Gordon Ye
Undergraduate Student, University of California, San Diego
11 active projects
Social Determinants and Healthcare Access in Eye Conditions - v5 Dataset
Scientific Questions Being Studied
We are planning to explore disparities in healthcare access and utilization for patients with eye conditions across different demographic groups. We would like to evaluate risk of developing advanced/severe disease in different eye conditions, and understand how social determinants contribute to this risk while adjusting for other known risk factors. We are also interested in understanding the availability of social determinants of health data in this data repository compared to EHR clinical data warehouses alone.
Project Purpose(s)
- Population Health
Scientific Approaches
We will build cohorts of patients with various eye diseases (i.e. diabetic retinopathy, retinal vein occlusions, glaucoma, etc.). Then we will develop concept sets and extract data on outcomes (i.e. development of complications), as well as predictors including clinical data and social data. We will draw on survey data and EHR data within All of Us. When genomic data and wearable data become available, we are interested in evaluating those data sources as well. We will use statistical modeling and machine learning to generate predictive models.
Anticipated Findings
We anticipate that there may be differential risk for developing complications based on disparities in healthcare access and utilization for patients with eye conditions.
Demographic Categories of Interest
- Race / Ethnicity
- Age
- Geography
- Disability Status
- Access to Care
- Education Level
- Income Level
Data Set Used
Registered TierResearch Team
Owner:
- Varsha Varkhedi - Undergraduate Student, University of California, San Diego
- Terrence Lee - Graduate Trainee, University of California, San Diego
- Sally Baxter - Research Fellow, University of California, San Diego
- Niloofar Radgoudarzi - Graduate Trainee, University of California, San Diego
- John McDermott - Graduate Trainee, University of California, San Diego
- Grace Ahn - Graduate Trainee, University of California, San Diego
- Gordon Ye - Undergraduate Student, University of California, San Diego
- Alison Chan - Graduate Trainee, University of California, San Diego
- Bita Shahrvini - Graduate Trainee, University of California, San Diego
- Bharanidharan Radha Saseendrakumar - Project Personnel, University of California, San Diego
- Arash Delavar - Research Fellow, Baylor College of Medicine
Collaborators:
- Joy Guo - Graduate Trainee, University of California, San Diego
- Alireza Kamalipour - Research Fellow, University of California, San Diego
- Priyanka Soe - Project Personnel, University of California, San Diego
- Mahasweta Nayak - Undergraduate Student, University of California, San Diego
- Cecilia Vallejos - Undergraduate Student, University of California, San Diego
- Albert Sohn - Graduate Trainee, Washington State University
Problematic Alcohol Use and Related Psychiatric and Cardiometabolic Conditions
Scientific Questions Being Studied
The aim of this proposal is to identify new genetic and non-genetic factors that are leveraged through a machine-learning based approach to predict individual 1) risk for problematic alcohol use, 2) outcome from problematic alcohol use (e.g., recurrence of alcohol-related hospitalization or death), and 3) genetic and non-genetic alcohol risk factors that are shared with other psychiatric diseases and obesity-related cardiometabolic phenotypes. Prediction will utilize a combination of genetic, clinical, and lifestyle risk factors. Ultimately, we aim to identify not only individual predictors, but build a novel risk prediction model that improves on currently developed polygenic risk scores, which show clinical promise, but have methodological shortcomings that limit their accuracy.
Project Purpose(s)
- Disease Focused Research (alcohol misuse and associated diseases)
- Social / Behavioral
- Ancestry
Scientific Approaches
We are integrating data from the UK Biobank and the NIH All of Us Research Program. We will conduct genome-wide studies (GWAS) with REGENIE or Tractor to identify new variants associated with our alcohol use phenotypes. Potential clinical predictors will be identified from literature and machine learning (e.g., gradient boosting) analyses of separate lifestyle domains. For individual risk prediction, we will use neural networks to reduce the dimensionality of genetic data into interpretable independent latent factors, demonstrate that the latent factors recapitulate the alcohol-related GWAS associations that we identified, before finally using the latent factors in a multi-layer perceptron model to predict broad alcohol use phenotypes. We will also use neural networks to predict different sub-components of problematic alcohol use and negative alcohol use outcomes. Similar stepwise approaches will be performed for Mondrian cross-conformal prediction and gradient boosting classification.
