Activity Number:
|
551
- Risk Prediction Methods and Applications in Risk Stratified Prevention
|
Type:
|
Invited
|
Date/Time:
|
Wednesday, July 31, 2019 : 2:00 PM to 3:50 PM
|
Sponsor:
|
ENAR
|
Abstract #300459
|
|
Title:
|
Development and Validation of Breast Cancer Risk Prediction Models Using ICARE and Projections for Future Risk Stratification
|
Author(s):
|
Amber Wilcox* and Parichoy Pal Choudhury and Montserrat Garcia-Closas and Nilanjan Chatterjee
|
Companies:
|
National Cancer Institute and National Cancer Institute and National Cancer Institute and Johns Hopkins University
|
Keywords:
|
breast cancer;
iCARE;
model validation;
risk prediction;
risk stratification
|
Abstract:
|
We have developed an R package, called the Individualized Coherent Absolute Risk Estimation (iCARE) tool, that allows researchers to build and validate absolute risk models and apply them to estimate an individual's risk of developing disease during a specified time interval using relative risks, distributions of risk factors, and disease incidence and mortality rates from multiple data sources. It includes advanced features to allow users flexibility to update models based on new risk factors and account for missing risk factors using imputation. The validation component of iCARE allows for comparative evaluation of multiple models across studies using uniform methodology. We have used iCARE to develop two breast cancer risk models that integrate classical risk factors and polygenic risk scores. We validate the performance of these models in predicting five-year absolute risk of breast cancer in 15 independent prospective cohorts of women of European ancestry from six countries. Our risk projections illustrate the levels of risk stratification attained by these models in the populations of those countries.
|
Authors who are presenting talks have a * after their name.