Breast Cancer Risk Prediction Models Research Articles

Abstract PS10-09: Development of an absolute risk prediction model for premenopausal breast cancer in an international consortium

Abstract Risk prediction models that have been developed for overall breast cancer risk are based on a limited number of premenopausal cases in individual cohorts. As some risk factors differ in their associations with pre- versus postmenopausal breast cancer, a distinct risk prediction model is needed for premenopausal breast cancer. We developed a risk prediction model for premenopausal breast cancer using 779,601 participants and 9,665 incident cases from 18 prospective studies within the Premenopausal Breast Cancer Collaborative Group (PBCCG), across North America (N=9), Europe (N=6), Australia (N=1), and Asia (N=2). Data were split, within each cohort, into training (2/3) and testing (1/3) datasets. Individual risk was assessed in five-year intervals, using variables reported at the start of the time interval. Cox proportional hazards regression was used to model risk factors in a backwards-selection method, stratified by cohort: age at menarche, age at first birth, parity, breastfeeding (months), height (cm), BMI (kg/m2), BMI at age 18, recent weight change (kg), alcohol consumption (drinks/week), first-degree family history of breast cancer, and personal history of benign breast disease. To enable the use of information from all cohorts despite differences in missing variables by design, cohorts were grouped by available variables and risk models were fit for each group. In cohorts with incomplete data, model coefficients were adjusted based on the correlation of covariates with the missing variables in the complete case dataset. Coefficients were meta-analyzed with inverse variance weighting to obtain final coefficients. Discrimination was evaluated in the testing dataset by calculation of the c-index. Work is ongoing to calibrate the model based on five-year absolute risk using GLOBOCAN continent- and age-specific incidence rates to represent baseline risk. The final model included age at menarche, parity, height, BMI, BMI at age 18, first-degree family history of breast cancer, and history of benign breast disease. Young adulthood BMI and BMI (at start of the 5-year risk interval) were associated with a decreased risk (Hazard Ratio (HR) (95% confidence interval (CI)) per 5 kg/m2 = 0.87 (0.81-0.93) and 0.90 (0.86-0.95), respectively) as was parity (HR (95% CI) = 0.92 (0.90-0.94)). Height was associated with increased risk (HR (95% CI) per 10 cm = 1.14 (1.07-1.21)), while history of benign breast disease and family history were associated with larger increases in risk (HR (95% CI) = 1.64 (1.30-2.06) and 1.76 (1.63-1.90), respectively). Model discrimination was higher than that reported for women under 50 years in existing breast cancer risk prediction models considering clinical factors (AUC (95% CI) = 0.61 (0.59-0.62)). Calibration of absolute 5-year risk is ongoing. Several factors driving risk prediction of postmenopausal breast cancer have similar influence on risk of premenopausal breast cancer, while family history has a stronger influence on premenopausal breast cancer risk. Our model demonstrates acceptable discrimination and will enable individual 5-year absolute risk prediction for premenopausal breast cancer. Citation Format: Kristen Brantley, Michael Jones, Minouk Schoemaker, Hazel Nichols, Anthony Swerdlow, Robert MacInnis, Roger Milne, Tess Clenenden, Yu Chen, Xiao-Ou Shu, Wei Zheng, Woon-Puay Koh, Jian-Min Yuan, Cari Kitahara, Martha Linet, Dale Sandler, Bernard A Rosner, Peter Kraft, A. Heather Eliassen. Development of an absolute risk prediction model for premenopausal breast cancer in an international consortium [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PS10-09.

The Prognostic Quality of Risk Prediction Models to Assess the Individual Breast Cancer Risk in Women: An Overview of Reviews

