Jonathan Sanchez

Graduate Trainee, George Mason University

6 active projects

Duplicate of Breast Cancer Diagnosis Prediction_March2024

The specific scientific questions that we intend to study when building a predictive model of breast cancer diagnosis using Fitbit data and social/behavioral factors as inputs encompass several key areas. Firstly, we aim to investigate whether Fitbit data, encompassing metrics…

Scientific Questions Being Studied

The specific scientific questions that we intend to study when building a predictive model of breast cancer diagnosis using Fitbit data and social/behavioral factors as inputs encompass several key areas. Firstly, we aim to investigate whether Fitbit data, encompassing metrics like activity levels, heart rate, and sleep patterns, can serve as reliable predictors of breast cancer development. This question is of high importance as it explores the potential of utilizing wearable technology for early breast cancer risk detection, potentially leading to more timely diagnosis and improved patient outcomes. Additionally, we seek to understand the extent to which social factors, including socioeconomic status, healthcare access, and social support, influence breast cancer risk and how they can be incorporated into the predictive model to identify vulnerable populations and tailor prevention efforts.

Project Purpose(s)

  • Disease Focused Research (female breast cancer)
  • Population Health
  • Social / Behavioral

Scientific Approaches

Our study will leverage the "All of Us" dataset, featuring diverse participant data, to develop a predictive breast cancer diagnosis model. We'll use Fitbit data (activity, heart rate, sleep), complemented by socioeconomic status, lifestyle, healthcare access, and historical breast cancer incidence records. We will employ machine learning techniques to explore the complex relationships between these factors and breast cancer risk. Rigorous validation and ethical considerations will be integral, and interdisciplinary collaboration will ensure a holistic approach to enhance breast cancer risk prediction.

Anticipated Findings

Our predictive model, integrating Fitbit data and social/behavioral factors, may enable early breast cancer risk assessment, offering a non-invasive and continuous monitoring approach. The study may uncover specific lifestyle and behavioral factors that interact with physiological data to influence breast cancer risk. This could lead to the identification of individuals at higher risk, allowing for targeted screening and preventive interventions.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Controlled Tier

Research Team

Owner:

Duplicate of Breast Cancer Diagnosis Prediction_2

The specific scientific questions that we intend to study when building a predictive model of breast cancer diagnosis using Fitbit data and social/behavioral factors as inputs encompass several key areas. Firstly, we aim to investigate whether Fitbit data, encompassing metrics…

Scientific Questions Being Studied

The specific scientific questions that we intend to study when building a predictive model of breast cancer diagnosis using Fitbit data and social/behavioral factors as inputs encompass several key areas. Firstly, we aim to investigate whether Fitbit data, encompassing metrics like activity levels, heart rate, and sleep patterns, can serve as reliable predictors of breast cancer development. This question is of high importance as it explores the potential of utilizing wearable technology for early breast cancer risk detection, potentially leading to more timely diagnosis and improved patient outcomes. Additionally, we seek to understand the extent to which social factors, including socioeconomic status, healthcare access, and social support, influence breast cancer risk and how they can be incorporated into the predictive model to identify vulnerable populations and tailor prevention efforts.

Project Purpose(s)

  • Disease Focused Research (female breast cancer)
  • Population Health
  • Social / Behavioral

Scientific Approaches

Our study will leverage the "All of Us" dataset, featuring diverse participant data, to develop a predictive breast cancer diagnosis model. We'll use Fitbit data (activity, heart rate, sleep), complemented by socioeconomic status, lifestyle, healthcare access, and historical breast cancer incidence records. We will employ machine learning techniques to explore the complex relationships between these factors and breast cancer risk. Rigorous validation and ethical considerations will be integral, and interdisciplinary collaboration will ensure a holistic approach to enhance breast cancer risk prediction.

Anticipated Findings

Our predictive model, integrating Fitbit data and social/behavioral factors, may enable early breast cancer risk assessment, offering a non-invasive and continuous monitoring approach. The study may uncover specific lifestyle and behavioral factors that interact with physiological data to influence breast cancer risk. This could lead to the identification of individuals at higher risk, allowing for targeted screening and preventive interventions.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Controlled Tier

Research Team

Owner:

Breast Cancer Diagnosis Prediction

The specific scientific questions that we intend to study when building a predictive model of breast cancer diagnosis using Fitbit data and social/behavioral factors as inputs encompass several key areas. Firstly, we aim to investigate whether Fitbit data, encompassing metrics…

Scientific Questions Being Studied

The specific scientific questions that we intend to study when building a predictive model of breast cancer diagnosis using Fitbit data and social/behavioral factors as inputs encompass several key areas. Firstly, we aim to investigate whether Fitbit data, encompassing metrics like activity levels, heart rate, and sleep patterns, can serve as reliable predictors of breast cancer development. This question is of high importance as it explores the potential of utilizing wearable technology for early breast cancer risk detection, potentially leading to more timely diagnosis and improved patient outcomes. Additionally, we seek to understand the extent to which social factors, including socioeconomic status, healthcare access, and social support, influence breast cancer risk and how they can be incorporated into the predictive model to identify vulnerable populations and tailor prevention efforts.

