Limits...
Can multiple SNP testing in BRCA2 and BRCA1 female carriers be used to improve risk prediction models in conjunction with clinical assessment?

Prosperi MC, Ingham SL, Howell A, Lalloo F, Buchan IE, Evans DG - BMC Med Inform Decis Mak (2014)

Bottom Line: Multivariable Cox proportional hazards models were fit in the separate BRCA datasets and in menopausal stages screening different combinations of clinical/demographic/genetic variables.Random survival forests did not yield higher performance compared to Cox proportional hazards.We found improvement in prediction performance when coupling the genetic SNP score with clinical/demographic markers, which warrants further investigation.

View Article: PubMed Central - PubMed

Affiliation: Institute of Population Health, Centre for Health Informatics, University of Manchester, Manchester, UK. mattia.prosperi@manchester.ac.uk.

ABSTRACT

Background: Several single nucleotide polymorphisms (SNPs) at different loci have been associated with breast cancer susceptibility, accounting for around 10% of the familial component. Recent studies have found direct associations between specific SNPs and breast cancer in BRCA1/2 mutation carriers. Our aim was to determine whether validated susceptibility SNP scores improve the predictive ability of risk models in comparison/conjunction to other clinical/demographic information.

Methods: Female BRCA1/2 carriers were identified from the Manchester genetic database, and included in the study regardless of breast cancer status or age. DNA was extracted from blood samples provided by these women and used for gene and SNP profiling. Estimates of survival were examined with Kaplan-Meier curves. Multivariable Cox proportional hazards models were fit in the separate BRCA datasets and in menopausal stages screening different combinations of clinical/demographic/genetic variables. Nonlinear random survival forests were also fit to identify relevant interactions. Models were compared using Harrell's concordance index (1 - c-index).

Results: 548 female BRCA1 mutation carriers and 523 BRCA2 carriers were identified from the database. Median Kaplan-Meier estimate of survival was 46.0 years (44.9-48.1) for BRCA1 carriers and 48.9 (47.3-50.4) for BRCA2. By fitting Cox models and random survival forests, including both a genetic SNP score and clinical/demographic variables, average 1 - c-index values were 0.221 (st.dev. 0.019) for BRCA1 carriers and 0.215 (st.dev. 0.018) for BRCA2 carriers.

Conclusions: Random survival forests did not yield higher performance compared to Cox proportional hazards. We found improvement in prediction performance when coupling the genetic SNP score with clinical/demographic markers, which warrants further investigation.

Show MeSH

Related in: MedlinePlus

Model selection results forBRCA1(upper panel) andBRCA2(lower panel) data sets, comparing AUROC performance of Cox regression models (i) through (vi) and random survival forest (RSF). Time points correspond to the quartiles of the overall population observation time distribution. Curves drawn upon out-of-bag predictions (15 resampled sets).
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4197237&req=5

Fig3: Model selection results forBRCA1(upper panel) andBRCA2(lower panel) data sets, comparing AUROC performance of Cox regression models (i) through (vi) and random survival forest (RSF). Time points correspond to the quartiles of the overall population observation time distribution. Curves drawn upon out-of-bag predictions (15 resampled sets).

Mentions: When applying models (i) through (vi) and RSF on the whole BRCA1 population, using the out-of-bag estimator, average (st. dev.) 1 - c-index values of models were (see Table 3), respectively, 0.468 (0.037), 0.221 (0.019), 0.504 (0.026), 0.238 (0.019), 0.222 (0.019), 0.236 (0.018), 0.243 (0.019). When applying models (i) through (vi) and RSF on the whole BRCA2 population, using the out-of-bag estimator, average (st. dev.) 1 - c-index values of models were, respectively, 0.417 (0.021), 0.215 (0.018), 0.469 (0.028), 0.241 (0.019), 0.217 (0.018), 0.232 (0.019), 0.230 (0.019). The best model was therefore (ii), including GPS and clinical/demographic variables. The hypothesis of a lower difference in mean with respect to model (ii) for all other models could be rejected, except for model (i) and (iii), which included only genetic variables (all p > 0.0001 for both BRCA1 and BRCA2, Student’s t-test corrected for sample overlap from multiple validation). Notably a re-calibrated SNP score, i.e. models (iii) and (iv), did not perform as well as the GPS. Consistent results were obtained by looking at the AUROC in the 1st, 2nd and 3rd quartiles of observation times. The AUROC estimation was performed on a smaller out-of-bag sample (333 out-of-bag instances) for computational reasons. Figures 2 and 3 show c-index/AUROC graphs for BRCA1/2 sets based on the out-of-bag estimator. Similar figures were obtained when stratifying for the menopausal stage (data not shown).Table 3


Can multiple SNP testing in BRCA2 and BRCA1 female carriers be used to improve risk prediction models in conjunction with clinical assessment?

