Jeffrey Annis

Vanderbilt University Medical Center

11 active projects

Ruderfer - Brittain Collaboration

The demo project aims to explore the strategies to leverage Fitbit along with genomics, survey and EHR data on the cloud-based platform in a cost-efficient fashion. These strategies can lay the foundation to multiple research studies which can drive evidence-based…

Scientific Questions Being Studied

The demo project aims to explore the strategies to leverage Fitbit along with genomics, survey and EHR data on the cloud-based platform in a cost-efficient fashion. These strategies can lay the foundation to multiple research studies which can drive evidence-based care for all. Specifically, the project aims to develop the workspace on Researcher Workbench to develop use cases for digital biomarker development for the Fitbit data and its integration with other AoU data types. One existing challenge is how to ensure that information about multiple streams of health data can be conveyed appropriately to enable fit-for-purpose analyses. Therefore, the intent of the demonstration projects is to understand the challenges that users might face who would like to leverage Fitbit data in tandem with surveys, measurements, genomics and EHR data.

Project Purpose(s)

  • Population Health
  • Social / Behavioral
  • Educational
  • Ancestry

Scientific Approaches

Data wrangling strategies to meaningfully combine Fitbit data with EHR and genomics data on the Researcher Workbench. Develop strategy in R and Python (RMarkdown and Jupyter Notebooks), including calculation of summary statistics and data visualizations, for users of varying levels of digital health literacy.

Develop educational materials to acquaint researchers with the benefits and limitations of combining Fitbit, EHR and genomics data. Materials to be developed include peer-reviewed manuscript, articles/blogs, videos, and user guides.

Anticipated Findings

All of Us Research program (AoURP) currently provides multiple streams of health data (i.e., genomics, surveys, electronic healthcare records (EHR) and Fitbit) to registered users on Researcher Workbench - cloud based platform. This in turn provides a unique opportunity to answer clinically relevant questions. Wearable devices enable continuous monitoring of physiological signals, which may be used for discovery, diagnostic, and prognostic purposes. The Fitbit study as a part of the AoURP includes Fitbit data from approximately 12,000 patients. The information available from the Fitbits (such as activity, heart rate, sleep patterns and device metadata) can be used to develop new digital biomarkers by exploring their correlations with clinical measurements, genetic risk scores and information from surveys such as social determinants of health.

Demographic Categories of Interest

  • Race / Ethnicity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Controlled Tier

Research Team

Owner:

Duplicate of Wearables Data and COVID-19 - Controlled Tier

Our primary goal is to understand the interaction between activity levels and the development, progression, and societal effects of COVID-19. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality…

Scientific Questions Being Studied

Our primary goal is to understand the interaction between activity levels and the development, progression, and societal effects of COVID-19. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality in patients seeking care.

Project Purpose(s)

  • Population Health
  • Social / Behavioral

Scientific Approaches

We will examine the relationship between daily activity (steps, activity intensity) over time and the prevalence of COVID-19. We will use the Fitbit data, EHR-curated diagnoses, laboratory values, quality of life survey results, and clinical outcomes (hospitalizations/mortality).

Anticipated Findings

We may find substantial variation in activity and disease prevalence/severity by socioeconomic status and/or location which would motivate studies/interventions to reduce these health disparities.

Demographic Categories of Interest

  • Race / Ethnicity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Controlled Tier

Research Team

Owner:

  • STACY DESINE - Project Personnel, Vanderbilt University Medical Center
  • Hiral Master - Project Personnel, All of Us Program Operational Use
  • Aymone Kouame - Other, All of Us Program Operational Use
  • Jeffrey Annis - Other, Vanderbilt University Medical Center

Duplicate of Type 2 DM and Wearables Data

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease with a primary focus on type 2 diabetes mellitus. Higher physical activity is associated with lower prevalence and…

Scientific Questions Being Studied

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease with a primary focus on type 2 diabetes mellitus. Higher physical activity is associated with lower prevalence and better outcomes in virtually every human disease. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality in patients seeking care.

