본문

서브메뉴

Evaluating Multi-Modal Data Fusion Approaches for Predictive Clinical Models Using Multiple Medical Data Domains
Evaluating Multi-Modal Data Fusion Approaches for Predictive Clinical Models Using Multipl...
Evaluating Multi-Modal Data Fusion Approaches for Predictive Clinical Models Using Multiple Medical Data Domains

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202104702
ISBN  
9798288832888
DDC  
610
저자명  
Alipour, Ehsan.
서명/저자  
Evaluating Multi-Modal Data Fusion Approaches for Predictive Clinical Models Using Multiple Medical Data Domains
발행사항  
[Sl] : University of Washington, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
157 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Tarczy-Hornoch, Peter;Hadlock, Jennifer.
학위논문주기  
Thesis (Ph.D.)--University of Washington, 2025.
초록/해제  
요약Disease outcome prediction is a central research focus in biomedical informatics, as it facilitates precision health related interventions and scientific discovery by enabling digital clinical trials and multiple other benefits. Multimodal deep learning models have emerged as powerful tools in biomedical research, offering the ability to integrate diverse data sources such as clinical records, multi-omics data, imaging, survey responses, and wearable data to enhance predictive accuracy and deepen understanding of medical phenomena. Central to multimodal modeling is the process of data fusion, where information from different modalities is integrated into a unified model. Three primary fusion strategies exist in deep learning: early fusion (feature-level), intermediate fusion and late fusion (decision-level). While widely adopted in other domains, their comparative performance and implementation considerations remain underexplored in biomedical applications, where data heterogeneity, missingness, and varying dimensionality present additional challenges.This dissertation aims to evaluate the implications of data fusion strategies for developing multimodal predictive models in medicine. Across three distinct aims, I assess the impact of early, intermediate, and late fusion techniques on predictive performance, implementation complexity, and generalizability using diverse combinations of data types, outcomes, and modeling strategies. These studies span multiple datasets and outcome types (binary categorial variables vs continuous ratio variables) providing a broad view of fusion strategy utility in real-world biomedical settings.In Aim 1-Evaluation and comparison of early, intermediate, and late fusion techniques for combining exposures, clinical and genomics data for disease risk prediction task using All of Us: Risk of CKD in patients with type 2 diabetes-I evaluated and compared early, intermediate, and late fusion strategies for integrating longitudinal EHR, genomic, and survey data to predict chronic kidney disease (CKD) progression in patients with type 2 diabetes using a novel transformer-based multimodal architecture. Using data from the NIH's All of Us initiative, I trained models on a cohort of approximately 40,000 patients. While the best performing unimodal model achieved a baseline performance with an AUROC of 0.73 (0.71 - 0.75), the inclusion of multimodal data offered only marginal improvement with an AUROC of 0.74 (0.72 - 0.76), with the benefit limited to the early fusion approach and lacking statistical significance. This aim highlighted the challenges of integrating multimodal data with different dimensions using transformer models and emphasized the role of modality-specific relative predictive strength.In Aim 2-Development and assessment of the incremental value of combining a deep convolutional neural network feature extractor on imaging data and clinical data on a binary prediction task: Predict post-surgical margin status in soft tissue sarcoma-I extended the fusion analysis to imaging data by combining a convolutional neural network (CNN) trained on longitudinal cross-sectional imaging with a shallow neural network trained on clinical and pathology variables to predict post-surgical margin status in patients with soft tissue sarcoma (n=202). Here, the intermediate fusion strategy significantly outperformed other approaches, achieving an AUROC of 0.80 (0.66-0.95), suggesting that cross-modal interactions between histologic features and imaging embeddings may be best captured through intermediate fusion. This result demonstrated the potential value of intermediate fusion when complementary signals exist across modalities.In Aim 3-Evaluation and comparison of early, intermediate, and late fusion techniques for combining imaging and clinical data on a regression prediction task: Estimation of CT-based body composition metrics from chest radiographs-I explored fusion strategies for estimating continuous CT-derived body composition metrics (e.g., visceral, and subcutaneous fat volumes) using only chest radiographs and clinical variables in a dataset of 1,088 patients. A multitask multimodal model was developed and evaluated across early, intermediate, and late fusion strategies. Late fusion consistently delivered the best performance across most body composition metrics, closely followed by intermediate fusion. These results suggest that when individual modalities offer high independent predictive power, decision-level integration may be optimal for regression tasks.Collectively, these aims provide a broad evaluation of data fusion strategies in multimodal biomedical modeling, highlighting their strengths, limitations, and practical considerations. Findings suggest that no single fusion strategy universally outperforms the others; rather, optimal fusion depends on data characteristics, model architecture, and task-specific objectives. This dissertation lays the groundwork for future research aimed at developing adaptive fusion strategies tailored to the complexities of real-world biomedical data.
