서브메뉴
검색
ML-Assisted Therapeutics for Neurodegenerative Disorders
ML-Assisted Therapeutics for Neurodegenerative Disorders
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260209102847
- ISBN
- 9798291563540
- DDC
- 614
- 저자명
- Dadu, Anant.
- 서명/저자
- ML-Assisted Therapeutics for Neurodegenerative Disorders
- 발행사항
- [Sl] : University of Illinois at Urbana-Champaign, 2023
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2023
- 형태사항
- 121 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
- 주기사항
- Advisor: Campbell, Roy H.
- 학위논문주기
- Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2023.
- 초록/해제
- 요약Neurodegenerative disorders (NDDs) are a significant public health issue, affecting 50 million people worldwide every year. The complexity of NDDs hinders progress in the development of prevention and disease-modifying therapies. Despite numerous clinical trials, the success rate for treating the condition remains less than 1%, with many trials failing at the late stage leading to significant financial burden and negative outcomes. Challenges presented by NDDs include disease heterogeneity, overlapping clinical syndromes, a long asymptomatic phase, and incomplete understanding of disease mechanisms. A more systematic and efficient approach to the causes and diagnosis of these diseases is needed to accelerate the growth of effective treatments and ultimately improve health outcomes.In the current research landscape, there has been a remarkable upsurge in real-world datasets dedicated to NDDs, characterized by a significant expansion in both sample size and the inclusion of diverse data modalities. Leveraging machine learning techniques to analyze this data presents an exciting opportunity to address challenges presented by NDDs. We have shown that a machine learning algorithm can delineate subgroups within Parkinson's disease by discovering hidden patterns from multi-modal symptomatic data in an unbiased way. Given the longitudinal nature of NDDs, we illustrated the use of longitudinal dimensional reduction approach to identify underlying trajectory patterns within large biomedical datasets. We demonstrated that disease probability scores obtained by exposing brain imaging and genomics data to machine learning tools are useful for risk stratification, prognosis prediction, and monitoring disease progression. Our multi-modal approach on large aggregates of real-world data, along with the contribution of our interactive data-driven web applications, leads to a substantial enhancement in transparency, reproducibility, and accessibility.We anticipate that this dissertation will have a transformative impact on industry and academia by advocating for and enabling data-driven methodologies to enhance medical research. Our comprehensive evaluation and open-source deployment of research results should reduce the friction between basic science research and its practical implementation in clinical settings or drug development processes. As research evolves and produces more complex datasets, we believe that the use of computational tools will become more prevalent in the field. Research outputs of this work can serve as a reference for future research in this area, as it showcases the potential of machine learning to assist medical research for neurodegenerative disorders.
- 일반주제명
- Health sciences
- 일반주제명
- Biomedical engineering
- 일반주제명
- Neurosciences
- 일반주제명
- Genetics
- 키워드
- Machine learning
- 기타저자
- University of Illinois at Urbana-Champaign Computer Science
- 기본자료저록
- Dissertations Abstracts International. 87-03B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260203s2023 us c eng d■001000017365883
■00520260209102847
■006m o d
■007cr#unu||||||||
■020 ▼a9798291563540
■035 ▼a(MiAaPQ)AAI32271328
■035 ▼a(MiAaPQ)httphdlhandlenet2142121427
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a614
■1001 ▼aDadu, Anant.
■24510▼aML-Assisted Therapeutics for Neurodegenerative Disorders
■260 ▼a[Sl]▼bUniversity of Illinois at Urbana-Champaign▼c2023
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2023
■300 ▼a121 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-03, Section: B.
■500 ▼aAdvisor: Campbell, Roy H.
■5021 ▼aThesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2023.
■520 ▼aNeurodegenerative disorders (NDDs) are a significant public health issue, affecting 50 million people worldwide every year. The complexity of NDDs hinders progress in the development of prevention and disease-modifying therapies. Despite numerous clinical trials, the success rate for treating the condition remains less than 1%, with many trials failing at the late stage leading to significant financial burden and negative outcomes. Challenges presented by NDDs include disease heterogeneity, overlapping clinical syndromes, a long asymptomatic phase, and incomplete understanding of disease mechanisms. A more systematic and efficient approach to the causes and diagnosis of these diseases is needed to accelerate the growth of effective treatments and ultimately improve health outcomes.In the current research landscape, there has been a remarkable upsurge in real-world datasets dedicated to NDDs, characterized by a significant expansion in both sample size and the inclusion of diverse data modalities. Leveraging machine learning techniques to analyze this data presents an exciting opportunity to address challenges presented by NDDs. We have shown that a machine learning algorithm can delineate subgroups within Parkinson's disease by discovering hidden patterns from multi-modal symptomatic data in an unbiased way. Given the longitudinal nature of NDDs, we illustrated the use of longitudinal dimensional reduction approach to identify underlying trajectory patterns within large biomedical datasets. We demonstrated that disease probability scores obtained by exposing brain imaging and genomics data to machine learning tools are useful for risk stratification, prognosis prediction, and monitoring disease progression. Our multi-modal approach on large aggregates of real-world data, along with the contribution of our interactive data-driven web applications, leads to a substantial enhancement in transparency, reproducibility, and accessibility.We anticipate that this dissertation will have a transformative impact on industry and academia by advocating for and enabling data-driven methodologies to enhance medical research. Our comprehensive evaluation and open-source deployment of research results should reduce the friction between basic science research and its practical implementation in clinical settings or drug development processes. As research evolves and produces more complex datasets, we believe that the use of computational tools will become more prevalent in the field. Research outputs of this work can serve as a reference for future research in this area, as it showcases the potential of machine learning to assist medical research for neurodegenerative disorders.
■590 ▼aSchool code: 0090.
■650 4▼aHealth sciences
■650 4▼aBiomedical engineering
■650 4▼aNeurosciences
■650 4▼aGenetics
■653 ▼aMachine learning
■653 ▼aNeurodegenerative diseases
■653 ▼aParkinson's disease
■653 ▼aAlzheimer's disease
■653 ▼aBiomedical datasets
■690 ▼a0800
■690 ▼a0566
■690 ▼a0541
■690 ▼a0317
■690 ▼a0369
■71020▼aUniversity of Illinois at Urbana-Champaign▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g87-03B.
■790 ▼a0090
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17365883▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