Purpose. Breast cancer is the most common cancer among women globally, with an incidence of approximately two million cases in 2018. Organised age-based breast cancer screening programs were established worldwide to detect breast cancer earlier and to reduce mortality. Currently, there is substantial anticipation regarding risk-adjusted screening programs, considering various risk factors in addition to age. The present study investigated the discriminatory accuracy of breast cancer risk prediction models and whether they suit risk-based screening programs. Methods. Following the PICO scheme, we conducted an overview of reviews and systematically searched four databases. All methodological steps, including the literature selection, data extraction and synthesis, and the quality appraisal were conducted following the 4-eyes principle. For the quality assessment, the AMSTAR 2 tool was used. Results. We included eight systematic reviews out of 833 hits based on the prespecified inclusion criteria. The eight systematic reviews comprised ninety-nine primary studies that were also considered for the data analysis. Three systematic reviews were assessed as having a high risk of bias, while the others were rated with a moderate or low risk of bias. Most identified breast cancer risk prediction models showed a low prognostic quality. Adding breast density and genetic information as risk factors only moderately improved the models’ discriminatory accuracy. Conclusion. All breast cancer risk prediction models published to date show a limited ability to predict the individual breast cancer risk in women. Hence, it is too early to implement them in national breast cancer screening programs. Relevant randomised controlled trials about the benefit-harm ratio of risk-adjusted breast cancer screening programs compared to conventional age-based programs need to be awaited.

Association between Family History of Breast Cancer and Breast Density in Saudi Premenopausal Women Participating in Mammography Screening.

Mammographic density and family history of breast cancer (FHBC) are well-established independent factors affecting breast cancer risk; however, the association between these two risk factors in premenopausal-screened women remains unclear. The aim of this study is to investigate the relationship between mammographic density and FHBC among Saudi premenopausal-screened women. A total of 446 eligible participants were included in the study. Mammographic density was assessed qualitatively using the Breast Imaging Reporting and Data System (BIRADS 4th edition). Logistic regression models were built to investigate the relationship between mammographic density and FHBC. Women with a family history of breast cancer demonstrated an 87% greater chance of having dense tissue than women without a family history of breast cancer (95% CI: 1.14-3.08; p = 0.01). Having a positive family history for breast cancer in mothers was significantly associated with dense tissue (adjusted odds ratio (OR): 5.6; 95% CI: 1.3-24.1; p = 0.02). Dense breast tissue in Saudi premenopausal women undergoing screening may be linked to FHBC. If this conclusion is replicated in larger studies, then breast cancer risk prediction models must carefully consider these breast cancer risk factors.

Addition of polygenic risk score to a risk calculator for prediction of breast cancer in US Black women

BackgroundPrevious work in European ancestry populations has shown that adding a polygenic risk score (PRS) to breast cancer risk prediction models based on epidemiologic factors results in better discriminatory performance as measured by the AUC (area under the curve). Following publication of the first PRS to perform well in women of African ancestry (AA-PRS), we conducted an external validation of the AA-PRS and then evaluated the addition of the AA-PRS to a risk calculator for incident breast cancer in Black women based on epidemiologic factors (BWHS model).MethodsData from the Black Women’s Health Study, an ongoing prospective cohort study of 59,000 US Black women followed by biennial questionnaire since 1995, were used to calculate AUCs and 95% confidence intervals (CIs) for discriminatory accuracy of the BWHS model, the AA-PRS alone, and a new model that combined them. Analyses were based on data from 922 women with invasive breast cancer and 1844 age-matched controls.ResultsAUCs were 0.577 (95% CI 0.556–0.598) for the BWHS model and 0.584 (95% CI 0.563–0.605) for the AA-PRS. For a model that combined estimates from the questionnaire-based BWHS model with the PRS, the AUC increased to 0.623 (95% CI 0.603–0.644).ConclusionsThis combined model represents a step forward for personalized breast cancer preventive care for US Black women, as its performance metrics are similar to those from models in other populations. Use of this new model may mitigate exacerbation of breast cancer disparities if and when it becomes feasible to include a PRS in routine health care decision-making.

Breast cancer prediction using different machine learning methods applying multi factors.

Breast cancer (BC) is a multifactorial disease and is one of the most common cancers globally. This study aimed to compare different machine learning (ML) techniques to develop a comprehensive breast cancer risk prediction model based on features of various factors. The population sample contained 810 records (115 cancer patients and 695 healthy individuals). 45 attributes out of 85 were selected based on the opinion of experts. These selected attributes are in genetic, biochemical, biomarker, gender, demographic and pathological factors. 13 Machine learning models were trained with proposed attributes and coefficient of attributes and internal relationships were calculated. Compared to other methods random forest (RF) has higher performance (accuracy 99.26%, precision 99%,and area under the curve (AUC) 99%). The results of assessing the impact and correlation of variables using the RF method based on PCA indicated that pathology, biomarker,biochemistry, gene, and demographic factors with a coefficient of 0.35, 0.23, 0.15, 0.14, and 0.13 respectively, affected the risk of BC (r2 = 0.54). Breast cancer has several risk factors. Medical experts use these risk factors for early diagnosis. Therefore, identifying related risk factors and their effect can increase the accuracy of diagnosis. Considering the broad features for predicting breast cancer leads to the development of a comprehensive prediction model. In this study, using RF technique a breast cancer prediction model with 99.3% accuracy was developed based on multifactorial features.