Project Purpose(s)

  • Disease Focused Research (type 2 diabetes mellitus)
  • Population Health
  • Social / Behavioral

Scientific Approaches

We will examine the relationship between daily activity (steps, activity intensity) over time and the prevalence and progression of coded human diseases with a primary focus on Type 2 DM. We will use the Fitbit data, EHR-curated diagnoses, laboratory values, quality of life survey results, and clinical outcomes (hospitalizations/mortality).

Anticipated Findings

We expect to find that lower levels of activity are associated with a higher prevalence and more rapid progression of Type 2 DM and other diseases. These data will provide the rationale to link wearables data with electronic health records nationwide as a window into behavioral activity choice as a modifiable risk factor for chronic diseases. We may find substantial variation in activity and disease prevalence/severity by socioeconomic status, which would motivate studies/interventions to reduce these health disparities.

Demographic Categories of Interest

  • Race / Ethnicity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Registered Tier

Research Team

Owner:

Duplicate of Fitbit Phenotyping - Controlled Tier

This is an extension of the Fitbit Phenotyping notebook in which the controlled tier data set will be used to determine daily, weekly, and seasonal patterns in physical activity. Our primary goal is to understand the interaction between activity levels…

Scientific Questions Being Studied

This is an extension of the Fitbit Phenotyping notebook in which the controlled tier data set will be used to determine daily, weekly, and seasonal patterns in physical activity.
Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease utilizing clustering and other machine learning techniques. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality in patients seeking care.

Project Purpose(s)

  • Population Health
  • Social / Behavioral

Scientific Approaches

We will examine the relationship between daily activity (steps, activity intensity) over time and the prevalence and progression of coded human diseases. We will use the Fitbit data, EHR-curated diagnoses, laboratory values, quality of life survey results, and clinical outcomes (hospitalizations/mortality). We will be utilizing the controlled tier version of AOU in this workspace.

Anticipated Findings

We expect to find that lower levels of activity are associated with a higher prevalence and more rapid progression of chronic diseases. We may find clustering in activity and disease prevalence/severity which would motivate studies/interventions to reduce these health disparities. We may also find patterns in seasonal, weekly, or daily patterns in physical activity lead to differences in outcomes.

Demographic Categories of Interest

  • Race / Ethnicity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Controlled Tier

Research Team

Owner:

Wearables and The Human Phenome (v2)

This replicates the workspace Wearables and The Human Phenome. We would like to create a clean and reduced version of our prior workspace for public facing code that was requested from us by Nature Medicine. Our primary goal is to…

Scientific Questions Being Studied

This replicates the workspace Wearables and The Human Phenome. We would like to create a clean and reduced version of our prior workspace for public facing code that was requested from us by Nature Medicine.

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease. Higher physical activity is associated with lower prevalence and better outcomes in virtually every human disease. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality in patients seeking care.

Project Purpose(s)

  • Population Health
  • Social / Behavioral

Scientific Approaches

We will examine the relationship between daily activity (steps, activity intensity) over time and the prevalence and progression of coded human diseases. We will use the Fitbit data, EHR-curated diagnoses, laboratory values, quality of life survey results, and clinical outcomes (hospitalizations/mortality).

Anticipated Findings

We expect to find that lower levels of activity are associated with a higher prevalence and more rapid progression of chronic diseases. These data will provide the rationale to link wearables data with electronic health records nationwide as a window into behavioral activity choice as a modifiable risk factor for chronic diseases. We may find substantial variation in activity and disease prevalence/severity by socioeconomic status, which would motivate studies/interventions to reduce these health disparities.

