Limits...
New genetic variants improve personalized breast cancer diagnosis.

Liu J, Page D, Peissig P, McCarty C, Onitilo AA, Trentham-Dietz A, Burnside E - AMIA Jt Summits Transl Sci Proc (2014)

Bottom Line: Recent large-scale genome-wide association studies (GWAS) have identified a number of new genetic variants associated with breast cancer.A naïve Bayes model was developed on the mammography features and these genetic variants.We observed that the incorporation of the genetic variants significantly improved breast cancer diagnosis based on mammographic findings.

View Article: PubMed Central - PubMed

Affiliation: University of Wisconsin, Madison, WI, US.

ABSTRACT
Recent large-scale genome-wide association studies (GWAS) have identified a number of new genetic variants associated with breast cancer. However, the degree to which these genetic variants improve breast cancer diagnosis in concert with mammography remains unknown. We conducted a case-control study and collected mammography features and 77 genetic variants which reflect the state of the art GWAS findings on breast cancer. A naïve Bayes model was developed on the mammography features and these genetic variants. We observed that the incorporation of the genetic variants significantly improved breast cancer diagnosis based on mammographic findings.

No MeSH data available.


Related in: MedlinePlus

The ROC and PR curves for the three genetic models.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4333695&req=5

f2-1840407: The ROC and PR curves for the three genetic models.

Mentions: Furthermore, we compare the discriminative power of the three genetic models, namely the Genetic-10 model, the Genetic-22 model and the Genetic-77 model. The ROC curves and the PR curves for the three genetic models are provided in Figure 2, respectively. For each model, we vertically average the curves from the 10-fold cross-valuation to obtain the final curve. The area under the ROC curves for the Genetic-10 model, the Genetic-22 model and the Genetic-77 model are 0.591, 0.622 and 0.684, which demonstrates that the more associated SNPs the genetic model includes, the more discriminative the model becomes. We also use a two-sided paired t-test to compare the area under the ROC curves yielded by the three genetic models. The Genetic-77 model outperforms both the Genetic-22 model (P=0.028) and the Genetic-10 model (P=0.0068).


New genetic variants improve personalized breast cancer diagnosis.

Liu J, Page D, Peissig P, McCarty C, Onitilo AA, Trentham-Dietz A, Burnside E - AMIA Jt Summits Transl Sci Proc (2014)

The ROC and PR curves for the three genetic models.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4333695&req=5

f2-1840407: The ROC and PR curves for the three genetic models.
Mentions: Furthermore, we compare the discriminative power of the three genetic models, namely the Genetic-10 model, the Genetic-22 model and the Genetic-77 model. The ROC curves and the PR curves for the three genetic models are provided in Figure 2, respectively. For each model, we vertically average the curves from the 10-fold cross-valuation to obtain the final curve. The area under the ROC curves for the Genetic-10 model, the Genetic-22 model and the Genetic-77 model are 0.591, 0.622 and 0.684, which demonstrates that the more associated SNPs the genetic model includes, the more discriminative the model becomes. We also use a two-sided paired t-test to compare the area under the ROC curves yielded by the three genetic models. The Genetic-77 model outperforms both the Genetic-22 model (P=0.028) and the Genetic-10 model (P=0.0068).

Bottom Line: Recent large-scale genome-wide association studies (GWAS) have identified a number of new genetic variants associated with breast cancer.A naïve Bayes model was developed on the mammography features and these genetic variants.We observed that the incorporation of the genetic variants significantly improved breast cancer diagnosis based on mammographic findings.

View Article: PubMed Central - PubMed

Affiliation: University of Wisconsin, Madison, WI, US.

ABSTRACT
Recent large-scale genome-wide association studies (GWAS) have identified a number of new genetic variants associated with breast cancer. However, the degree to which these genetic variants improve breast cancer diagnosis in concert with mammography remains unknown. We conducted a case-control study and collected mammography features and 77 genetic variants which reflect the state of the art GWAS findings on breast cancer. A naïve Bayes model was developed on the mammography features and these genetic variants. We observed that the incorporation of the genetic variants significantly improved breast cancer diagnosis based on mammographic findings.

No MeSH data available.


Related in: MedlinePlus