Skip to Main Content

COVID-19 is an emerging, rapidly evolving situation.

What people with cancer should know: https://www.cancer.gov/coronavirus

Get the latest public health information from CDC: https://www.coronavirus.gov

Get the latest research information from NIH: https://www.nih.gov/coronavirus

Principal Investigator
Name
Renee George
Degrees
Ph.D.
Institution
Multimodal Imaging Services Corporation, dba HealthLytix
Position Title
Senior Scientist - Bioinformatics Lead
Email
About this CDAS Project
Study
PLCO (Learn more about this study)
Project ID
PLCO-574
Initial CDAS Request Approval
Jan 30, 2020
Title
Prostate cancer risk prediction using clinical risk factors and genetics
Summary
The goal of this research is to develop and validate a model to predict risk for clinically significant prostate cancer. The model will incorporate clinical risk factors such as prostate-specific antigen, digital rectal exam, family history, and demographics, and a polygenic risk score representing the cumulative effect of 50 genetic variants. We hypothesize that the addition of genetics will greatly improve the predictive ability of our model over models based only on clinical risk factors (e.g. Prostate Cancer Trial Risk Calculator). Our model will use logistic regression to estimate risk for high-grade prostate cancer from clinical risk factors, and will then be updated to incorporate genetic information from a polygenic risk score. Genotypes for PLCO participants will be obtained from the PEGASUS (phs000882.v1.p1) and CGEMS (phs000207.v1.p1) studies in dbGaP. Model performance will be measured using cross-fold validation and compared to existing risk calculators for prostate cancer.
Aims

- Fit a multinomial logistic regression model to predict risk of high-grade prostate cancer (Gleason score >= 7) with clinical risk factors.
- Calculate a polygenic risk score for PLCO participants genotyped through PEGASUS (phs000882.v1.p1) and CGEMS (phs000207.v1.p1), and update the risk model with this information.
- Measure model performance using cross-fold validation and compare to existing risk calculators based only on clinical risk factors.

Collaborators

Chun Fan, Multimodal Imaging Services, dba HealthLytix
Christine Swisher, Multimodal Imaging Services, dba HealthLytix