Demographic Categories of Interest

  • Race / Ethnicity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Registered Tier

Research Team

Owner:

  • Hiral Master - Project Personnel, All of Us Program Operational Use
  • Jeffrey Annis - Other, Vanderbilt University Medical Center

Wearables Data and the Human Phenome

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease. Higher physical activity is associated with lower prevalence and better outcomes in virtually every human disease. These analyses…

Scientific Questions Being Studied

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease. Higher physical activity is associated with lower prevalence and better outcomes in virtually every human disease. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality in patients seeking care.

Project Purpose(s)

  • Population Health
  • Social / Behavioral

Scientific Approaches

We will examine the relationship between daily activity (steps, activity intensity) over time and the prevalence and progression of coded human diseases. We will use the Fitbit data, EHR-curated diagnoses, laboratory values, quality of life survey results, and clinical outcomes (hospitalizations/mortality).

Anticipated Findings

We expect to find that lower levels of activity are associated with a higher prevalence and more rapid progression of chronic diseases. These data will provide the rationale to link wearables data with electronic health records nationwide as a window into behavioral activity choice as a modifiable risk factor for chronic diseases. We may find substantial variation in activity and disease prevalence/severity by socioeconomic status, which would motivate studies/interventions to reduce these health disparities.

Demographic Categories of Interest

  • Race / Ethnicity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Registered Tier

Research Team

Owner:

  • Shi Huang - Other, Vanderbilt University Medical Center
  • Hiral Master - Project Personnel, All of Us Program Operational Use
  • Evan Brittain - Mid-career Tenured Researcher, Vanderbilt University Medical Center
  • Jeffrey Annis - Other, Vanderbilt University Medical Center

Duplicate of Fitbit Phenotyping

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease utilizing clustering and other machine learning techniques. These analyses will generate hypotheses guiding clinical and research interventions focused…

Scientific Questions Being Studied

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease utilizing clustering and other machine learning techniques. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality in patients seeking care.

Project Purpose(s)

  • Population Health
  • Social / Behavioral

Scientific Approaches

We will examine the relationship between daily activity (steps, activity intensity) over time and the prevalence and progression of coded human diseases. We will use the Fitbit data, EHR-curated diagnoses, laboratory values, quality of life survey results, and clinical outcomes (hospitalizations/mortality).

Anticipated Findings

We expect to find that lower levels of activity are associated with a higher prevalence and more rapid progression of chronic diseases. We may find clustering in activity and disease prevalence/severity which would motivate studies/interventions to reduce these health disparities.

Demographic Categories of Interest

  • Race / Ethnicity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Registered Tier

Research Team

Owner:

Fitbit Phenotyping

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease utilizing clustering and other machine learning techniques. These analyses will generate hypotheses guiding clinical and research interventions focused…

Scientific Questions Being Studied

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease utilizing clustering and other machine learning techniques. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality in patients seeking care.

Project Purpose(s)

  • Population Health
  • Social / Behavioral

Scientific Approaches

We will examine the relationship between daily activity (steps, activity intensity) over time and the prevalence and progression of coded human diseases. We will use the Fitbit data, EHR-curated diagnoses, laboratory values, quality of life survey results, and clinical outcomes (hospitalizations/mortality).

Anticipated Findings

We expect to find that lower levels of activity are associated with a higher prevalence and more rapid progression of chronic diseases. We may find clustering in activity and disease prevalence/severity which would motivate studies/interventions to reduce these health disparities.

Demographic Categories of Interest

  • Race / Ethnicity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Registered Tier

Research Team

Owner:

Wearables Data and COVID-19 - Controlled Tier

Our primary goal is to understand the interaction between activity levels and the development, progression, and societal effects of COVID-19. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality…

Scientific Questions Being Studied

Our primary goal is to understand the interaction between activity levels and the development, progression, and societal effects of COVID-19. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality in patients seeking care.

Project Purpose(s)

  • Population Health
  • Social / Behavioral

Scientific Approaches

We will examine the relationship between daily activity (steps, activity intensity) over time and the prevalence of COVID-19. We will use the Fitbit data, EHR-curated diagnoses, laboratory values, quality of life survey results, and clinical outcomes (hospitalizations/mortality).