Project Purpose(s)

  • Disease Focused Research (female breast cancer)
  • Population Health
  • Social / Behavioral

Scientific Approaches

Our study will leverage the "All of Us" dataset, featuring diverse participant data, to develop a predictive breast cancer diagnosis model. We'll use Fitbit data (activity, heart rate, sleep), complemented by socioeconomic status, lifestyle, healthcare access, and historical breast cancer incidence records. We will employ machine learning techniques to explore the complex relationships between these factors and breast cancer risk. Rigorous validation and ethical considerations will be integral, and interdisciplinary collaboration will ensure a holistic approach to enhance breast cancer risk prediction.

Anticipated Findings

Our predictive model, integrating Fitbit data and social/behavioral factors, may enable early breast cancer risk assessment, offering a non-invasive and continuous monitoring approach. The study may uncover specific lifestyle and behavioral factors that interact with physiological data to influence breast cancer risk. This could lead to the identification of individuals at higher risk, allowing for targeted screening and preventive interventions.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Controlled Tier

Research Team

Owner:

Collaborators:

  • Sreeja Puthumana - Graduate Trainee, George Mason University
  • Bhumi Patel - Graduate Trainee, George Mason University

Duplicate of Breast Cancer Diagnosis Prediction

The specific scientific questions that we intend to study when building a predictive model of breast cancer diagnosis using Fitbit data and social/behavioral factors as inputs encompass several key areas. Firstly, we aim to investigate whether Fitbit data, encompassing metrics…

Scientific Questions Being Studied

The specific scientific questions that we intend to study when building a predictive model of breast cancer diagnosis using Fitbit data and social/behavioral factors as inputs encompass several key areas. Firstly, we aim to investigate whether Fitbit data, encompassing metrics like activity levels, heart rate, and sleep patterns, can serve as reliable predictors of breast cancer development. This question is of high importance as it explores the potential of utilizing wearable technology for early breast cancer risk detection, potentially leading to more timely diagnosis and improved patient outcomes. Additionally, we seek to understand the extent to which social factors, including socioeconomic status, healthcare access, and social support, influence breast cancer risk and how they can be incorporated into the predictive model to identify vulnerable populations and tailor prevention efforts.

Project Purpose(s)

  • Disease Focused Research (female breast cancer)
  • Population Health
  • Social / Behavioral

Scientific Approaches

Our study will leverage the "All of Us" dataset, featuring diverse participant data, to develop a predictive breast cancer diagnosis model. We'll use Fitbit data (activity, heart rate, sleep), complemented by socioeconomic status, lifestyle, healthcare access, and historical breast cancer incidence records. We will employ machine learning techniques to explore the complex relationships between these factors and breast cancer risk. Rigorous validation and ethical considerations will be integral, and interdisciplinary collaboration will ensure a holistic approach to enhance breast cancer risk prediction.

Anticipated Findings

Our predictive model, integrating Fitbit data and social/behavioral factors, may enable early breast cancer risk assessment, offering a non-invasive and continuous monitoring approach. The study may uncover specific lifestyle and behavioral factors that interact with physiological data to influence breast cancer risk. This could lead to the identification of individuals at higher risk, allowing for targeted screening and preventive interventions.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Controlled Tier

Research Team

Owner:

Collaborators:

  • Bhumi Patel - Graduate Trainee, George Mason University

Evaluation of Risk Variants in Adult Cancer

Scientific Question: identify sets of germline SNPs that are significantly associated with cancer survival predictions in adults with eye cancer Purpose: This research question is a part of my overall master's in statistics research question which aims to identify variants…

Scientific Questions Being Studied

Scientific Question: identify sets of germline SNPs that are significantly associated with cancer survival predictions in adults with eye cancer

Purpose: This research question is a part of my overall master's in statistics research question which aims to identify variants associated with cancer risk in a set of pediatric cancers including retinoblastomas (RBL). I am training models with data from a set of 200 RBL patients to identify variants associated with cancer risk. Once these variants are identified, I will look for the distribution of these variants in patients within the All of Us Cohort that have eye cancer.

Project Purpose(s)

  • Educational

Scientific Approaches

Datasets: DNA variant data from eye cancer patients and age matched non-cancer controls
Research methods and tools: I plan to use ggplot and other R based software packages to plot the distribution of variants within cases and non-cancer controls. I also plan to look at survival rates between the two groups and will generate survival plots to compare rates of survival between patients that carry putative risk variants identified from our study versus non-cancer controls. The R survival package will be used for this comparison; reference: https://cran.r-project.org/web/packages/survival/index.html

Anticipated Findings

I expect to find a distribution of risk variants uniquely found in cases and not found in controls. The purpose of this analysis is to provide further evidence of risk variants identified within a cohort of retinoblastoma patients. The goal of the overall project is to identify unique variants associated with cancer risk.

Demographic Categories of Interest

  • Age

Data Set Used

Controlled Tier

Research Team

Owner:

Bone Metastasis Study

Will study metastasis of lung cancer

Scientific Questions Being Studied

Will study metastasis of lung cancer

Project Purpose(s)

  • Disease Focused Research (non-small cell lung carcinoma)
  • Population Health
  • Ancestry

Scientific Approaches

Will use methods in basic statistics, survival modeling, machine learning

Anticipated Findings

understanding of disease progression in under-represented minorities

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Controlled Tier

Research Team

Owner:

Collaborators:

  • Lesley Chapman Hannah - Research Fellow, National Cancer Institute (NIH - NCI)
1 - 6 of 6
<
>
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.