서브메뉴
검색
Personalizing Type 2 Diabetes Risk Prediction
Personalizing Type 2 Diabetes Risk Prediction
Detailed Information
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202103140
- ISBN
- 9798283479873
- DDC
- 574
- 저자명
- Khattab, Ahmed.
- 서명/저자
- Personalizing Type 2 Diabetes Risk Prediction
- 발행사항
- [Sl] : The Scripps Research Institute, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 112 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
- 주기사항
- Advisor: Torkamani, Ali;Zorrilla, Eric P.
- 학위논문주기
- Thesis (Ph.D.)--The Scripps Research Institute, 2025.
- 초록/해제
- 요약Type 2 diabetes mellitus (T2DM) is a rapidly growing public health crisis, driven by both modifiable and non-modifiable risk factors. Its rising prevalence, particularly among younger populations, places a substantial burden on healthcare systems, with global and national costs escalating sharply in recent years. Despite the availability of established screening guidelines and traditional risk assessment models, existing approaches often fail to adequately account for the heterogeneity in T2DM susceptibility across populations. These models predominantly rely on clinical and demographic factors, resulting in suboptimal sensitivity and specificity, particularly in diverse, real-world settings. Advancements in genomics and machine learning (ML) offer transformative potential for improving early detection and prevention of T2DM. Polygenic risk scores (PRS) enable the quantification of genetic susceptibility, while ML models can integrate high-dimensional genetic, clinical, and lifestyle data to uncover complex risk patterns. However, the translation of these innovations into clinical practice remains hindered by data heterogeneity, limited validation in diverse populations, and the complexity of integrating genetic and metabolic factors into screening workflows.This dissertation aims to bridge critical gaps in T2DM risk prediction by developing a unified pipeline of genomic discovery, computational tool development, and ML frameworks to enhance precision screening and personalized prevention strategies. First, a genome-wide association study (GWAS) and meta-analysis are conducted to investigate the genetic basis of diabetic kidney disease (DKD), identifying novel loci, including a splicing quantitative trait locus in the Nidogen-1 (NID1) gene, which highlights the role of genetic factors in diabetes complications. Second, a versatile and cost-effective PRS calculator, AoUPRS, is developed to enable efficient genomic analyses tailored for the All of Us dataset, facilitating the integration of genetic risk scores into research and clinical practice. Third, a two-stage ML-based screening approach is proposed, integrating PRS with clinical and metabolic data. This screening model is designed to be adaptable to real-world electronic health record (EHR) data, capable of handling missingness, and validated across diverse populations.Together, these studies form a cohesive pipeline that bridges genomic discovery, computational tool development, and ML-driven screening, underscoring the potential of personalized medicine to advance early detection, improve risk prediction, and reduce disparities in T2DM outcomes.
- 일반주제명
- Bioinformatics
- 일반주제명
- Public health
- 일반주제명
- Statistics
- 일반주제명
- Epidemiology
- 키워드
- Machine learning
- 키워드
- Risk prediction
- 키워드
- Type 2 diabetes
- 기타저자
- The Scripps Research Institute Computational Biology/Bioinformatics
- 기본자료저록
- Dissertations Abstracts International. 86-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017357155
■00520260202103140
■006m o d
■007cr#unu||||||||
■020 ▼a9798283479873
■035 ▼a(MiAaPQ)AAI31994002
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a574
■1001 ▼aKhattab, Ahmed.
■24510▼aPersonalizing Type 2 Diabetes Risk Prediction
■260 ▼a[Sl]▼bThe Scripps Research Institute▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a112 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-12, Section: B.
■500 ▼aAdvisor: Torkamani, Ali;Zorrilla, Eric P.
■5021 ▼aThesis (Ph.D.)--The Scripps Research Institute, 2025.
■520 ▼aType 2 diabetes mellitus (T2DM) is a rapidly growing public health crisis, driven by both modifiable and non-modifiable risk factors. Its rising prevalence, particularly among younger populations, places a substantial burden on healthcare systems, with global and national costs escalating sharply in recent years. Despite the availability of established screening guidelines and traditional risk assessment models, existing approaches often fail to adequately account for the heterogeneity in T2DM susceptibility across populations. These models predominantly rely on clinical and demographic factors, resulting in suboptimal sensitivity and specificity, particularly in diverse, real-world settings. Advancements in genomics and machine learning (ML) offer transformative potential for improving early detection and prevention of T2DM. Polygenic risk scores (PRS) enable the quantification of genetic susceptibility, while ML models can integrate high-dimensional genetic, clinical, and lifestyle data to uncover complex risk patterns. However, the translation of these innovations into clinical practice remains hindered by data heterogeneity, limited validation in diverse populations, and the complexity of integrating genetic and metabolic factors into screening workflows.This dissertation aims to bridge critical gaps in T2DM risk prediction by developing a unified pipeline of genomic discovery, computational tool development, and ML frameworks to enhance precision screening and personalized prevention strategies. First, a genome-wide association study (GWAS) and meta-analysis are conducted to investigate the genetic basis of diabetic kidney disease (DKD), identifying novel loci, including a splicing quantitative trait locus in the Nidogen-1 (NID1) gene, which highlights the role of genetic factors in diabetes complications. Second, a versatile and cost-effective PRS calculator, AoUPRS, is developed to enable efficient genomic analyses tailored for the All of Us dataset, facilitating the integration of genetic risk scores into research and clinical practice. Third, a two-stage ML-based screening approach is proposed, integrating PRS with clinical and metabolic data. This screening model is designed to be adaptable to real-world electronic health record (EHR) data, capable of handling missingness, and validated across diverse populations.Together, these studies form a cohesive pipeline that bridges genomic discovery, computational tool development, and ML-driven screening, underscoring the potential of personalized medicine to advance early detection, improve risk prediction, and reduce disparities in T2DM outcomes.
■590 ▼aSchool code: 1179.
■650 4▼aBioinformatics
■650 4▼aPublic health
■650 4▼aStatistics
■650 4▼aEpidemiology
■653 ▼aMachine learning
■653 ▼aPersonalized screening
■653 ▼aPolygenic risk score
■653 ▼aPrecision medicine
■653 ▼aRisk prediction
■653 ▼aType 2 diabetes
■690 ▼a0715
■690 ▼a0766
■690 ▼a0463
■690 ▼a0573
■71020▼aThe Scripps Research Institute▼bComputational Biology/Bioinformatics.
■7730 ▼tDissertations Abstracts International▼g86-12B.
■790 ▼a1179
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357155▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
Preview
Export
ChatGPT Discussion
AI Recommended Related Books
Подробнее информация.
- Бронирование
- не существует
- моя папка
- Первый запрос зрения
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