Anticipated Findings

We may find substantial variation in activity and disease prevalence/severity by socioeconomic status and/or location which would motivate studies/interventions to reduce these health disparities.

Demographic Categories of Interest

  • Race / Ethnicity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Controlled Tier

Research Team

Owner:

Type 2 DM and Wearables Data

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease with a primary focus on type 2 diabetes mellitus. Higher physical activity is associated with lower prevalence and…

Scientific Questions Being Studied

Our primary goal is to understand the interaction between activity levels and sleep quality with the development and progression of human disease with a primary focus on type 2 diabetes mellitus. Higher physical activity is associated with lower prevalence and better outcomes in virtually every human disease. These analyses will generate hypotheses guiding clinical and research interventions focused on activity and sleep to reduce morbidity and mortality in patients seeking care.

Project Purpose(s)

  • Disease Focused Research (type 2 diabetes mellitus)
  • Population Health
  • Social / Behavioral

Scientific Approaches

We will examine the relationship between daily activity (steps, activity intensity) over time and the prevalence and progression of coded human diseases with a primary focus on Type 2 DM. We will use the Fitbit data, EHR-curated diagnoses, laboratory values, quality of life survey results, and clinical outcomes (hospitalizations/mortality).

Anticipated Findings

We expect to find that lower levels of activity are associated with a higher prevalence and more rapid progression of Type 2 DM and other diseases. These data will provide the rationale to link wearables data with electronic health records nationwide as a window into behavioral activity choice as a modifiable risk factor for chronic diseases. We may find substantial variation in activity and disease prevalence/severity by socioeconomic status, which would motivate studies/interventions to reduce these health disparities.

Demographic Categories of Interest

  • Race / Ethnicity
  • Geography
  • Access to Care
  • Education Level
  • Income Level

Data Set Used

Registered Tier

Research Team

Owner:

Pulmonary Hypertension in All of Us

Our primary purpose at this stage is to test whether we can reliably identify patients with pulmonary hypertension in the All of Us resource. We have developed and internally validated a machine learning algorithm to identify patients with pulmonary hypertension…

Scientific Questions Being Studied

Our primary purpose at this stage is to test whether we can reliably identify patients with pulmonary hypertension in the All of Us resource. We have developed and internally validated a machine learning algorithm to identify patients with pulmonary hypertension using administrative data. We first want to test the performance of that algorithm in All of Us. If the performance is satisfactory, we will then begin addressing research questions centered around the epidemiology and outcomes of patients with pulmonary hypertension. We will examine the geographic distributions, trends in the diagnosis over time, hospitalization and mortality rates, medication use, and medication exposures that may suggest drug-induced PH.

Project Purpose(s)

  • Disease Focused Research (pulmonary hypertension)

Scientific Approaches

We will use ICD and CPT codes, and medications exposures to test our machine learning algorithm. If the algorithm performs well, we will then use basic demographics, medications, and outcomes data to study the epidemiology of pulmonary hypertension in All of Us.

Anticipated Findings

We anticipate that our study will provide a contemporary "real world" view of pulmonary hypertension patients in the United States. This is important and new because most epidemiological studies of pulmonary hypertension in the United States to date derive from either single centers or registries that enroll patients from select centers.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Registered Tier

Research Team

Owner:

  • Evan Brittain - Mid-career Tenured Researcher, Vanderbilt University Medical Center
  • Jeffrey Annis - Other, Vanderbilt University Medical Center

Collaborators:

  • Shi Huang - Other, Vanderbilt University Medical Center
1 - 11 of 11
<
>
Request a Review of this Research Project

You can request that the All of Us Resource Access Board (RAB) review a research purpose description if you have concerns that this research project may stigmatize All of Us participants or violate the Data User Code of Conduct in some other way. To request a review, you must fill in a form, which you can access by selecting ‘request a review’ below.