Scott Kulm
Graduate Trainee, Cornell University
3 active projects
Prostate Cancer
Scientific Questions Being Studied
This workspace is designed to investigate the efficacy of genetic predictions for Prostate Cancer. Often times genetic predictions are more efficacious for people of European ancestry. We would like to see if genetic predictions generated from recently developed methods can break this trend and work equitably for people of all groups and backgrounds.
Project Purpose(s)
- Disease Focused Research (prostate cancer)
Scientific Approaches
We will initially just survey the number of prostate cancer cases across different populations. If the sample sizes are sufficient we will generate polygenic risk scores, then lastly compare these scores against the case status within logistic regression models.
Anticipated Findings
If sample sizes are sufficient, we hypothesize that our polygenic risk scores, which are generated from newer, advanced methods, will perform with greater equability than former polygenic risk scores. This finding would contribute to the larger scientific field by definitely proving polygenic risk scores have the potential to work well across populations, and specifically which underlying method is the best to use.
Demographic Categories of Interest
- Race / Ethnicity
Data Set Used
Controlled TierCRC and CBC
Scientific Questions Being Studied
The goal of the project is to use machine learning algorithms to predict colorectal cancer risk by monitoring complete blood counts.
Project Purpose(s)
- Disease Focused Research (colorectal cancer)
- Educational
- Commercial
Scientific Approaches
We plan to use various machine learning algorithms from SciKit Learn to predict those with onset of colorectal cancer by monitoring complete blood counts.
Anticipated Findings
We hope to find that by monitoring complete blood counts that we will be able to improve screening for individuals with a higher predictive risk of developing colorectal cancer.
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set Used
Registered TierResearch Team
Owner:
- Scott Kulm - Graduate Trainee, Cornell University
- Matthew Wickersham - Graduate Trainee, Cornell University
African American Prostate Cancer Polygenic Risk Score - WCM SPORE
Scientific Questions Being Studied
build a multiethnic polygenic risk score for prostate cancer onset, and identify modifiable risk factors associated with the score. this is important for disease screening and public health
Project Purpose(s)
- Disease Focused Research (prostate cancer)
Scientific Approaches
generate a polygenic risk score from all of us data and publicly available gwas summary statistics. regression models will be used to achieve these aims
Anticipated Findings
expect to a cross-ancestry risk model that can be deployed for preventative measures. existing models have poor cross-ancestry portability
Demographic Categories of Interest
- Race / Ethnicity
Data Set Used
Registered TierResearch Team
Owner:
- Yajas Shah - Graduate Trainee, Cornell University
- Scott Kulm - Graduate Trainee, Cornell University
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.