서브메뉴
검색
Using Multivariate Statistics and Machine Learning to Reveal Gait as a Pre-Clinical Biomarker of Injury, Disease, and Age
Using Multivariate Statistics and Machine Learning to Reveal Gait as a Pre-Clinical Biomarker of Injury, Disease, and Age
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211153042
- ISBN
- 9798346857457
- DDC
- 610
- 서명/저자
- Using Multivariate Statistics and Machine Learning to Reveal Gait as a Pre-Clinical Biomarker of Injury, Disease, and Age
- 발행사항
- [Sl] : Northwestern University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 245 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
- 주기사항
- Advisor: Luo, Yuan;Wertheim, Jason A.
- 학위논문주기
- Thesis (Ph.D.)--Northwestern University, 2024.
- 초록/해제
- 요약Every 30 seconds someone in the world has a limb amputated. Prosthetic limb replacement technology has been available for thousands of years and has made huge technological leaps in the last few hundred. Surgical limb replacement and reconstruction is a far more nascent field. In the last few decades reconstructive transplantation has emerged as a viable option for individuals with upper extremity loss. Today, more than 130 people around the world have received hand or arm transplants and seen restoration of sensation and function. However, only 4 people have received lower extremity transplants with one surviving to date. As a result, there is little to no opportunity to study new techniques, materials, technology, or approaches for advancing lower extremity transplantation in humans. With the concept proven in at least one human, a robust animal model is needed that will unlock the evaluation of new surgical techniques, tissue engineering strategies, or other approaches for their roles in restoring the limbs of millions of people who have lost them. This thesis dissertation will answer the question of how we might quantify and measure success in lower extremity transplantation across immunological, vascular, neurological, and musculoskeletal aspects in an accessible pre-clinical model. Particularly utilizing multivariate statistics and machine learning techniques to characterize and quantify something as complex as gait at increasing degrees of neuromusculoskeletal injury. In the process revealing the spatial and temporal features that are most descriptive of peripheral nerve injury at those increasing degrees. Finally, demonstrating how the same multivariate statistics can be applied to pre-clinical studies of other etiologies of gait deficit or deviation (e.g. central, congenital, age-related). Ultimately revealing gait to be a pre-clinical biomarker of injury, disease, and age. These results may provide scientists a novel method to reduce observational bias when analyzing data from treadmill gait systems.
- 일반주제명
- Biomedical engineering
- 일반주제명
- Bioinformatics
- 일반주제명
- Statistics
- 일반주제명
- Biomechanics
- 키워드
- Limb replacement
- 키워드
- Machine learning
- 기타저자
- Northwestern University Biomedical Engineering
- 기본자료저록
- Dissertations Abstracts International. 86-06B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017164760
■00520250211153042
■006m o d
■007cr#unu||||||||
■020 ▼a9798346857457
■035 ▼a(MiAaPQ)AAI31639145
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a610
■1001 ▼aNaved, Bilal Abdullah.▼0(orcid)0000-0001-5870-624X
■24510▼aUsing Multivariate Statistics and Machine Learning to Reveal Gait as a Pre-Clinical Biomarker of Injury, Disease, and Age
■260 ▼a[Sl]▼bNorthwestern University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a245 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-06, Section: B.
■500 ▼aAdvisor: Luo, Yuan;Wertheim, Jason A.
■5021 ▼aThesis (Ph.D.)--Northwestern University, 2024.
■520 ▼aEvery 30 seconds someone in the world has a limb amputated. Prosthetic limb replacement technology has been available for thousands of years and has made huge technological leaps in the last few hundred. Surgical limb replacement and reconstruction is a far more nascent field. In the last few decades reconstructive transplantation has emerged as a viable option for individuals with upper extremity loss. Today, more than 130 people around the world have received hand or arm transplants and seen restoration of sensation and function. However, only 4 people have received lower extremity transplants with one surviving to date. As a result, there is little to no opportunity to study new techniques, materials, technology, or approaches for advancing lower extremity transplantation in humans. With the concept proven in at least one human, a robust animal model is needed that will unlock the evaluation of new surgical techniques, tissue engineering strategies, or other approaches for their roles in restoring the limbs of millions of people who have lost them. This thesis dissertation will answer the question of how we might quantify and measure success in lower extremity transplantation across immunological, vascular, neurological, and musculoskeletal aspects in an accessible pre-clinical model. Particularly utilizing multivariate statistics and machine learning techniques to characterize and quantify something as complex as gait at increasing degrees of neuromusculoskeletal injury. In the process revealing the spatial and temporal features that are most descriptive of peripheral nerve injury at those increasing degrees. Finally, demonstrating how the same multivariate statistics can be applied to pre-clinical studies of other etiologies of gait deficit or deviation (e.g. central, congenital, age-related). Ultimately revealing gait to be a pre-clinical biomarker of injury, disease, and age. These results may provide scientists a novel method to reduce observational bias when analyzing data from treadmill gait systems.
■590 ▼aSchool code: 0163.
■650 4▼aBiomedical engineering
■650 4▼aBioinformatics
■650 4▼aStatistics
■650 4▼aBiomechanics
■653 ▼aLimb replacement
■653 ▼aSurgical techniques
■653 ▼aMachine learning
■653 ▼aPre-clinical biomarker
■653 ▼aTissue engineering
■690 ▼a0541
■690 ▼a0715
■690 ▼a0463
■690 ▼a0648
■71020▼aNorthwestern University▼bBiomedical Engineering.
■7730 ▼tDissertations Abstracts International▼g86-06B.
■790 ▼a0163
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164760▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