Development of a Breast Cancer Risk Prediction Model Incorporating Polygenic Risk Scores and Nongenetic Risk Factors for Korean Women.

To develop a breast cancer prediction model for Korean women using published polygenic risk scores (PRS) combined with nongenetic risk factors (NGRF). Thirteen PRS models generated from single or multiple combinations of the Asian and European PRSs were evaluated among 20,434 Korean women. The AUC and increase in OR per SD were compared for each PRS. The PRSs with the highest predictive power were combined with NGRFs; then, an integrated prediction model was established using the Individualized Coherent Absolute Risk Estimation (iCARE) tool. The absolute breast cancer risk was stratified for 18,142 women with available follow-up data. PRS38_ASN+PRS190_EB, a combination of Asian and European PRSs, had the highest AUC (0.621) among PRSs, with an OR per SD increase of 1.45 (95% confidence interval: 1.31-1.61). Compared with the average risk group (35%-65%), women in the top 5% had a 2.5-fold higher risk of breast cancer. Incorporating NGRFs yielded a modest increase in the AUC of women ages >50 years. For PRS38_ASN+PRS190_EB+NGRF, the average absolute risk was 5.06%. The lifetime absolute risk at age 80 years for women in the top 5% was 9.93%, whereas that of women in the lowest 5% was 2.22%. Women at higher risks were more sensitive to NGRF incorporation. Combined Asian and European PRSs were predictive of breast cancer in Korean women. Our findings support the use of these models for personalized screening and prevention of breast cancer. Our study provides insights into genetic susceptibility and NGRFs for predicting breast cancer in Korean women.

Breast cancer risk prediction models in a moderate risk family history clinic

Breast cancer risk prediction models in a moderate risk family history clinic

Abstract 4174: Incorporating continuous mammographic density into the BOADICEA breast cancer risk prediction model

Abstract BOADICEA, implemented in the CanRisk tool (www.canrisk.org) can be used to calculate future breast cancer risk using data on cancer family history, genetics (rare high- or moderate-risk pathogenic variants; polygenic scores (PGS)), questionnaire-based risk factors and mammographic density (MD) measured using the BI-RADS classification. The BI-RADS categorization requires manual reading which is not feasible at population level. Moreover, BI-RADS captures MD in 4 categories, whereas continuous measures are stronger risk predictors. Here, BOADICEA was extended to incorporate continuous breast density measured by the fully automated Volpara and STRATUS software, working on raw and processed images, respectively. We used data from the KARMA prospective screening cohort (60,276 participants; 1,167 incident breast cancers). The associations between Volpara or STRATUS density measurements and incident breast cancer risk were estimated in a randomly selected training subset consisting of two-thirds of the full dataset. For this, we calculated density residuals after regressing on participant’s age at mammography. Hazard ratios (HR) for the normalized residuals were calculated using a Cox proportional hazards model, adjusting for family history, BMI and all risk factors included in BOADICEA. Multiple Imputation by Chained Equations (MICE) was used to impute missing data. The remaining one-third of the KARMA cohort was used to assess the performance of BOADICEA in predicting 5-year risks, after including the estimated Volpara and STRATUS associations.Under the best fitting multivariable model including PGS, the HRs per SD of residual STRATUS density were estimated to be 1.67 (95%CI: 1.44-1.93) and 1.38 (95%CI: 1.26-1.51) for pre- and post-menopausal women, respectively. The HR estimates per SD of residual Volpara density were 1.38 (95%CI: 1.19-1.59) and 1.39 (95%CI: 1.27-1.52) for pre- and post-menopausal women, respectively. After incorporating these associations in BOADICEA, there was a marked improvement in the model discriminatory ability in the test dataset, compared to using the BI-RADS classification. The largest increase in AUC was observed for STRATUS residual density, with a 3% increase compared to using BI-RADS vs a 1.6% increase in AUC when using Volpara residual density. These increases were consistent across BOADICEA models considering different combinations of risk factors, including PGS.Including continuous breast density in BOADICEA can lead to improved breast cancer risk stratification and could allow for automated measures of MD to be more readily deployed in breast cancer risk prediction. Additional prospective studies are required to further validate the findings. The models will be implemented in the CanRisk tool. Citation Format: Lorenzo Ficorella, Mikael Eriksson, Kamila Czene, Goska Leslie, Xin Yang, Tim J. Carver, Douglas F. Easton, Per F. Hall, Antonis C. Antoniou. Incorporating continuous mammographic density into the BOADICEA breast cancer risk prediction model. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 4174.

