본문

서브메뉴

Towards Scalable and Stable Machine Learning in Clinical Contexts: Addressing Computational Efficiency and Dataset Shift
Towards Scalable and Stable Machine Learning in Clinical Contexts: Addressing Computationa...
Towards Scalable and Stable Machine Learning in Clinical Contexts: Addressing Computational Efficiency and Dataset Shift

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105218
ISBN  
9798291565995
DDC  
004
저자명  
Krishnamoorthy, Meera.
서명/저자  
Towards Scalable and Stable Machine Learning in Clinical Contexts: Addressing Computational Efficiency and Dataset Shift
발행사항  
[Sl] : University of Michigan, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
183 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
주기사항  
Advisor: Wiens, Jenna.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2025.
초록/해제  
요약Clinical machine learning (ML) models have the potential to improve patient outcomes, but realizing this potential requires models that are both computationally efficient and robust to dataset shift. In terms of computational efficiency, simpler models that are memory and storage efficient can help increase the probability of adoption and the feasibility of running models at the bedside in health systems, which are often IT-resource constrained. Robustness to dataset shift ensures long-term model reliability since resources for model retraining are often unavailable. Yet, many existing clinical ML models fail on both fronts. This dissertation addresses these challenges by proposing methods that improve models' (i) computational efficiency and (ii) performance under dataset shift.To improve computational efficiency, we explore two domains. First, in genomic sequence classification, we show that standard approaches are inefficient because they rely on large reference databases at inference time. We introduce an ML-based method that removes this dependency, enabling accurate and memory-efficient classification. Second, we reduce unnecessary model complexity in multiple instance learning (MIL) for large-scale medical image classification. While transformers outperform simpler MIL approaches on tasks where relevant image regions are spatially aligned (e.g., detecting cardiac conditions), they are more computationally complex. We find their advantage stems from their inclusion of positional information. Based on this insight, we propose a positional encoding wrapper that boosts the accuracy of standard MIL models, without adding excessive computational overhead, enabling accurate and efficient image classification.To improve robustness to dataset shift, we examine two settings. The first involves developing models in the presence of unstable correlations-transient associations between features and outcomes that appear in training data but fail to generalize over time (e.g., due to changes in clinical practice). We show that standard model selection strategies, which average model performance across random or temporal splits, mask reliance on unstable correlations. In light of this shortcoming, we propose a new model selection approach that yields models with more stable performance over time. The second setting considers predicting the time to a medical event (e.g., spontaneous labor) when there is dataset shift due to changes in an individual's probability of being censored (e.g., undergoing a c-section) over time. This can lead to limited uncensored support during training compared to testing. Standard survival analysis methods often treat censoring times as lower bounds, causing them to overestimate event times for individuals resembling censored training data in this setting. We propose a method that identifies individuals likely censored close to their true event time and uses them as supervision during training, improving predictions for censored-like test cases without compromising accuracy on uncensored ones.Together, these contributions support the development of clinical ML models that are both efficient and robust. These contributions aim to support the development of models that are easier to integrate into clinical workflows and more reliable in real-world healthcare settings.
일반주제명  
Computer science
일반주제명  
Computer engineering
키워드  
Machine learning
키워드  
Multiple instance learning
키워드  
Computational efficiency
기타저자  
University of Michigan Computer Science & Engineering
기본자료저록  
Dissertations Abstracts International. 87-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359814
■00520260202105218
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798291565995
■035    ▼a(MiAaPQ)AAI32271784
■035    ▼a(MiAaPQ)umichrackham006398
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aKrishnamoorthy,  Meera.
