서브메뉴
검색
Streamlining Healthcare Operations Using Causal Inference and Machine Learning
Streamlining Healthcare Operations Using Causal Inference and Machine Learning
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202103125
- ISBN
- 9798315705277
- DDC
- 614
- 저자명
- Celik, Umit.
- 서명/저자
- Streamlining Healthcare Operations Using Causal Inference and Machine Learning
- 발행사항
- [Sl] : The University of North Carolina at Chapel Hill, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 163 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
- 주기사항
- Advisor: Staats, Bradley.
- 학위논문주기
- Thesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2025.
- 초록/해제
- 요약Aim: Healthcare operations involve complex interactions between physician decision-making, system design, and technological tools. While Electronic Health Records (EHR) and predictive analytics influence efficiency, their effects on workload distribution, appointment delays, and patient outcomes require further examination.Background: The increasing use of digital systems in healthcare has reshaped provider workflows, yet challenges remain in balancing efficiency, standardization, and clinical decision-making.Methodology and Results: This dissertation applies operations management principles, machine learning, and causal inference methods to improve healthcare workflows. The first study (Chapter 1) finds that shifting documentation to before appointments decreases total EHR time by 15.5% and reduces after-hours EHR work by 12%. Alternatively, completing tasks after appointments lowers after-hours work by 22% but increases overall workload. The second study (Chapter 2) shows that increased use of standardized documentation reduces appointment delays by 0.4% and in-room time by 6.8% but also leads to 78 more words per note and longer follow-up visits. The third study (Chapter 3) uses machine learning to identify patients at risk of opioid relapse with 0.97 accuracy and 0.99 recall, and shows that prediction-informed care reduces relapse rates by 2.6%.Conclusion: This dissertation provides empirical evidence on how healthcare workflows can be structured to reduce workload strains, improve timeliness, and enhance patient care. By integrating causal inference with operations management and machine learning, these findings contribute to the development of data-driven strategies for streamlining healthcare operations while addressing the challenges faced by providers and patients.
- 일반주제명
- Health sciences
- 키워드
- Causal inference
- 키워드
- Data analytics
- 키워드
- Econometrics
- 키워드
- Machine learning
- 기타저자
- The University of North Carolina at Chapel Hill Business Administration
- 기본자료저록
- Dissertations Abstracts International. 86-11B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017357066
■00520260202103125
■006m o d
■007cr#unu||||||||
■020 ▼a9798315705277
■035 ▼a(MiAaPQ)AAI31938711
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a614
■1001 ▼aCelik, Umit.
■24510▼aStreamlining Healthcare Operations Using Causal Inference and Machine Learning
■260 ▼a[Sl]▼bThe University of North Carolina at Chapel Hill▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a163 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-11, Section: B.
■500 ▼aAdvisor: Staats, Bradley.
■5021 ▼aThesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2025.
■520 ▼aAim: Healthcare operations involve complex interactions between physician decision-making, system design, and technological tools. While Electronic Health Records (EHR) and predictive analytics influence efficiency, their effects on workload distribution, appointment delays, and patient outcomes require further examination.Background: The increasing use of digital systems in healthcare has reshaped provider workflows, yet challenges remain in balancing efficiency, standardization, and clinical decision-making.Methodology and Results: This dissertation applies operations management principles, machine learning, and causal inference methods to improve healthcare workflows. The first study (Chapter 1) finds that shifting documentation to before appointments decreases total EHR time by 15.5% and reduces after-hours EHR work by 12%. Alternatively, completing tasks after appointments lowers after-hours work by 22% but increases overall workload. The second study (Chapter 2) shows that increased use of standardized documentation reduces appointment delays by 0.4% and in-room time by 6.8% but also leads to 78 more words per note and longer follow-up visits. The third study (Chapter 3) uses machine learning to identify patients at risk of opioid relapse with 0.97 accuracy and 0.99 recall, and shows that prediction-informed care reduces relapse rates by 2.6%.Conclusion: This dissertation provides empirical evidence on how healthcare workflows can be structured to reduce workload strains, improve timeliness, and enhance patient care. By integrating causal inference with operations management and machine learning, these findings contribute to the development of data-driven strategies for streamlining healthcare operations while addressing the challenges faced by providers and patients.
■590 ▼aSchool code: 0153.
■650 4▼aHealth sciences
■653 ▼aCausal inference
■653 ▼aData analytics
■653 ▼aEconometrics
■653 ▼aHealthcare operations
■653 ▼aMachine learning
■653 ▼aService operations
■690 ▼a0310
■690 ▼a0566
■690 ▼a0769
■71020▼aThe University of North Carolina at Chapel Hill▼bBusiness Administration.
■7730 ▼tDissertations Abstracts International▼g86-11B.
■790 ▼a0153
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357066▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