Anticipated Findings
There is growing interest in using genetic risk scores in clinical practice, especially for decision making surrounding early intervention in high-risk individuals as well as triaging alcohol- and cardiometabolic-risk after an alcohol-related medical event for increased follow-up. Current genetic risk models can stratify individuals into large buckets of risk, but many of these methods discard useful information in favor of simple models or fail to generalize to real-world settings. A further limitation broadly plaguing the field of genomics research is the drastic overrepresentation of individuals of white European ancestry. By leveraging the diversity of the All of Us Research Program, we seek to build reproducible and equitable risk prediction models that may benefit a diverse patient population.
Demographic Categories of Interest
- Race / Ethnicity
- Gender Identity
- Geography
- Education Level
- Income Level
Data Set Used
Controlled TierResearch Team
Owner:
- Gordon Ye - Undergraduate Student, University of California, San Diego
- Eric Zorrilla - Early Career Tenure-track Researcher, Scripps Research
Collaborators:
- Sandra Sanchez-Roige - Early Career Tenure-track Researcher, University of California, San Diego
- Emily Zhu - Other, Scripps Research
- John Huber - Other, Scripps Research
- Jennifer Zhang - Project Personnel, All of Us Program Operational Use
- Eli Browne - Other, Scripps Research
- Bhadra Rupesh - Other, Scripps Research
- Paulina Ai - Other, Scripps Research
Problematic Alcohol Use and Related Psychiatric and Cardiometabolic Conditions 7
Scientific Questions Being Studied
The aim of this proposal is to identify new genetic and non-genetic factors that are leveraged through a machine-learning based approach to predict individual 1) risk for problematic alcohol use, 2) outcome from problematic alcohol use (e.g., recurrence of alcohol-related hospitalization or death), and 3) genetic and non-genetic alcohol risk factors that are shared with other psychiatric diseases and obesity-related cardiometabolic phenotypes. Prediction will utilize a combination of genetic, clinical, and lifestyle risk factors. Ultimately, we aim to identify not only individual predictors, but build a novel risk prediction model that improves on currently developed polygenic risk scores, which show clinical promise, but have methodological shortcomings that limit their accuracy.
Project Purpose(s)
- Disease Focused Research (alcohol misuse and associated diseases)
- Social / Behavioral
- Ancestry
Scientific Approaches
We are integrating data from the UK Biobank and the NIH All of Us Research Program. We will conduct genome-wide studies (GWAS) with REGENIE or Tractor to identify new variants associated with our alcohol use phenotypes. Potential clinical predictors will be identified from literature and machine learning (e.g., gradient boosting) analyses of separate lifestyle domains. For individual risk prediction, we will use neural networks to reduce the dimensionality of genetic data into interpretable independent latent factors, demonstrate that the latent factors recapitulate the alcohol-related GWAS associations that we identified, before finally using the latent factors in a multi-layer perceptron model to predict broad alcohol use phenotypes. We will also use neural networks to predict different sub-components of problematic alcohol use and negative alcohol use outcomes. Similar stepwise approaches will be performed for Mondrian cross-conformal prediction and gradient boosting classification.
Anticipated Findings
There is growing interest in using genetic risk scores in clinical practice, especially for decision making surrounding early intervention in high-risk individuals as well as triaging alcohol- and cardiometabolic-risk after an alcohol-related medical event for increased follow-up. Current genetic risk models can stratify individuals into large buckets of risk, but many of these methods discard useful information in favor of simple models or fail to generalize to real-world settings. A further limitation broadly plaguing the field of genomics research is the drastic overrepresentation of individuals of white European ancestry. By leveraging the diversity of the All of Us Research Program, we seek to build reproducible and equitable risk prediction models that may benefit a diverse patient population.