Abstract 4175: Development of breast cancer risk assessment tool: The Korean decision aid for cancer screening (K-DACS) study

Abstract Purpose: Widely used breast cancer risk prediction tools are based on data from Western countries, but risk factors may differ for Asian women. Hence, we aimed to develop a risk assessment tool for breast cancer in Asian women, using a nationwide, population-based cohort in Korea. Methods: Women aged ≥ 40 years who participated in both breast cancer screening and general health examination in 2009 were eligible for this study. Age, body mass index (BMI), breast density, lifestyle and reproductive factors, and comorbidities were used to develop 5-year breast cancer risk prediction models in premenopausal (n=771,856) and postmenopausal (n=1,108,047) women at baseline. Backward stepwise selection in the Cox proportional hazards model was used to construct the best-fit risk prediction model, which was then converted into a risk score nomogram, representing an individual probability estimate of incident breast cancer. Model performance was evaluated by discrimination and calibration. Results: Among premenopausal women, high BMI, low parity, short breastfeeding period, early age at menarche, high breast density, history of benign breast mass, and family history of breast cancer contributed to breast cancer risk prediction. The appropriate predictors in postmenopausal women additionally included age, type 2 diabetes, dyslipidemia, late age at menopause, hormone replacement therapy use, except for number of parities. The concordant statistic of risk prediction model was 0.58 (95% confidence interval [CI] 0.57-0.59) for premenopausal women, and 0.64 (95% CI 0.63-0.65) for postmenopausal women. Our model correlated well in the calibration plot in both premenopausal and postmenopausal women.Conclusions: Our breast cancer risk prediction model showed good performance for postmenopausal women, providing the background for risk-based screening recommendations in Asian women. Citation Format: Wonyoung Jung, Yong-Moon Mark Park, Sang Hyun Park, Kyungdo Han, Junhee Park, Yohwan Yeo, Jung Kwon Lee, Dale P. Sandler, Dong Wook Shin. Development of breast cancer risk assessment tool: The Korean decision aid for cancer screening (K-DACS) study. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 4175.

Validation of an Abridged Breast Cancer Risk Prediction Model for the General Population.

In this prospective population-based cohort study, we show the improved performance of a new risk assessment model compared with a gold-standard model (BCRAT). The classification of at-risk women using this new model highlights the opportunity to improve risk stratification and implement existing clinical risk-reduction interventions.

Abstract PD14-05: PD14-05 Prospective longitudinal validation of a breast cancer risk prediction model in a cohort of 130,058 women

