■00520250211150953
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798383163184
■035    ▼a(MiAaPQ)AAI30993347
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a020
■1001  ▼aLi,  Changye.
■24510▼aDetecting  Cognitive  Impairment  From  Language  and  Speech  for  Early  Screening  of  Alzheimer's  Disease  Dementia  With  Interpretable  Transformer-Based  Language  Models
■260    ▼a[Sl]▼bUniversity  of  Minnesota▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a141  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-12,  Section:  B.
■500    ▼aAdvisor:  Pakhomov,  Serguei.
■5021  ▼aThesis  (Ph.D.)--University  of  Minnesota,  2024.
■520    ▼aAlzheimer's  disease  (AD)  is  a  neurodegenerative  disorder  that  affects  the  use  of  speech  and  language  and  is  diffcult  to  diagnose  in  its  early  stages.  Neural  language  models  (NLMs)  have  delivered  impressive  performance  on  the  task  of  discriminating  between  language  produced  by  cognitively  healthy  individuals,  and  those  with  AD.  As  artificial  neural  networks  (ANNs)  grow  in  complexity,  understanding  their  inner  workings  becomes  increasingly  challenging,  which  is  particularly  important  in  healthcare  applications.  The  intrinsic  evaluation  metrics  of  autoregressive  NLMs  (e.g.,  predicting  the  next  token  given  the  context),  such  as  perplexity  (PPL),  reflecting  a  model's  "surprise"  at  novel  input,  and  have  been  widely  used  to  understand  the  behavior  of  NLMs.  As  an  alternative  to  fitting  model  parameters  directly,  this  thesis  proposes  a  novel  method  by  which  a  pre-trained  transformer-based  NLM,  GPT-2,  is  paired  with  an  artificially  degraded  version  of  itself,  GPT-D,  to  compute  the  ratio  between  these  two  models'  PPLs  on  language  from  cognitively  healthy  and  impaired  individuals.  This  technique  approaches  state-of-the-art  (SOTA)  performance  on  text  data  from  a  widely  used  "Cookie  Theft"  picture  description  task,  and  unlike  established  alternatives  also  generalizes  well  to  spontaneous  conversations,  the  degraded  models  generate  text  with  characteristics  known  to  be  associated  with  AD,  demonstrating  the  induction  of  dementia-related  linguistic  anomalies.  The  novel  attention  head  ablation  method  employed  in  this  thesis  exhibits  properties  attributed  to  the  concepts  of  cognitive  and  brain  reserve  in  human  brain  studies,  which  postulate  that  people  with  more  neurons  in  the  brain  and  more  effcient  processing  are  more  resilient  to  neurodegeneration.  The  results  show  that  larger  GPT-2  models  require  a  disproportionately  larger  share  of  attention  heads  to  be  masked/ablated  to  display  degradation  of  similar  magnitude  to  masking  in  smaller  models.To  realize  their  benefits  for  assessment  of  mental  status,  transformer-based  NLMs  require  verbatim  transcriptions  of  speech  from  patients.  While  such  models  have  shown  promise  in  detecting  cognitive  impairment  from  language  samples,  the  feasibility  of  deploying  such  automated  tools  in  large-scale  clinical  settings  depends  on  the  ability  to  reliably  capture  and  transcribe  the  speech  input.  Currently  available  automatic  speech  recognition  ASR  solutions  have  improved  dramatically  over  the  last  few  years  but  are  still  not  perfect  and  can  have  high  error  rates  on  challenging  speech,  such  as  speech  from  audio  data  with  sub-optimal  recording  quality.  One  of  the  key  questions  for  successfully  applying  ASR  technology  for  clinical  applications  is  whether  imperfect  transcripts  generated  by  ASR  provide  sufficient  information  for  downstream  tasks  to  operate  at  an  acceptable  level  of  accuracy.  This  thesis  examines  the  relationship  between  the  errors  produced  by  several  transformer-based  ASR  systems  and  their  impact  on  downstream  dementia  classification.  One  of  the  key  findings  is  that  ASR  errors  may  provide  important  features  for  this  downstream  classification  task,  resulting  in  better  performance  compared  to  using  manual  transcripts.In  summary,  this  thesis  is  a  step  toward  a  better  understanding  of  the  relationships  between  the  inner  workings  of  generative  NLMs,  the  language  that  they  produce,  and  the  deleterious  effects  of  dementia  on  human  speech  and  language  characteristics.  The  probing  methods  also  suggest  that  the  attention  mechanism  in  transformer  models  may  present  an  analogue  to  the  notions  of  cognitive  and  brain  reserve  and  could  potentially  be  used  to  model  certain  aspects  of  the  progression  of  neurodegenerative  disorders  and  aging.  Additionally,  the  results  presented  in  this  thesis  suggest  that  the  ASR  models  and  the  downstream  classification  models  react  to  acoustic  and  linguistic  dementia  manifestations  in  systematic  and  mutually  synergistic  ways,  which  would  have  significant  implications  for  use  of  ASR  technology.
■590    ▼aSchool  code:  0130.
■650  4▼aInformation  science
■650  4▼aComputer  science
■650  4▼aHealth  sciences
■650  4▼aNeurosciences
■653    ▼aAlzheimer's  disease
■653    ▼aAutomatic  speech  recognition
■653    ▼aNatural  language  processing
■653    ▼aArtificial  neural  networks
■690    ▼a0723
■690    ▼a0984
■690    ▼a0566
■690    ▼a0317
■71020▼aUniversity  of  Minnesota▼bHealth  Informatics.
■7730  ▼tDissertations  Abstracts  International▼g85-12B.
■790    ▼a0130
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160302▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF13909 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.