일반주제명  
Medicine
일반주제명  
Computer science
일반주제명  
Bioinformatics
키워드  
Data fusion strategies
키워드  
Deep learning
키워드  
Informatics
키워드  
Medical predictive models
키워드  
Multitask multimodal model
기타저자  
University of Washington Biomedical Informatics and Medical Education
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017358433
■00520260202104702
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288832888
■035    ▼a(MiAaPQ)AAI32116252
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a610
■1001  ▼aAlipour,  Ehsan.
■24510▼aEvaluating  Multi-Modal  Data  Fusion  Approaches  for  Predictive  Clinical  Models  Using  Multiple  Medical  Data  Domains
■260    ▼a[Sl]▼bUniversity  of  Washington▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a157  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Tarczy-Hornoch,  Peter;Hadlock,  Jennifer.
■5021  ▼aThesis  (Ph.D.)--University  of  Washington,  2025.
■520    ▼aDisease  outcome  prediction  is  a  central  research  focus  in  biomedical  informatics,  as  it  facilitates  precision  health  related  interventions  and  scientific  discovery  by  enabling  digital  clinical  trials  and  multiple  other  benefits.  Multimodal  deep  learning  models  have  emerged  as  powerful  tools  in  biomedical  research,  offering  the  ability  to  integrate  diverse  data  sources  such  as  clinical  records,  multi-omics  data,  imaging,  survey  responses,  and  wearable  data  to  enhance  predictive  accuracy  and  deepen  understanding  of  medical  phenomena.  Central  to  multimodal  modeling  is  the  process  of  data  fusion,  where  information  from  different  modalities  is  integrated  into  a  unified  model.  Three  primary  fusion  strategies  exist  in  deep  learning:  early  fusion  (feature-level),  intermediate  fusion  and  late  fusion  (decision-level).  While  widely  adopted  in  other  domains,  their  comparative  performance  and  implementation  considerations  remain  underexplored  in  biomedical  applications,  where  data  heterogeneity,  missingness,  and  varying  dimensionality  present  additional  challenges.This  dissertation  aims  to  evaluate  the  implications  of  data  fusion  strategies  for  developing  multimodal  predictive  models  in  medicine.  Across  three  distinct  aims,  I  assess  the  impact  of  early,  intermediate,  and  late  fusion  techniques  on  predictive  performance,  implementation  complexity,  and  generalizability  using  diverse  combinations  of  data  types,  outcomes,  and  modeling  strategies.  These  studies  span  multiple  datasets  and  outcome  types  (binary  categorial  variables  vs  continuous  ratio  variables)  providing  a  broad  view  of  fusion  strategy  utility  in  real-world  biomedical  settings.In  Aim  1-Evaluation  and  comparison  of  early,  intermediate,  and  late  fusion  techniques  for  combining  exposures,  clinical  and  genomics  data  for  disease  risk  prediction  task  using  All  of  Us:  Risk  of  CKD  in  patients  with  type  2  diabetes-I  evaluated  and  compared  early,  intermediate,  and  late  fusion  strategies  for  integrating  longitudinal  EHR,  genomic,  and  survey  data  to  predict  chronic  kidney  disease  (CKD)  progression  in  patients  with  type  2  diabetes  using  a  novel  transformer-based  multimodal  architecture.  Using  data  from  the  NIH's  All  of  Us  initiative,  I  trained  models  on  a  cohort  of  approximately  40,000  patients.  