Demographic Categories of Interest
- Race / Ethnicity
- Gender Identity
- Geography
- Education Level
- Income Level
Data Set Used
Controlled TierResearch Team
Owner:
- Gordon Ye - Undergraduate Student, University of California, San Diego
- Eric Zorrilla - Early Career Tenure-track Researcher, Scripps Research
Collaborators:
- Sandra Sanchez-Roige - Early Career Tenure-track Researcher, University of California, San Diego
- Emily Zhu - Other, Scripps Research
- John Huber - Other, Scripps Research
- Jennifer Zhang - Project Personnel, All of Us Program Operational Use
- Eli Browne - Other, Scripps Research
- Bhadra Rupesh - Other, Scripps Research
- Paulina Ai - Other, Scripps Research
SDHA in Eye Conditions - v6 Dataset
Scientific Questions Being Studied
We are planning to explore disparities in healthcare access and utilization for patients with eye conditions across different demographic groups. We would like to evaluate risk of developing advanced/severe disease in different eye conditions, and understand how social determinants contribute to this risk while adjusting for other known risk factors. We are also interested in understanding the availability of social determinants of health data in this data repository compared to EHR clinical data warehouses alone.
Project Purpose(s)
- Population Health
Scientific Approaches
We will build cohorts of patients with various eye diseases (i.e. diabetic retinopathy, retinal vein occlusions, glaucoma, etc.). Then we will develop concept sets and extract data on outcomes (i.e. development of complications), as well as predictors including clinical data and social data. We will draw on survey data and EHR data within All of Us. When genomic data and wearable data become available, we are interested in evaluating those data sources as well. We will use statistical modeling and machine learning to generate predictive models.
Anticipated Findings
We anticipate that there may be differential risk for developing complications based on disparities in healthcare access and utilization for patients with eye conditions.
Demographic Categories of Interest
- Race / Ethnicity
- Age
- Geography
- Disability Status
- Access to Care
- Education Level
- Income Level
Data Set Used
Registered TierResearch Team
Owner:
- Varsha Varkhedi - Undergraduate Student, University of California, San Diego
- Tonya Lee - Graduate Trainee, University of California, San Diego
- Sophia Sidhu - Graduate Trainee, University of California, San Diego
- Sally Baxter - Research Fellow, University of California, San Diego
- Kaela Acuff - Graduate Trainee, University of California, San Diego
- Gordon Ye - Undergraduate Student, University of California, San Diego
- Catherine Sheils - Research Fellow, University of California, San Diego
- Bita Shahrvini - Graduate Trainee, University of California, San Diego
- Bharanidharan Radha Saseendrakumar - Project Personnel, University of California, San Diego
- Arash Delavar - Research Fellow, Baylor College of Medicine
Collaborators:
- Joy Guo - Graduate Trainee, University of California, San Diego
- Bonnie Huang - Graduate Trainee, Northwestern University
- Kiana Tavakoli - Research Fellow, University of California, San Diego
Meta-analysis of tobacco use disorders and associations with health outcomes
Scientific Questions Being Studied
Tobacco use disorders (TUD) are the most prevalent substance use disorder in the US, with a high proportion of smokers meeting criteria for dependence. These individuals often have difficulty quitting, experience withdrawal symptoms, and continue smoking despite negative mental, social, and medical consequences. Genetic factors influence smoking behaviors and strides have been made in understanding aspects of tobacco initiation and use via genome-wide association studies (GWAS). However existing GWAS of TUD and nicotine-related traits have small sample sizes and focus on individuals of European ancestry. We performed a cross-ancestral meta-analysis of TUD in 740,361 individuals of European, African American, and Latin American ancestries and hope to replicate some of the main findings using All of Us, and evaluate what are the social and medical outcomes associated with genetic liability to TUD.
Project Purpose(s)
- Disease Focused Research (tobacco use disorders)
- Ancestry
Scientific Approaches
We will perform genetic associations of loci implicated in our study in the AllOfUs dataset using REGINIE, accounting for relevant covariates and principal components of genetic ancestry. We will test associations with smoking traits as well as other comorbid traits.
Anticipated Findings
This work will furthers our biological understanding of TUD and its shared genetic risk with other mental and physical traits, and establish EHR as useful sources of phenotypic information for studying the genetics of TUD.
