서브메뉴
검색
Pitfalls of Neuroimaging Predictive Models of Individual Differences
Pitfalls of Neuroimaging Predictive Models of Individual Differences
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202103029
- ISBN
- 9798286442027
- DDC
- 616
- 서명/저자
- Pitfalls of Neuroimaging Predictive Models of Individual Differences
- 발행사항
- [Sl] : Yale University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 184 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
- 주기사항
- Advisor: Scheinost, Dustin.
- 학위논문주기
- Thesis (Ph.D.)--Yale University, 2025.
- 초록/해제
- 요약Advances in data collection efforts and computational methods have established neuroimaging-based predictive models as a fundamental area of human neuroscience research. Predictive models have successfully related individual differences in brain structure and function to a wide variety of phenotypes, but several pitfalls challenge the reliability of these models. In this thesis, I highlight several prominent limitations that need to be addressed to improve the reproducibility, replicability, and generalizability of neuroimaging predictive models of individual differences. In Chapters 2-3, I demonstrate how accidentally introducing information about the test data into the model training pipeline ("data leakage") leads to the misestimation of prediction performance. In Chapters 4-6, I discuss how neuroimaging-based predictive models are susceptible to minor data manipulations, which limits the trustworthiness of results in both research and clinical settings. Among Chapters 2-6, external validation-or the evaluation of models in independent datasets-emerged as a promising solution. Yet, in Chapters 7-8, I describe how current implementations of external validation are not conducive to improving the robustness of neuroimaging results due to poor statistical power. Notably, unlike traditional power calculations, power in external validation depends on two sample sizes: the training dataset sample size and the external dataset sample size. Together, the results presented in this thesis provide a strong foundation for advancing the robustness and reliability of neuroimaging predictive models, which brings the field one step closer to practical utility.
- 일반주제명
- Medical imaging
- 일반주제명
- Bioengineering
- 일반주제명
- Neurosciences
- 키워드
- Connectomes
- 키워드
- Data leakage
- 키워드
- Machine learning
- 키워드
- Reproducibility
- 기타저자
- Yale University Biomedical Engineering
- 기본자료저록
- Dissertations Abstracts International. 86-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017356754
■00520260202103029
■006m o d
■007cr#unu||||||||
■020 ▼a9798286442027
■035 ▼a(MiAaPQ)AAI31845667
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a616
■1001 ▼aRosenblatt, Matthew.
■24510▼aPitfalls of Neuroimaging Predictive Models of Individual Differences
■260 ▼a[Sl]▼bYale University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a184 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-12, Section: B.
■500 ▼aAdvisor: Scheinost, Dustin.
■5021 ▼aThesis (Ph.D.)--Yale University, 2025.
■520 ▼aAdvances in data collection efforts and computational methods have established neuroimaging-based predictive models as a fundamental area of human neuroscience research. Predictive models have successfully related individual differences in brain structure and function to a wide variety of phenotypes, but several pitfalls challenge the reliability of these models. In this thesis, I highlight several prominent limitations that need to be addressed to improve the reproducibility, replicability, and generalizability of neuroimaging predictive models of individual differences. In Chapters 2-3, I demonstrate how accidentally introducing information about the test data into the model training pipeline ("data leakage") leads to the misestimation of prediction performance. In Chapters 4-6, I discuss how neuroimaging-based predictive models are susceptible to minor data manipulations, which limits the trustworthiness of results in both research and clinical settings. Among Chapters 2-6, external validation-or the evaluation of models in independent datasets-emerged as a promising solution. Yet, in Chapters 7-8, I describe how current implementations of external validation are not conducive to improving the robustness of neuroimaging results due to poor statistical power. Notably, unlike traditional power calculations, power in external validation depends on two sample sizes: the training dataset sample size and the external dataset sample size. Together, the results presented in this thesis provide a strong foundation for advancing the robustness and reliability of neuroimaging predictive models, which brings the field one step closer to practical utility.
■590 ▼aSchool code: 0265.
■650 4▼aMedical imaging
■650 4▼aBioengineering
■650 4▼aNeurosciences
■653 ▼aConnectomes
■653 ▼aData leakage
■653 ▼aMachine learning
■653 ▼aMagnetic resonance imaging
■653 ▼aPredictive modeling
■653 ▼aReproducibility
■690 ▼a0574
■690 ▼a0202
■690 ▼a0317
■690 ▼a0800
■71020▼aYale University▼bBiomedical Engineering.
■7730 ▼tDissertations Abstracts International▼g86-12B.
■790 ▼a0265
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17356754▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
