Haben Yhdego
Research Fellow, University of California, San Diego
3 active projects
MED264_AKI_Readmission
Scientific Questions Being Studied
We'd like to study what features (including social determinants of health) contribute to readmission in patients with acute kidney injury (AKI). Understanding these features is important since the ability to proactively identify readmission risk could lead to improved consultation & follow-up for high-risk patients.
Project Purpose(s)
- Disease Focused Research (Acute Kidney Injury)
- Educational
Scientific Approaches
We'll be analyzing subsequent visits and looking at a range of features including vital signs, laboratory measurements, and survey responses. We anticipate we'll be using the PERSON, VISIT_OCCURRENCE, MEASUREMENT, and OBSERVATION tables. From these features we'll apply logistic regression and deep learning to build a predictive model for readmission risk. We'll identify the corresponding importance of features using odd-ratios or SHAP values.
Anticipated Findings
We anticipate that we'll be able to achieve a performant predictive model for the readmission of patients with AKI. To our knowledge this is the first such study conducted on All of Us.
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Registered TierResearch Team
Owner:
- Haben Yhdego - Research Fellow, University of California, San Diego
- Arshia Nayebnazar - Other, University of California, San Diego
- Aaron Boussina - Graduate Trainee, University of California, San Diego
Collaborators:
- Fatemeh Amrollahi - Graduate Trainee, University of California, San Diego
- Shamim Nemati - Early Career Tenure-track Researcher, University of California, San Diego
V6 - MED264_AKI_Readmission_Group
Scientific Questions Being Studied
We'd like to study what features (including social determinants of health) contribute to readmission in patients with acute kidney injury (AKI). Understanding these features is important since the ability to proactively identify readmission risk could lead to improved consultation & follow-up for high-risk patients.
Project Purpose(s)
- Disease Focused Research (Acute Kidney Injury)
- Educational
Scientific Approaches
We'll be analyzing subsequent visits and looking at a range of features including vital signs, laboratory measurements, and survey responses. We anticipate we'll be using the PERSON, VISIT_OCCURRENCE, MEASUREMENT, and OBSERVATION tables. From these features we'll apply logistic regression and deep learning to build a predictive model for readmission risk. We'll identify the corresponding importance of features using odd-ratios or SHAP values.
Anticipated Findings
We anticipate that we'll be able to achieve a performant predictive model for the readmission of patients with AKI. To our knowledge this is the first such study conducted on All of Us.
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Registered TierResearch Team
Owner:
- Haben Yhdego - Research Fellow, University of California, San Diego
- Arshia Nayebnazar - Other, University of California, San Diego
- Aaron Boussina - Graduate Trainee, University of California, San Diego
Collaborators:
- Fatemeh Amrollahi - Graduate Trainee, University of California, San Diego
6 - MED264_MSE_AKI_Readmission_Group
Scientific Questions Being Studied
We'd like to study what features (including social determinants of health) contribute to readmission in patients with acute kidney injury (AKI). Understanding these features is important since the ability to proactively identify readmission risk could lead to improved consultation & follow-up for high-risk patients.
Project Purpose(s)
- Disease Focused Research (Acute Kidney Injury)
- Educational
Scientific Approaches
We'll be analyzing subsequent visits and looking at a range of features including vital signs, laboratory measurements, and survey responses. We anticipate we'll be using the PERSON, VISIT_OCCURRENCE, MEASUREMENT, and OBSERVATION tables. From these features we'll apply logistic regression and deep learning to build a predictive model for readmission risk. We'll identify the corresponding importance of features using odd-ratios or SHAP values.
Anticipated Findings
We anticipate that we'll be able to achieve a performant predictive model for the readmission of patients with AKI. To our knowledge this is the first such study conducted on All of Us.
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Registered TierRequest 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.