Abstract Background: Personalized breast cancer (BC) risk assessment depends on known traditional risk factors, specific germline mutations, and genome-wide polygenic risk scores (PRS). PRS explains a substantial proportion of genetic BC susceptibility. Accuracy of BC risk prediction may be improved by combining a PRS with traditional risk factors. We recently developed and validated a 149-SNP PRS for women of diverse ancestries using ancestry-informative genetic markers and combined this with version 7 of the Tyrer-Cuzick (TC) model to generate a Combined Risk Score (CRS). Here, we describe a pre-specified prospective longitudinal clinical validation of CRS as a predictor of BC risk. Methods: Women in the U.S. who were referred for clinical genetic testing between January 2017 and February 2019 were matched to medical and hospital claims in an anonymized dataset. Women with a pathogenic mutation in a BC-related gene were excluded from analysis. Follow-up began 4 months after testing and extended to the earliest date of BC diagnosis, censoring at the time of BC preventive treatment, or November 1, 2019. Incident BC events were determined by an ICD10 code of C50.* and confirmed by relevant treatment codes. CRS calibration was evaluated by the ratio of observed (O) to expected (E) incident BCs for the full cohort, and for women split into event-based 5-year CRS risk deciles. Cox proportional hazards models were used to evaluate discriminatory accuracy in terms of hazard ratios (HR) with 95% confidence intervals (CI) and p-values from likelihood ratio chi-squared statistics. Kaplan-Meier analysis was used to examine risk for women split into high- or low-risk groups according to a 3% 5-year CRS risk threshold. Results: 130,058 women with 148,349 total patient years met study eligibility criteria and were matched to claims data. Over a median (range) follow-up of 12.1 (4.0-29.5) months, 340 incident BC events were observed. The CRS was well calibrated in the overall cohort with an O/E ratio of 1.11 (95% CI=0.99-1.23) and within deciles of predicted risk (Table). Importantly, in the highest risk decile, the O/E was 0.91 (95% CI=0.63-1.27) with CRS, but 0.67 (95% CI=0.46-0.94) with TC alone, illustrating the superior calibration of CRS. In a Cox model adjusted for age at testing, PRS had an HR per standard deviation (SD) of 1.48 (95% CI=1.33-1.64, p=2.55×10-13); the HR/SD was 1.43 (95% CI=1.29-1.59, p=1.61×10-11) after adjusting for family history. In a bivariate analysis using both CRS and TC to predict time to BC, CRS added significantly to the model after accounting for TC (HR/SD=2.89, 95% CI=2.12-3.94, p=1.20×10-11), whereas TC did not add significant information after accounting for CRS. 15,986 (12.3%) women were above the CRS high-risk threshold, including 123 with events. A total of 10,248 (7.9%) women were reclassified by the CRS model compared to the TC model. Among women who were classified as high-risk by TC, 32.6% were reclassified as low-risk by CRS; among those classified as low-risk by TC, 4.3% were reclassified as high-risk by CRS. The CRS high-risk group experienced events at over three times the rate of the low-risk group (HR=3.75, 95% CI=3.00-4.68, p=6.39×10-27). Conclusion: The CRS was well-calibrated in predicting BC and significantly improved upon a traditional risk factor model. Clinical use of the CRS may lead to improved BC prevention and screening strategies. Table: Absolute risk calibration by 5-year risk decile Incidence is reported per 1,000 women-years. 34 breast cancers were observed per decile. Citation Format: Brent Mabey, Elisha Hughes, Braden Probst, Holly J. Pederson, Timothy Simmons, Brian Morris, Brooke Hullinger, Susan Domchek, Charis Eng, Monique Gary, Jennifer Klemp, Semanti Mukherjee, Vijai Joseph, Kenneth Offit, Olufunmilayo I. Olopade, Sandhya Pruthi, Allison W. Kurian, Mark E. Robson, Pat Whitworth, Susanne Wagner, Jerry Lanchbury, Thomas Slavin, Alexander Gutin. PD14-05 Prospective longitudinal validation of a breast cancer risk prediction model in a cohort of 130,058 women [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr PD14-05.

Abstract PD14-06: PD14-06 Polygenic risk score added to risk calculator improves prediction of breast cancer in U.S. Black women

