Genetic Variants Improve Breast Cancer Risk Prediction on Mammograms

AMIA 2013 Annual Symposium

Jie Liu ; MS1 ; David Page ; PhD1 ; Houssam Nassif ; PhD1 ; Jude Shavlik ; PhD1 ; Peggy Peissig ; PhD2 ; Catherine McCarty ; PhD3 ; Adedayo A. Onitilo MD ; MSCR ; FACP 4 ; 2 ; 5 and Elizabeth Burnside ; MD ; MPH ; MS1

PID  :  122607

来源: CEUR

【 摘 要 】

Several recent genomewide association studies have identified genetic variants associated with breast cancer. However, how much these genetic variants may help advance breast cancer risk prediction based on other clinical features, like mammographic findings, is unknown. We conducted a retrospective casecontrol study, collecting mammographic findings and highfrequency/lowpenetrance genetic variants from an existing personalized medicine data repository. A Bayesian network was developed using Tree Augmented Naive Bayes (TAN) by training on the mammographic findings, with and without the 22 genetic variants collected. We analyzed the predictive performance using the area under the ROC curve, and found that the genetic variants significantly improved breast cancer risk prediction on mammograms. We also identified the interaction effect between the genetic variants and collected mammographic findings in an attempt to link genotype to mammographic phenotype to better understand disease