서브메뉴
검색
Interpretable Statistical Learning for Real-World Behavioral Data- [electronic resource]
![Interpretable Statistical Learning for Real-World Behavioral Data - [electronic resource]](/Users/Baul/Images/book.png)
Interpretable Statistical Learning for Real-World Behavioral Data- [electronic resource]
상세정보
- 자료유형
- 학위논문파일 국외
- 최종처리일시
- 20240214100448
- ISBN
- 9798379613648
- DDC
- 574
- 서명/저자
- Interpretable Statistical Learning for Real-World Behavioral Data - [electronic resource]
- 발행사항
- [S.l.]: : Harvard University., 2023
- 발행사항
- Ann Arbor : : ProQuest Dissertations & Theses,, 2023
- 형태사항
- 1 online resource(122 p.)
- 주기사항
- Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
- 주기사항
- Advisor: Onnela, Jukka-Pekka;Lu, Junwei.
- 학위논문주기
- Thesis (Ph.D.)--Harvard University, 2023.
- 사용제한주기
- This item must not be sold to any third party vendors.
- 초록/해제
- 요약The rapid development of data collection methods and analysis techniques has revolutionized our understanding of human behavior and its relationship to health outcomes. However, despite the increasing availability of real-world behavioral data, the effective use of this information for real-time prediction and intervention remains a significant challenge. This dissertation explores interpretable statistical learning methods for real-world behavioral data, with a focus on overcoming limitations in episodic data collection by leveraging smartphone-based digital phenotyping. The approaches explored ultimately provide a scalable method for utilizing real-world history data on human behavior to inform decision-making and interventions, while improving current standards of care. Chapter 1 presents a novel method for estimating interpretable value functions in reinforcement learning. By incorporating local kernel regression and basis expansion, we develop a sparse, additive representation of the action-value function. This allows us to approximate the action-value function and retrieve the nonlinear, independent contributions of select features and joint feature pairs. We validate this approach through a simulation study and an application to spine disease, uncovering recovery recommendations in line with clinical knowledge. Chapter 2 explores the trade-offs of learning in the growing-batch reinforcement learning setting and investigates how information provided by a teacher (i.e., demonstrations, expert actions, and gradient information) can be leveraged during training to mitigate the sample complexity and coverage requirements for actor-critic methods. We validate our contributions on tasks from the DeepMind Control Suite. Chapter 3 introduces an approach where we use hidden semi-Markov models on smartphone activity logs to identify key patterns of differentiation in smartphone usage among adolescents with bipolar disorder and their typically-developing peers. This analysis enables the identification of latent constructs that correspond to resting and active smartphone usage, providing insights into the long-term behavioral trends in adolescents with bipolar disorder.Chapter 4 presents the Digital Assessment in Neuro-Oncology (DANO) pilot, which leverages smartphone-based digital phenotyping to monitor post-operative recovery in glioblastoma patients. We analyze passive GPS and accelerometer data to construct mobility patterns and compare these patterns with a control group of non-operative spine disease patients. Our findings reveal significant changes in mobility among glioblastoma patients during the first six months following surgery and between subsequent cycles of chemotherapy.
- 일반주제명
- Biostatistics.
- 일반주제명
- Statistics.
- 일반주제명
- Computer science.
- 키워드
- Behavioral data
- 키워드
- Real-world
- 기타저자
- Harvard University Biostatistics
- 기본자료저록
- Dissertations Abstracts International. 84-12B.
- 기본자료저록
- Dissertation Abstract International
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008240612s2023 us |||||||||||||||c||eng d■001000016932364
■00520240214100448
■006m o d
■007cr#unu||||||||
■020 ▼a9798379613648
■035 ▼a(MiAaPQ)AAI30491865
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a574
■1001 ▼aEmedom-Nnamdi, Patrick Ugochukwu.▼0(orcid)0000-0003-4442-924X
■24510▼aInterpretable Statistical Learning for Real-World Behavioral Data▼h[electronic resource]
■260 ▼a[S.l.]:▼bHarvard University. ▼c2023
■260 1▼aAnn Arbor :▼bProQuest Dissertations & Theses, ▼c2023
■300 ▼a1 online resource(122 p.)
■500 ▼aSource: Dissertations Abstracts International, Volume: 84-12, Section: B.
■500 ▼aAdvisor: Onnela, Jukka-Pekka;Lu, Junwei.
■5021 ▼aThesis (Ph.D.)--Harvard University, 2023.
■506 ▼aThis item must not be sold to any third party vendors.
■520 ▼aThe rapid development of data collection methods and analysis techniques has revolutionized our understanding of human behavior and its relationship to health outcomes. However, despite the increasing availability of real-world behavioral data, the effective use of this information for real-time prediction and intervention remains a significant challenge. This dissertation explores interpretable statistical learning methods for real-world behavioral data, with a focus on overcoming limitations in episodic data collection by leveraging smartphone-based digital phenotyping. The approaches explored ultimately provide a scalable method for utilizing real-world history data on human behavior to inform decision-making and interventions, while improving current standards of care. Chapter 1 presents a novel method for estimating interpretable value functions in reinforcement learning. By incorporating local kernel regression and basis expansion, we develop a sparse, additive representation of the action-value function. This allows us to approximate the action-value function and retrieve the nonlinear, independent contributions of select features and joint feature pairs. We validate this approach through a simulation study and an application to spine disease, uncovering recovery recommendations in line with clinical knowledge. Chapter 2 explores the trade-offs of learning in the growing-batch reinforcement learning setting and investigates how information provided by a teacher (i.e., demonstrations, expert actions, and gradient information) can be leveraged during training to mitigate the sample complexity and coverage requirements for actor-critic methods. We validate our contributions on tasks from the DeepMind Control Suite. Chapter 3 introduces an approach where we use hidden semi-Markov models on smartphone activity logs to identify key patterns of differentiation in smartphone usage among adolescents with bipolar disorder and their typically-developing peers. This analysis enables the identification of latent constructs that correspond to resting and active smartphone usage, providing insights into the long-term behavioral trends in adolescents with bipolar disorder.Chapter 4 presents the Digital Assessment in Neuro-Oncology (DANO) pilot, which leverages smartphone-based digital phenotyping to monitor post-operative recovery in glioblastoma patients. We analyze passive GPS and accelerometer data to construct mobility patterns and compare these patterns with a control group of non-operative spine disease patients. Our findings reveal significant changes in mobility among glioblastoma patients during the first six months following surgery and between subsequent cycles of chemotherapy.
■590 ▼aSchool code: 0084.
■650 4▼aBiostatistics.
■650 4▼aStatistics.
■650 4▼aComputer science.
■653 ▼aBehavioral data
■653 ▼aDigital phenotyping
■653 ▼aReal-world
■653 ▼aReinforcement learning
■653 ▼aState space models
■690 ▼a0308
■690 ▼a0463
■690 ▼a0984
■71020▼aHarvard University▼bBiostatistics.
■7730 ▼tDissertations Abstracts International▼g84-12B.
■773 ▼tDissertation Abstract International
■790 ▼a0084
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16932364▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
■980 ▼a202402▼f2024
