본문

서브메뉴

Detecting Risky Alcohol Use With Natural Language Processing and Computable Phenotypes in Clinical Records
Detecting Risky Alcohol Use With Natural Language Processing and Computable Phenotypes in ...
Detecting Risky Alcohol Use With Natural Language Processing and Computable Phenotypes in Clinical Records

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211153007
ISBN  
9798384044314
DDC  
004
저자명  
Weber, Katherine G.
서명/저자  
Detecting Risky Alcohol Use With Natural Language Processing and Computable Phenotypes in Clinical Records
발행사항  
[Sl] : University of Michigan, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
141 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-03, Section: A.
주기사항  
Advisor: Vydiswaran, V. G. Vinod.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2024.
초록/해제  
요약Alcohol use is common throughout the United States. Alcohol Use Disorder (AUD) is estimated to affect 12-14% of the US population, and has destructive impacts on the physical and social health of an individual. Unless a person has received diagnosis or treatment for AUD, information about their consumption is largely restricted to free-text notes in their social history and is difficult to locate with simple searches. Because of the correlation between alcohol use and poor surgical outcomes, there is a need to locate alcohol-related information and calculate alcohol-use risk for clinicians who may be seeing a patient for the first time before a procedure. This information alert the preoperative team to this under-recognized surgical risk factor, triggering additional alcohol screening that could aid in clinical decision making.The aims of this dissertation are to develop a natural language processing (NLP) classifier that assesses the text in health records to issue a label representing the degree to which the patient experiences risky alcohol use; and to develop a computable phenotype for risky alcohol use that uses structured data in the clinical record.A binary (high-risk/not high-risk) NLP classifier has an F1 score of 0.78, far outperforming the ability of ICD codes alone to correctly identify high-risk patients. An ordered four-class NLP algorithm applies a transformer encoder and a CNN for intermediate labeling and a bidirectional LSTM neural network as an inference head to effectively build a model with scarce data in rare classes to an overall macro F1 score of 0.77, with true-positive performance of 0.83 and 0.73 for Probable-Dependence and High-Risk, respectively. The proposed structured-data computable phenotype is novel in its ability to provide stratified levels of risk and as a two-class classifier, is significantly more effective than others in the literature. However, it is unable to classify 41% of patients and relies on non-standard structured data in the record for its improvements over another published phenotype.Finally, we consider this model in the context of other Large Language Model approaches to clinical concept extraction, examine the utility of alternatives to the F1 statistic for model selection in ordinal classifiers, and validate the NLP approach to extracting and calculating a numeric value for a patient's weekly alcohol consumption. This dissertation's contributions include a multi-stage, novel approach for extracting sparse information in a noisy, imbalanced dataset, a new ordinal NLP classifier representing alcohol-use risk, and a four-class computable phenotype for alcohol-use risk.
일반주제명  
Information technology
일반주제명  
American studies
일반주제명  
Psychology
일반주제명  
Mental health
키워드  
Natural language processing
키워드  
Alcohol Use Disorder
키워드  
United States
키워드  
US population
키워드  
ICD codes
기타저자  
University of Michigan Hlth Infrastr & Lrng Systs PhD
기본자료저록  
Dissertations Abstracts International. 86-03A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164478
■00520250211153007
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384044314
■035    ▼a(MiAaPQ)AAI31631407
■035    ▼a(MiAaPQ)umichrackham005726
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aWeber,  Katherine  G.
■24510▼aDetecting  Risky  Alcohol  Use  With  Natural  Language  Processing  and  Computable  Phenotypes  in  Clinical  Records
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a141  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-03,  Section:  A.
■500    ▼aAdvisor:  Vydiswaran,  V.  G.  Vinod.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2024.
■520    ▼aAlcohol  use  is  common  throughout  the  United  States.  Alcohol  Use  Disorder  (AUD)  is  estimated  to  affect  12-14%  of  the  US  population,  and  has  destructive  impacts  on  the  physical  and  social  health  of  an  individual.  Unless  a  person  has  received  diagnosis  or  treatment  for  AUD,  information  about  their  consumption  is  largely  restricted  to  free-text  notes  in  their  social  history  and  is  difficult  to  locate  with  simple  searches.  Because  of  the  correlation  between  alcohol  use  and  poor  surgical  outcomes,  there  is  a  need  to  locate  alcohol-related  information  and  calculate  alcohol-use  risk  for  clinicians  who  may  be  seeing  a  patient  for  the  first  time  before  a  procedure.  This  information  alert  the  preoperative  team  to  this  under-recognized  surgical  risk  factor,  triggering  additional  alcohol  screening  that  could  aid  in  clinical  decision  making.The  aims  of  this  dissertation  are  to  develop  a  natural  language  processing  (NLP)  classifier  that  assesses  the  text  in  health  records  to  issue  a  label  representing  the  degree  to  which  the  patient  experiences  risky  alcohol  use;  and  to  develop  a  computable  phenotype  for  risky  alcohol  use  that  uses  structured  data  in  the  clinical  record.A  binary  (high-risk/not  high-risk)  NLP  classifier  has  an  F1  score  of  0.78,  far  outperforming  the  ability  of  ICD  codes  alone  to  correctly  identify  high-risk  patients.  An  ordered  four-class  NLP  algorithm  applies  a  transformer  encoder  and  a  CNN  for  intermediate  labeling  and  a  bidirectional  LSTM  neural  network  as  an  inference  head  to  effectively  build  a  model  with  scarce  data  in  rare  classes  to  an  overall  macro  F1  score  of  0.77,  with  true-positive  performance  of  0.83  and  0.73  for  Probable-Dependence  and  High-Risk,  respectively.  The  proposed  structured-data  computable  phenotype  is  novel  in  its  ability  to  provide  stratified  levels  of  risk  and  as  a  two-class  classifier,  is  significantly  more  effective  than  others  in  the  literature.  However,  it  is  unable  to  classify  41%  of  patients  and  relies  on  non-standard  structured  data  in  the  record  for  its  improvements  over  another  published  phenotype.Finally,  we  consider  this  model  in  the  context  of  other  Large  Language  Model  approaches  to  clinical  concept  extraction,  examine  the  utility  of  alternatives  to  the  F1  statistic  for  model  selection  in  ordinal  classifiers,  and  validate  the  NLP  approach  to  extracting  and  calculating  a  numeric  value  for  a  patient's  weekly  alcohol  consumption.  This  dissertation's  contributions  include  a  multi-stage,  novel  approach  for  extracting  sparse  information  in  a  noisy,  imbalanced  dataset,  a  new  ordinal  NLP  classifier  representing  alcohol-use  risk,  and  a  four-class  computable  phenotype  for  alcohol-use  risk.
■590    ▼aSchool  code:  0127.
■650  4▼aInformation  technology
■650  4▼aAmerican  studies
■650  4▼aPsychology
■650  4▼aMental  health
■653    ▼aNatural  language  processing
■653    ▼aAlcohol  Use  Disorder
■653    ▼aUnited  States
■653    ▼aUS  population
■653    ▼aICD  codes
■690    ▼a0489
■690    ▼a0323
■690    ▼a0621
■690    ▼a0347
■71020▼aUniversity  of  Michigan▼bHlth  Infrastr  &  Lrng  Systs  PhD.
■7730  ▼tDissertations  Abstracts  International▼g86-03A.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164478▼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
    TF11376 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.