본문

서브메뉴

Improving High-Stakes Decision Making with Statistical and Machine Learning Methods
Improving High-Stakes Decision Making with Statistical and Machine Learning Methods
Improving High-Stakes Decision Making with Statistical and Machine Learning Methods

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211153055
ISBN  
9798346389378
DDC  
362.1
저자명  
Nguyen, Minh Chau Thanh.
서명/저자  
Improving High-Stakes Decision Making with Statistical and Machine Learning Methods
발행사항  
[Sl] : Stanford University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
114 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
주기사항  
Advisor: Baiocchi, Mike;Chen, Jonathan.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2024.
초록/해제  
요약Over the past twenty years, emergency department (ED) visits have increased about twice as fast as population growth, and each year, roughly two million ED visits resulted in Intensive Care Unit (ICU) admissions. Everyday, physicians triage patients to determine their acuity levels, the levels of care they need when being admitted to the hospital.These decisions largely depend on human judgment in a high-stakes environment with poor evidence, limited information, and intensive-time pressures. The difficulty of triaging coupled with inherent biases in decision-making highlights the need and opportunity for computer-aided clinical decision support, leveraging electronic health records (EHRs) to manage difficult triage decisions that otherwise place undue pressure on decision-makers with potentially dire consequences.The goal of my research is to develop a framework to support clinical decision making in high-stakes environments with a data-driven approach using statistical and machine learning methods. How can we help physicians to better prioritize patients and decide initial treatments in hospitals?First, I developed machine learning models for initial risk assessments. One model focuses on a specific issue of initial insulin dosing for patients admitted with high blood glucose, whether a patient needs low or higher insulin dose, and how many units, to guide initial interventions. Another model predicts general patient's risk for initial ICU admission.Second, I proposed an inductive and iterative framework for improving model development and assessment, named thick data analytics. Thick data analytics utilizes both quantitative and qualitative approach where experts review discordance cases from related prediction models (e.g. a patient admission with risks predicted at different times within the first 24 hours of admission). The goal is to understand the discordance, improve prediction, and reduce preventable transfers within a short time frame. Thick analytics facilitates model redesign to be more trustworthy in aiding triage.Lastly, I will discuss tie-breaker designs for a pragmatic clinical trial where patients with similar risks could be randomized for admission to ICUs vs non-ICUs. We aim to evaluate the effectiveness of interventions such as ICU admission on patient's health outcomes such as mortality and length of stay. When allowing overriding in such experiments, randomization is an encouragement, which is a form of instrumental variables. Our work will help understand medical decision biases to improve triage process for better patient outcomes.
일반주제명  
Health care access
일반주제명  
Patients
일반주제명  
Emergency medical care
일반주제명  
Electronic health records
일반주제명  
Success
일반주제명  
Clinical decision making
일반주제명  
Design
일반주제명  
Insulin
일반주제명  
Intensive care
일반주제명  
Hospitalization
일반주제명  
Clinical outcomes
일반주제명  
Drug dosages
일반주제명  
Health sciences
일반주제명  
Information science
일반주제명  
Pharmaceutical sciences
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 86-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164849
■00520250211153055
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798346389378
■035    ▼a(MiAaPQ)AAI31643381
■035    ▼a(MiAaPQ)Stanfordsz697sp0293
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a362.1
■1001  ▼aNguyen,  Minh  Chau  Thanh.
■24510▼aImproving  High-Stakes  Decision  Making  with  Statistical  and  Machine  Learning  Methods
■260    ▼a[Sl]▼bStanford  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a114  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-05,  Section:  B.
■500    ▼aAdvisor:  Baiocchi,  Mike;Chen,  Jonathan.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2024.
■520    ▼aOver  the  past  twenty  years,  emergency  department  (ED)  visits  have  increased  about  twice  as  fast  as  population  growth,  and  each  year,  roughly  two  million  ED  visits  resulted  in  Intensive  Care  Unit  (ICU)  admissions.  Everyday,  physicians  triage  patients  to  determine  their  acuity  levels,  the  levels  of  care  they  need  when  being  admitted  to  the  hospital.These  decisions  largely  depend  on  human  judgment  in  a  high-stakes  environment  with  poor  evidence,  limited  information,  and  intensive-time  pressures.  The  difficulty  of  triaging  coupled  with  inherent  biases  in  decision-making  highlights  the  need  and  opportunity  for  computer-aided  clinical  decision  support,  leveraging  electronic  health  records  (EHRs)  to  manage  difficult  triage  decisions  that  otherwise  place  undue  pressure  on  decision-makers  with  potentially  dire  consequences.The  goal  of  my  research  is  to  develop  a  framework  to  support  clinical  decision  making  in  high-stakes  environments  with  a  data-driven  approach  using  statistical  and  machine  learning  methods.  How  can  we  help  physicians  to  better  prioritize  patients  and  decide  initial  treatments  in  hospitals?First,  I  developed  machine  learning  models  for  initial  risk  assessments.  One  model  focuses  on  a  specific  issue  of  initial  insulin  dosing  for  patients  admitted  with  high  blood  glucose,  whether  a  patient  needs  low  or  higher  insulin  dose,  and  how  many  units,  to  guide  initial  interventions.  Another  model  predicts  general  patient's  risk  for  initial  ICU  admission.Second,  I  proposed  an  inductive  and  iterative  framework  for  improving  model  development  and  assessment,  named  thick  data  analytics.  Thick  data  analytics  utilizes  both  quantitative  and  qualitative  approach  where  experts  review  discordance  cases  from  related  prediction  models  (e.g.  a  patient  admission  with  risks  predicted  at  different  times  within  the  first  24  hours  of  admission).  The  goal  is  to  understand  the  discordance,  improve  prediction,  and  reduce  preventable  transfers  within  a  short  time  frame.  Thick  analytics  facilitates  model  redesign  to  be  more  trustworthy  in  aiding  triage.Lastly,  I  will  discuss  tie-breaker  designs  for  a  pragmatic  clinical  trial  where  patients  with  similar  risks  could  be  randomized  for  admission  to  ICUs  vs  non-ICUs.  We  aim  to  evaluate  the  effectiveness  of  interventions  such  as  ICU  admission  on  patient's  health  outcomes  such  as  mortality  and  length  of  stay.  When  allowing  overriding  in  such  experiments,  randomization  is  an  encouragement,  which  is  a  form  of  instrumental  variables.  Our  work  will  help  understand  medical  decision  biases  to  improve  triage  process  for  better  patient  outcomes.
■590    ▼aSchool  code:  0212.
■650  4▼aHealth  care  access
■650  4▼aPatients
■650  4▼aEmergency  medical  care
■650  4▼aElectronic  health  records
■650  4▼aSuccess
■650  4▼aClinical  decision  making
■650  4▼aDesign
■650  4▼aInsulin
■650  4▼aIntensive  care
■650  4▼aHospitalization
■650  4▼aClinical  outcomes
■650  4▼aDrug  dosages
■650  4▼aHealth  sciences
■650  4▼aInformation  science
■650  4▼aPharmaceutical  sciences
■690    ▼a0389
■690    ▼a0800
■690    ▼a0769
■690    ▼a0566
■690    ▼a0723
■690    ▼a0572
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g86-05B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164849▼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
    TF12129 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.