While  the  best  performing  unimodal  model  achieved  a  baseline  performance  with  an  AUROC  of  0.73  (0.71  -  0.75),  the  inclusion  of  multimodal  data  offered  only  marginal  improvement  with  an  AUROC  of  0.74  (0.72  -  0.76),  with  the  benefit  limited  to  the  early  fusion  approach  and  lacking  statistical  significance.  This  aim  highlighted  the  challenges  of  integrating  multimodal  data  with  different  dimensions  using  transformer  models  and  emphasized  the  role  of  modality-specific  relative  predictive  strength.In  Aim  2-Development  and  assessment  of  the  incremental  value  of  combining  a  deep  convolutional  neural  network  feature  extractor  on  imaging  data  and  clinical  data  on  a  binary  prediction  task:  Predict  post-surgical  margin  status  in  soft  tissue  sarcoma-I  extended  the  fusion  analysis  to  imaging  data  by  combining  a  convolutional  neural  network  (CNN)  trained  on  longitudinal  cross-sectional  imaging  with  a  shallow  neural  network  trained  on  clinical  and  pathology  variables  to  predict  post-surgical  margin  status  in  patients  with  soft  tissue  sarcoma  (n=202).  Here,  the  intermediate  fusion  strategy  significantly  outperformed  other  approaches,  achieving  an  AUROC  of  0.80  (0.66-0.95),  suggesting  that  cross-modal  interactions  between  histologic  features  and  imaging  embeddings  may  be  best  captured  through  intermediate  fusion.  This  result  demonstrated  the  potential  value  of  intermediate  fusion  when  complementary  signals  exist  across  modalities.In  Aim  3-Evaluation  and  comparison  of  early,  intermediate,  and  late  fusion  techniques  for  combining  imaging  and  clinical  data  on  a  regression  prediction  task:  Estimation  of  CT-based  body  composition  metrics  from  chest  radiographs-I  explored  fusion  strategies  for  estimating  continuous  CT-derived  body  composition  metrics  (e.g.,  visceral,  and  subcutaneous  fat  volumes)  using  only  chest  radiographs  and  clinical  variables  in  a  dataset  of  1,088  patients.  A  multitask  multimodal  model  was  developed  and  evaluated  across  early,  intermediate,  and  late  fusion  strategies.  Late  fusion  consistently  delivered  the  best  performance  across  most  body  composition  metrics,  closely  followed  by  intermediate  fusion.  These  results  suggest  that  when  individual  modalities  offer  high  independent  predictive  power,  decision-level  integration  may  be  optimal  for  regression  tasks.Collectively,  these  aims  provide  a  broad  evaluation  of  data  fusion  strategies  in  multimodal  biomedical  modeling,  highlighting  their  strengths,  limitations,  and  practical  considerations.  Findings  suggest  that  no  single  fusion  strategy  universally  outperforms  the  others;  rather,  optimal  fusion  depends  on  data  characteristics,  model  architecture,  and  task-specific  objectives.  This  dissertation  lays  the  groundwork  for  future  research  aimed  at  developing  adaptive  fusion  strategies  tailored  to  the  complexities  of  real-world  biomedical  data.
■590    ▼aSchool  code:  0250.
■650  4▼aMedicine
■650  4▼aComputer  science
■650  4▼aBioinformatics
■653    ▼aData  fusion  strategies
■653    ▼aDeep  learning
■653    ▼aInformatics
■653    ▼aMedical  predictive  models
■653    ▼aMultitask  multimodal  model
■690    ▼a0564
■690    ▼a0984
■690    ▼a0715
■71020▼aUniversity  of  Washington▼bBiomedical  Informatics  and  Medical  Education.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0250
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358433▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF15820 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.