■24510▼aTowards  Scalable  and  Stable  Machine  Learning  in  Clinical  Contexts:  Addressing  Computational  Efficiency  and  Dataset  Shift
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a183  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-03,  Section:  B.
■500    ▼aAdvisor:  Wiens,  Jenna.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2025.
■520    ▼aClinical  machine  learning  (ML)  models  have  the  potential  to  improve  patient  outcomes,  but  realizing  this  potential  requires  models  that  are  both  computationally  efficient  and  robust  to  dataset  shift.  In  terms  of  computational  efficiency,  simpler  models  that  are  memory  and  storage  efficient  can  help  increase  the  probability  of  adoption  and  the  feasibility  of  running  models  at  the  bedside  in  health  systems,  which  are  often  IT-resource  constrained.  Robustness  to  dataset  shift  ensures  long-term  model  reliability  since  resources  for  model  retraining  are  often  unavailable.  Yet,  many  existing  clinical  ML  models  fail  on  both  fronts.  This  dissertation  addresses  these  challenges  by  proposing  methods  that  improve  models'  (i)  computational  efficiency  and  (ii)  performance  under  dataset  shift.To  improve  computational  efficiency,  we  explore  two  domains.  First,  in  genomic  sequence  classification,  we  show  that  standard  approaches  are  inefficient  because  they  rely  on  large  reference  databases  at  inference  time.  We  introduce  an  ML-based  method  that  removes  this  dependency,  enabling  accurate  and  memory-efficient  classification.  Second,  we  reduce  unnecessary  model  complexity  in  multiple  instance  learning  (MIL)  for  large-scale  medical  image  classification.  While  transformers  outperform  simpler  MIL  approaches  on  tasks  where  relevant  image  regions  are  spatially  aligned  (e.g.,  detecting  cardiac  conditions),  they  are  more  computationally  complex.  We  find  their  advantage  stems  from  their  inclusion  of  positional  information.  Based  on  this  insight,  we  propose  a  positional  encoding  wrapper  that  boosts  the  accuracy  of  standard  MIL  models,  without  adding  excessive  computational  overhead,  enabling  accurate  and  efficient  image  classification.To  improve  robustness  to  dataset  shift,  we  examine  two  settings.  The  first  involves  developing  models  in  the  presence  of  unstable  correlations-transient  associations  between  features  and  outcomes  that  appear  in  training  data  but  fail  to  generalize  over  time  (e.g.,  due  to  changes  in  clinical  practice).  We  show  that  standard  model  selection  strategies,  which  average  model  performance  across  random  or  temporal  splits,  mask  reliance  on  unstable  correlations.  In  light  of  this  shortcoming,  we  propose  a  new  model  selection  approach  that  yields  models  with  more  stable  performance  over  time.  The  second  setting  considers  predicting  the  time  to  a  medical  event  (e.g.,  spontaneous  labor)  when  there  is  dataset  shift  due  to  changes  in  an  individual's  probability  of  being  censored  (e.g.,  undergoing  a  c-section)  over  time.  This  can  lead  to  limited  uncensored  support  during  training  compared  to  testing.  Standard  survival  analysis  methods  often  treat  censoring  times  as  lower  bounds,  causing  them  to  overestimate  event  times  for  individuals  resembling  censored  training  data  in  this  setting.  We  propose  a  method  that  identifies  individuals  likely  censored  close  to  their  true  event  time  and  uses  them  as  supervision  during  training,  improving  predictions  for  censored-like  test  cases  without  compromising  accuracy  on  uncensored  ones.Together,  these  contributions  support  the  development  of  clinical  ML  models  that  are  both  efficient  and  robust.  These  contributions  aim  to  support  the  development  of  models  that  are  easier  to  integrate  into  clinical  workflows  and  more  reliable  in  real-world  healthcare  settings.
■590    ▼aSchool  code:  0127.
■650  4▼aComputer  science
■650  4▼aComputer  engineering
■653    ▼aMachine  learning
■653    ▼aMultiple  instance  learning
■653    ▼aComputational  efficiency
■690    ▼a0984
■690    ▼a0464
■690    ▼a0800
■71020▼aUniversity  of  Michigan▼bComputer  Science  &  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g87-03B.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359814▼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
    TF17897 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.