Research Projects Directory

Research Projects Directory

Information about each research project within the Workbench is available in the Research Projects Directory below. Approved researchers provide their project’s research purpose, description, populations of interest and more. This information helps All of Us ensure transparency on the type of research being conducted.

At this time, all listed projects are using data in the Registered Tier. The Registered Tier contains individual-level data from electronic health records, survey answers, and physical measurements. These data have been altered to protect participant privacy.

Note: Researcher Workbench users provide information about their research projects independently. Any views expressed in the Research Projects Directory belong to the relevant users and do not necessarily represent those of the All of Us Research Program.

Information in the Research Projects Directory is also cross-posted on AllofUs.nih.gov in compliance with the 21st Century Cures Act.

There are currently 291 active workspaces. This information was updated on 12/5/2020.

Sort By Title:

Validation of Physical measurements

Project Purpose(s)

  • Methods Development ...

Scientific Questions Being Studied

Validate physical measurements (height, weight, BMI) and blood measurement s between electronic health record data and physical measurements at the physical visit at the clinic. Examine those correlations by age categories, gender, race ethnicity and disease spectrum.

Scientific Approaches

Create calendar period specific measurements of height, weight, blood pressure from the EHR and during the physical measurement visits and examine the correlation and agreement between the two. In addition, examine those correlations by race ethnicity, age, gender and disease status.

Anticipated Findings

How interchangeable are the EMR data with Physical measurement data during the PMB visit
Are the All of Us data coming from the EMR valid for analyses and if yes this will facilitate an expansion of use of the All of Us data

Demographic Categories of Interest

  • Race / Ethnicity
  • Age
  • Education Level
  • Income Level

Research Team

Owner:

  • Argyrios Ziogas - Late Career Tenured Researcher, University of California, Irvine

Collaborators:

  • Steven Hiek - Project Personnel, University of California, Irvine
  • Kathryn Campbell - Project Personnel, University of California, Irvine

Vitamin B12 deficiency and supplementation in patients on metformin

Project Purpose(s)

  • Disease Focused Research (type 2 diabetes mellitus)
  • Population Health ...

Scientific Questions Being Studied

1. What proportion of patients with type 2 diabetes who take metformin have a vitamin B 12 deficiency?
2. What proportion of patients with type 2 diabetes who take metformin have had their vitamin B 12 levels measured?
3. What proportion of patients with type 2 diabetes who take metformin and have a vitamin B 12 deficiency are taking vitamin B 12 supplement?
4. Are there demographic or other disparities between patients with type 2 diabetes who take metformin and have vitamin B 12 deficiency compared with those who do not have deficiency?
5. Are there demographic or other disparities between patients with type 2 diabetes who take metformin and have had their vitamin B 12 levels measured compared with those who have not had it measured?
6. Are there demographic or other disparities between patients with type 2 diabetes who take metformin, have a vitamin B 12 deficiency and take vitamin B 12 supplement compared with those who do not take vitamin B 12 supplement?

Scientific Approaches

Data will be drawn from EHR domains (diagnosis of type 2 diabetes, use of metformin, vitamin B 12 levels, vitamin B 12 supplementation), and survey responses (demographics, healthcare access and utilization). Basic descriptive statistics will be used to answer questions 1-3 above and inferential statistics to assess for disparities based on demographic factors, etc. (questions 4-6).

Anticipated Findings

This work will contribute to our understanding of how common vitamin B 12 deficiency is in patients who take metformin. Additionally, how likely it is patients taking metformin will be tested for deficiency and how likely it is that deficiency will be treated if present. Finally, this work aims to assess disparities, whether they be gender/sex-based, racial/ethnic, socioeconomic (e.g. educational attainment, income), age-based, or others, in the likelihood a patient taking metformin will have their vitamin B 12 levels assessed, whether they will have a deficiency and whether a deficiency will be treated if it is present.

Demographic Categories of Interest

  • Race / Ethnicity
  • Age
  • Gender Identity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Research Team

Owner:

  • Keri Hurley-Kim - Other, University of California, Irvine

Warfarin ABO

Project Purpose(s)

  • Population Health ...

Scientific Questions Being Studied

We will investigate the frequency of warfarin dose tablet sizes in ABO blood groups. O blood type has been associated with higher warfarin doses.

Scientific Approaches

We will use the drug exposure warfarin and ABO blood groups in order to test the proportion of higher tablet dosage, and therefore dose, in different blood types.

Anticipated Findings

We anticipate to find blood types have disparately distributed warfarin tablet dosages. Blood type could be an easily implementable prediction variable in warfarin dose prediction algorithms.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Research Team

Owner:

  • Heidi Steiner - Graduate Trainee, University of Arizona

workbench tutorial breast ca demo nashville 2019-11-14

Project Purpose(s)

  • Educational ...

Scientific Questions Being Studied

can I learn how to use this workbench?

Scientific Approaches

Not available.

Anticipated Findings

I will understand the workbench better.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Research Team

Owner:

  • William Hogan - Late Career Tenured Researcher, University of Florida

Workspace & Data Orientation

Project Purpose(s)

  • Methods Development ...

Scientific Questions Being Studied

The purpose of this workspace is to provide the HealthPartners Institute AI group with baseline knowledge about the All of Us computing environment and data. It aims to answer some of the following questions:
- What are the capabilities and limitations of the All of Us Workbench system?
- What is the structure of the All of Us data when imported into the workbench?
- What level of technical skillsets and personnel are required to pursue a research question in the All of Us Workbench environment?
- What will GC infrastructure costs look like to train a simple classification model on a modest subset of All of Us data?

Scientific Approaches

Method: In this exercise, we will attempt to create a classification model to explain predictors for hypertension. We will identify a cohort of patients who have at least one clinical encounter at the time of or prior to systolic and diastolic blood pressure measurements. Using a GBDT, we will train a model to classify between stage 2 and non-stage 2 hypertension using as wide a feature set as can be accomplished within time limitations for this exercise. Should the ML model exhibit an AUC > .6, then we will attempt to explain the contributing features using SHAP or f-score.

Anticipated Findings

At the conclusion of this exercise, we expect to be able to report back to the HealthPartners Institute AI group on the capabilities, accessibility, costs associated with operation, and technical skillsets required to conduct research using the All of Us workbench tools. In addition, we anticipate identifying considerations and barriers to research that investigators at HPI will need to account for in future grant proposal design using All of Us data.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Research Team

Owner:

  • Samuel O'Blenes - Project Personnel, HealthPartners Institute