A5032840228- Genomics and Rare Diseases
- Scientific Computing and Data Management
- Genetic Associations and Epidemiology
- Research Data Management Practices
- Ethics in Clinical Research
- Mobile Health and mHealth Applications
- COVID-19 Clinical Research Studies
- Long-Term Effects of COVID-19
- Cancer Genomics and Diagnostics
- Health, Environment, Cognitive Aging
- Data-Driven Disease Surveillance
- Delphi Technique in Research
- Artificial Intelligence in Healthcare
- Explainable Artificial Intelligence (XAI)
- COVID-19 and Mental Health
- Biomedical Text Mining and Ontologies
- Artificial Intelligence in Healthcare and Education
- Nutritional Studies and Diet
- Machine Learning in Healthcare
- Data Quality and Management
- Genetic Syndromes and Imprinting
- Health and Medical Research Impacts
- Anomaly Detection Techniques and Applications
- Microbial Community Ecology and Physiology
- Cardiovascular Health and Risk Factors
National Institutes of Health
2020-2024
The
Abstract Machine learning (ML)-driven computable phenotypes are among the most challenging to share and reproduce. Despite this difficulty, urgent public health considerations around Long COVID make it especially important ensure rigor reproducibility of phenotyping algorithms such that they can be made available a broad audience researchers. As part NIH Researching Enhance Recovery (RECOVER) Initiative, researchers with National Cohort Collaborative (N3C) devised trained an ML-based...
The All of Us Research Program is a precision medicine initiative aimed at establishing vast, diverse biomedical database accessible through cloud-based data analysis platform, the Researcher Workbench (RW). Our goal was to empower research community by co-designing implementation SAS in RW alongside researchers enable broader use data.
Abstract Objectives The NIH All of Us Research Program (All Us) is engaging a diverse community more than 10 000 registered researchers using robust engagement ecosystem model. We describe strategies used to build an that attracts and supports inclusive researcher use the dataset provide metrics on usage growth. Materials Methods Researcher audiences diversity categories were defined guide strategy. A strategy was codeveloped with program partners support ecosystem. An adapted ecological...
Abstract Importance The All of Us Research Program hypothesizes that accruing one million or more diverse participants engaged in a longitudinal research cohort will advance precision medicine and ultimately improve human health. Launched nationally 2018, to date has recruited than 345,000 participants. plans open beta access researchers May 2020. Objective To demonstrate the quality, utility, diversity Program’s initial data release launch cloud-based analysis platform, Researcher...
In this issue of Cell Genomics, GA4GH reports key efforts to help share data across enclaves, including a framework for responsible sharing, use ontology, and approaches oversight. While there remains work in establishing reciprocity between providers, we envision future where joint analysis enclaves is as easy driving different countries.
Data from digital health technologies (DHT), including wearable sensors like Apple Watch, Whoop, Oura Ring, and Fitbit, are increasingly being used in biomedical research. Research development of DHT-related devices, platforms, applications is happening rapidly with significant private-sector involvement new biotech companies large tech (e.g. Google, Apple, Amazon, Uber) investing heavily to improve human health. Many academic institutions building capabilities related DHT research, often...
As biomedical research data grow, researchers need reliable and scalable solutions for storage compute. There is also a to build systems that encourage support collaboration sharing, result in greater reproducibility. This has led many organizations use cloud computing [1]. The not only enables scalable, on-demand resources compute, but continuity during virtual work, can provide superior security compliance features. Moving or adding resources, however, trivial without cost, may be the best...
Data from digital health technologies (DHT), including wearable sensors like Apple Watch, Whoop, Oura Ring, and Fitbit, are increasingly being used in biomedical research. Research development of DHT-related devices, platforms, applications is happening rapidly with significant private-sector involvement new biotech companies large tech (e.g. Google, Apple, Amazon, Uber) investing heavily to improve human health. Many academic institutions building capabilities related DHT research, often...
Abstract Over 200 million SARS-CoV-2 patients have or will develop persistent symptoms (long COVID). Given this pressing research priority, the National COVID Cohort Collaborative (N3C) developed a machine learning model using only electronic health record data to identify potential with long COVID. We hypothesized that additional from surveys, mobile devices, and genotypes could improve prediction ability. In cohort of infected individuals (n=17,755) in All Us program, we applied expanded...
Abstract The rapid growth of genomic data has led to a new research paradigm where are stored centrally in Trusted Research Environments (TREs) such as the All Us Researcher Workbench (AoU RW) and UK Biobank Analysis Platform (RAP). To characterize advantages drawbacks different TRE attributes facilitating cross-cohort analysis, we conducted Genome-Wide Association Study (GWAS) standard lipid measures on UKB RAP AoU RW using two approaches: meta-analysis pooled analysis. We curated...