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Controlled TierResearch Team
Owner:
- Sandra Sanchez-Roige - Early Career Tenure-track Researcher, University of California, San Diego
- Gordon Ye - Undergraduate Student, University of California, San Diego
Collaborators:
- John Meredith - Project Personnel, University of California, San Diego
Original - Social Determinants and Healthcare Access in Eye Conditions
Scientific Questions Being Studied
We are planning to explore disparities in healthcare access and utilization for patients with eye conditions across different demographic groups. We would like to evaluate risk of developing advanced/severe disease in different eye conditions, and understand how social determinants contribute to this risk while adjusting for other known risk factors. We are also interested in understanding the availability of social determinants of health data in this data repository compared to EHR clinical data warehouses alone.
Project Purpose(s)
- Population Health
Scientific Approaches
We will build cohorts of patients with various eye diseases (i.e. diabetic retinopathy, retinal vein occlusions, glaucoma, etc.). Then we will develop concept sets and extract data on outcomes (i.e. development of complications), as well as predictors including clinical data and social data. We will draw on survey data and EHR data within All of Us. When genomic data and wearable data become available, we are interested in evaluating those data sources as well. We will use statistical modeling and machine learning to generate predictive models.
Anticipated Findings
We anticipate that there may be differential risk for developing complications based on disparities in healthcare access and utilization for patients with eye conditions.
Demographic Categories of Interest
- Race / Ethnicity
- Age
- Geography
- Disability Status
- Access to Care
- Education Level
- Income Level
Data Set Used
Registered TierResearch Team
Owner:
- Terrence Lee - Graduate Trainee, University of California, San Diego
- Sally Baxter - Research Fellow, University of California, San Diego
- John McDermott - Graduate Trainee, University of California, San Diego
- Grace Ahn - Graduate Trainee, University of California, San Diego
- Gordon Ye - Undergraduate Student, University of California, San Diego
- Alison Chan - Graduate Trainee, University of California, San Diego
- Bita Shahrvini - Graduate Trainee, University of California, San Diego
- Bharanidharan Radha Saseendrakumar - Project Personnel, University of California, San Diego
- Arash Delavar - Research Fellow, Baylor College of Medicine
Collaborators:
- Hua Ou - Mid-career Tenured Researcher, National Institute of Child Health and Human Development (NIH - NICHD)
SDHA in Eye Conditions - v5 Dataset
Scientific Questions Being Studied
We are planning to explore disparities in healthcare access and utilization for patients with eye conditions across different demographic groups. We would like to evaluate risk of developing advanced/severe disease in different eye conditions, and understand how social determinants contribute to this risk while adjusting for other known risk factors. We are also interested in understanding the availability of social determinants of health data in this data repository compared to EHR clinical data warehouses alone.
Project Purpose(s)
- Population Health
Scientific Approaches
We will build cohorts of patients with various eye diseases (i.e. diabetic retinopathy, retinal vein occlusions, glaucoma, etc.). Then we will develop concept sets and extract data on outcomes (i.e. development of complications), as well as predictors including clinical data and social data. We will draw on survey data and EHR data within All of Us. When genomic data and wearable data become available, we are interested in evaluating those data sources as well. We will use statistical modeling and machine learning to generate predictive models.
Anticipated Findings
We anticipate that there may be differential risk for developing complications based on disparities in healthcare access and utilization for patients with eye conditions.
Demographic Categories of Interest
- Race / Ethnicity
- Age
- Geography
- Disability Status
- Access to Care
- Education Level
- Income Level
Data Set Used
Registered TierResearch Team
Owner:
- Terrence Lee - Graduate Trainee, University of California, San Diego
- Tonya Lee - Graduate Trainee, University of California, San Diego
- Sophia Sidhu - Graduate Trainee, University of California, San Diego
- Sally Baxter - Research Fellow, University of California, San Diego
- Kaela Acuff - Graduate Trainee, University of California, San Diego
- John McDermott - Graduate Trainee, University of California, San Diego
- Grace Ahn - Graduate Trainee, University of California, San Diego
- Gordon Ye - Undergraduate Student, University of California, San Diego
- Alison Chan - Graduate Trainee, University of California, San Diego
- Bita Shahrvini - Graduate Trainee, University of California, San Diego
- Bharanidharan Radha Saseendrakumar - Project Personnel, University of California, San Diego
- Arash Delavar - Research Fellow, Baylor College of Medicine
Collaborators:
- Francis Ratsimbazafy - Other, All of Us Program Operational Use
- Jun Qian - Other, All of Us Program Operational Use
- Joy Guo - Graduate Trainee, University of California, San Diego
- Bonnie Huang - Graduate Trainee, Northwestern University
Depression Fitbit Study (Clinical Phenotyping)
Scientific Questions Being Studied
Major depressive disorder (MDD) is associated with changes in physical activity, fidgeting/restlessness, energy levels, and sleep patterns. It has also been established that most MDD patients have recurrent episodes, separated by periods of "remission" that may last 2 months or more. The purpose of this study is to assess the ability of the Fitbit data to longitudinally distinguish individuals with and without a depression diagnosis during a transitional phase coded in the medical record (i.e., a new or change in diagnostic code). We will focus primarily on daily physical activity (minutes of activity, steps traveled, elevation traveled), energy expenditure (calories burned), and heart rate.