Prosperi MC, Ingham SL, Howell A, Lalloo F, Buchan IE, Evans DG - BMC Med Inform Decis Mak (2014)

Model selection results forBRCA1(upper panel) andBRCA2(lower panel) data sets, comparing AUROC performance of Cox regression models (i) through (vi) and random survival forest (RSF). Time points correspond to the quartiles of the overall population observation time distribution. Curves drawn upon out-of-bag predictions (15 resampled sets).
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4197237&req=5

Fig3: Model selection results forBRCA1(upper panel) andBRCA2(lower panel) data sets, comparing AUROC performance of Cox regression models (i) through (vi) and random survival forest (RSF). Time points correspond to the quartiles of the overall population observation time distribution. Curves drawn upon out-of-bag predictions (15 resampled sets).
Mentions: When applying models (i) through (vi) and RSF on the whole BRCA1 population, using the out-of-bag estimator, average (st. dev.) 1 - c-index values of models were (see Table 3), respectively, 0.468 (0.037), 0.221 (0.019), 0.504 (0.026), 0.238 (0.019), 0.222 (0.019), 0.236 (0.018), 0.243 (0.019). When applying models (i) through (vi) and RSF on the whole BRCA2 population, using the out-of-bag estimator, average (st. dev.) 1 - c-index values of models were, respectively, 0.417 (0.021), 0.215 (0.018), 0.469 (0.028), 0.241 (0.019), 0.217 (0.018), 0.232 (0.019), 0.230 (0.019). The best model was therefore (ii), including GPS and clinical/demographic variables. The hypothesis of a lower difference in mean with respect to model (ii) for all other models could be rejected, except for model (i) and (iii), which included only genetic variables (all p > 0.0001 for both BRCA1 and BRCA2, Student’s t-test corrected for sample overlap from multiple validation). Notably a re-calibrated SNP score, i.e. models (iii) and (iv), did not perform as well as the GPS. Consistent results were obtained by looking at the AUROC in the 1st, 2nd and 3rd quartiles of observation times. The AUROC estimation was performed on a smaller out-of-bag sample (333 out-of-bag instances) for computational reasons. Figures 2 and 3 show c-index/AUROC graphs for BRCA1/2 sets based on the out-of-bag estimator. Similar figures were obtained when stratifying for the menopausal stage (data not shown).Table 3

Bottom Line: Multivariable Cox proportional hazards models were fit in the separate BRCA datasets and in menopausal stages screening different combinations of clinical/demographic/genetic variables.Random survival forests did not yield higher performance compared to Cox proportional hazards.We found improvement in prediction performance when coupling the genetic SNP score with clinical/demographic markers, which warrants further investigation.

View Article: PubMed Central - PubMed

Affiliation: Institute of Population Health, Centre for Health Informatics, University of Manchester, Manchester, UK. mattia.prosperi@manchester.ac.uk.

ABSTRACT

Background: Several single nucleotide polymorphisms (SNPs) at different loci have been associated with breast cancer susceptibility, accounting for around 10% of the familial component. Recent studies have found direct associations between specific SNPs and breast cancer in BRCA1/2 mutation carriers. Our aim was to determine whether validated susceptibility SNP scores improve the predictive ability of risk models in comparison/conjunction to other clinical/demographic information.

Methods: Female BRCA1/2 carriers were identified from the Manchester genetic database, and included in the study regardless of breast cancer status or age. DNA was extracted from blood samples provided by these women and used for gene and SNP profiling. Estimates of survival were examined with Kaplan-Meier curves. Multivariable Cox proportional hazards models were fit in the separate BRCA datasets and in menopausal stages screening different combinations of clinical/demographic/genetic variables. Nonlinear random survival forests were also fit to identify relevant interactions. Models were compared using Harrell's concordance index (1 - c-index).

Results: 548 female BRCA1 mutation carriers and 523 BRCA2 carriers were identified from the database. Median Kaplan-Meier estimate of survival was 46.0 years (44.9-48.1) for BRCA1 carriers and 48.9 (47.3-50.4) for BRCA2. By fitting Cox models and random survival forests, including both a genetic SNP score and clinical/demographic variables, average 1 - c-index values were 0.221 (st.dev. 0.019) for BRCA1 carriers and 0.215 (st.dev. 0.018) for BRCA2 carriers.

Conclusions: Random survival forests did not yield higher performance compared to Cox proportional hazards. We found improvement in prediction performance when coupling the genetic SNP score with clinical/demographic markers, which warrants further investigation.

Show MeSH
Related in: MedlinePlus