Project Purpose(s)
- Disease Focused Research (major depressive disorder)
- Social / Behavioral
Scientific Approaches
We will build datasets and cohorts of individuals meeting the MDD/depression diagnostic criteria, as well as subsets for severity and additional modifiers. We will perform time series analysis of the Fitbit data with machine learning models, and assess their performance in the above questions. We will look specifically for trends and patterns in the time series Fitbit data that may be unique to the MDD/depression group.
Anticipated Findings
Consumer-grade technology has been pushing into the field of health and wellness. While previous studies have evaluated the performance of wearables in psychiatric and cardiovascular diseases, few have the sample sizes or data collection lengths made possible by the All of Us. We know that MDD comes with it changes in physical activity, and positive results may reinforce the role of wearable technology as a confirmatory step in the diagnostic process. Null results, on the other hand, will highlight the unique challenges of consumer health-related technologies, especially as these devices are becoming more and more common.
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Registered TierResearch Team
Owner:
- Sally Baxter - Research Fellow, University of California, San Diego
- Gordon Ye - Undergraduate Student, University of California, San Diego
- Bharanidharan Radha Saseendrakumar - Project Personnel, University of California, San Diego
Collaborators:
- Tonya Lee - Graduate Trainee, University of California, San Diego
Depression Fitbit Study (PHQ-9 Phenotyping)
Scientific Questions Being Studied
Depression is associated with changes in physical activity, fidgeting/restlessness, energy levels, and sleep patterns. It has also been established that most depression patients have recurrent episodes, separated by periods of "remission" that may last 2 months or more. The purpose of this study is to assess the ability of longitudinal Fitbit data to identify individuals with worsening symptoms of depression, and those potentially entering a depressive episode using longitudinal PHQ-9 survey responses, a standard and validated depression screening tool. We will focus primarily on daily physical activity (minutes of activity, steps traveled, elevation traveled), energy expenditure (calories burned), and heart rate.
Project Purpose(s)
- Disease Focused Research (major depressive disorder)
- Social / Behavioral
- Educational
Scientific Approaches
We will extract Fitbit data from participants who have responded to the PHQ-9 questions administered as part of the COPE survey. We will first compute PHQ-9 scores to stratify individuals by depression severity (or healthy control status). We will then train and evaluate machine learning models using the Fitbit data prior to PHQ-9 survey completion to predict the onset of worsening depressive symptoms and potential depressive episodes.
Anticipated Findings
Consumer-grade technology including smartwatches has been pushing into the field of health and wellness. While previous studies have evaluated the utility of mobile health (mHealth) technologies, few have the sample sizes or data collection lengths made possible by the All of Us. This is particularly the case for mHealth research in psychiatric diseases: the vast majority focus on data collected from small cohorts that may not be representative of real-world diversity. We know that depression comes with it changes in physical activity, and positive results may reinforce the role of wearable technology as a confirmatory or early detection step in the diagnostic process. Null results, on the other hand, will highlight the unique challenges of consumer health-related technologies despite their adoption by the public.
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Controlled TierResearch Team
Owner:
- Gordon Ye - Undergraduate Student, University of California, San Diego
- Bharanidharan Radha Saseendrakumar - Project Personnel, University of California, San Diego
Collaborators:
- Prothit Halder - Undergraduate Student, Scripps Research
- Nolan Chai - Undergraduate Student, University of California, San Diego
- Natalie Kwong - Undergraduate Student, University of California, San Diego
SDHA in Eye Conditions - v4 Dataset
Scientific Questions Being Studied
We are planning to explore disparities in healthcare access and utilization for patients with eye conditions across different demographic groups. We would like to evaluate risk of developing advanced/severe disease in different eye conditions, and understand how social determinants contribute to this risk while adjusting for other known risk factors. We are also interested in understanding the availability of social determinants of health data in this data repository compared to EHR clinical data warehouses alone.
Project Purpose(s)
- Population Health
Scientific Approaches
We will build cohorts of patients with various eye diseases (i.e. diabetic retinopathy, retinal vein occlusions, glaucoma, etc.). Then we will develop concept sets and extract data on outcomes (i.e. development of complications), as well as predictors including clinical data and social data. We will draw on survey data and EHR data within All of Us. When genomic data and wearable data become available, we are interested in evaluating those data sources as well. We will use statistical modeling and machine learning to generate predictive models.
Anticipated Findings
We anticipate that there may be differential risk for developing complications based on disparities in healthcare access and utilization for patients with eye conditions.
Demographic Categories of Interest
- Race / Ethnicity
- Age
- Geography
- Disability Status
- Access to Care
- Education Level
- Income Level
Data Set Used
Registered TierResearch Team
Owner:
- Terrence Lee - Graduate Trainee, University of California, San Diego
- Sally Baxter - Research Fellow, University of California, San Diego
- John McDermott - Graduate Trainee, University of California, San Diego
- Grace Ahn - Graduate Trainee, University of California, San Diego
- Gordon Ye - Undergraduate Student, University of California, San Diego
- Alison Chan - Graduate Trainee, University of California, San Diego
- Bita Shahrvini - Graduate Trainee, University of California, San Diego
- Bharanidharan Radha Saseendrakumar - Project Personnel, University of California, San Diego
- Arash Delavar - Research Fellow, Baylor College of Medicine
Social Determinants and Healthcare Access in Eye Conditions - v4 Dataset
Scientific Questions Being Studied
We are planning to explore disparities in healthcare access and utilization for patients with eye conditions across different demographic groups. We would like to evaluate risk of developing advanced/severe disease in different eye conditions, and understand how social determinants contribute to this risk while adjusting for other known risk factors. We are also interested in understanding the availability of social determinants of health data in this data repository compared to EHR clinical data warehouses alone.
Project Purpose(s)
- Population Health
Scientific Approaches
We will build cohorts of patients with various eye diseases (i.e. diabetic retinopathy, retinal vein occlusions, glaucoma, etc.). Then we will develop concept sets and extract data on outcomes (i.e. development of complications), as well as predictors including clinical data and social data. We will draw on survey data and EHR data within All of Us. When genomic data and wearable data become available, we are interested in evaluating those data sources as well. We will use statistical modeling and machine learning to generate predictive models.
Anticipated Findings
We anticipate that there may be differential risk for developing complications based on disparities in healthcare access and utilization for patients with eye conditions.
Demographic Categories of Interest
- Race / Ethnicity
- Age
- Geography
- Disability Status
- Access to Care
- Education Level
- Income Level
Data Set Used
Registered TierResearch Team
Owner:
- Terrence Lee - Graduate Trainee, University of California, San Diego
- Sally Baxter - Research Fellow, University of California, San Diego
- John McDermott - Graduate Trainee, University of California, San Diego
- Grace Ahn - Graduate Trainee, University of California, San Diego
- Gordon Ye - Undergraduate Student, University of California, San Diego
- Alison Chan - Graduate Trainee, University of California, San Diego
- Bita Shahrvini - Graduate Trainee, University of California, San Diego
- Bharanidharan Radha Saseendrakumar - Project Personnel, University of California, San Diego
- Arash Delavar - Research Fellow, Baylor College of Medicine
Collaborators:
- Priyanka Soe - Project Personnel, University of California, San Diego
- Mahasweta Nayak - Undergraduate Student, University of California, San Diego
- Cecilia Vallejos - Undergraduate Student, University of California, San Diego
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.