Abstract We recently derived an absolute breast cancer risk prediction model, the Black Women’s Health Study (BWHS) model, for breast cancer in U.S. Black women using data from three large case-control studies and validated it in independent prospective data from the Black Women’s Health Study (Palmer 2021). The BWHS model includes epidemiologic risk factors as well as family history of breast cancer and family history of prostate cancer. It does not include genetic variants because at the time of model development breast cancer polygenic risk scores performed poorly in women of predominantly African ancestry, primarily due to differences in allele frequency and linkage disequilibrium. More recently, Gao et al. (2022) developed and tested a polygenic risk score (PRS) using 56,943 SNPs for breast cancer in women of African ancestry (AA) based on 9,235 breast cancer cases and 10,184 controls from a large pooled analysis of studies from African American and African women; the c-statistic from cross-validation was 0.581, considerably better than in previous efforts. We evaluated whether adding this AA-PRS to the BWHS risk prediction model would improve risk stratification. We conducted a nested case-control study of 901 breast cancer cases and 1,576 controls matched on age and most recent questionnaire completed from among BWHS participants for whom genome-wide association data were available and who had not been included in the collaboration from which the PRS was derived and tested. We examined discriminatory accuracy, estimated by the area under the receiver operating characteristic curve (AUC), for the risk prediction model alone, the PRS alone, and the combination of risk prediction model and PRS, controlling for the matching factor “questionnaire cycle”. We conducted the analyses within strata of 5-year age and then combined results using inverse-variance weighting. In preliminary analyses, the AUC was 0.579 for the risk prediction model alone and 0.600 for the AA-PRS alone. When the AA-PRS and the BWHS risk prediction model were both used as predictors in a logistic regression model, the AUC increased from 0.579 to 0.622. This improvement in risk stratification is similar to what Kachuri et al. (2020) obtained in an analysis of U.K. Biobank data, where adding a PRS to epidemiologic and personal risk factors showed an improvement from 0.572 to 0.635 in women of European ancestry. The present study provides external validation of a recently derived AA PRS and demonstrates the potential for improving risk stratification for U.S. Black women by adding a PRS to a breast cancer risk prediction model that already includes family history of breast cancer. Citation Format: Gary R. Zirpoli, Kathryn L. Lunetta, Ruth M. Pfeiffer, Julie R. Palmer. PD14-06 Polygenic risk score added to risk calculator improves prediction of breast cancer in U.S. Black women [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr PD14-06.

Combining Breast Cancer Risk Prediction Models.

Accurate risk stratification is key to reducing cancer morbidity through targeted screening and preventative interventions. Multiple breast cancer risk prediction models are used in clinical practice, and often provide a range of different predictions for the same patient. Integrating information from different models may improve the accuracy of predictions, which would be valuable for both clinicians and patients. BRCAPRO is a widely used model that predicts breast cancer risk based on detailed family history information. A major limitation of this model is that it does not consider non-genetic risk factors. To address this limitation, we expand BRCAPRO by combining it with another popular existing model, BCRAT (i.e., Gail), which uses a largely complementary set of risk factors, most of them non-genetic. We consider two approaches for combining BRCAPRO and BCRAT: (1) modifying the penetrance (age-specific probability of developing cancer given genotype) functions in BRCAPRO using relative hazard estimates from BCRAT, and (2) training an ensemble model that takes BRCAPRO and BCRAT predictions as input. Using both simulated data and data from Newton-Wellesley Hospital and the Cancer Genetics Network, we show that the combination models are able to achieve performance gains over both BRCAPRO and BCRAT. In the Cancer Genetics Network cohort, we show that the proposed BRCAPRO + BCRAT penetrance modification model performs comparably to IBIS, an existing model that combines detailed family history with non-genetic risk factors.

Validation of a breast cancer risk prediction model based on the key risk factors: family history, mammographic density and polygenic risk

PurposeWe compared a simple breast cancer risk prediction model, BRISK (which includes mammographic density, polygenic risk and clinical factors), against a similar model with more risk factors (simplified Rosner) and against two commonly used clinical models (Gail and IBIS).MethodsUsing nested case–control data from the Nurses’ Health Study, we compared the models’ association, discrimination and calibration. Classification performance was compared between Gail and BRISK for 5-year risks and between IBIS and BRISK for remaining lifetime risk.ResultsThe odds ratio per standard deviation was 1.43 (95% CI 1.32, 1.55) for BRISK 5-year risk, 1.07 (95% CI 0.99, 1.14) for Gail 5-year risk, 1.72 (95% CI 1.59, 1.87) for simplified Rosner 10-year risk, 1.51 (95% CI 1.41, 1.62) for BRISK remaining lifetime risk and 1.26 (95% CI 1.16, 1.36) for IBIS remaining lifetime risk. The area under the receiver operating characteristic curve (AUC) was improved for BRISK over Gail for 5-year risk (AUC = 0.636 versus 0.511, P < 0.0001) and for BRISK over IBIS for remaining lifetime risk (AUC = 0.647 versus 0.571, P < 0.0001). BRISK was well calibrated for the estimation of both 5-year risk (expected/observed [E/O] = 1.03; 95% CI 0.73, 1.46) and remaining lifetime risk (E/O = 1.01; 95% CI 0.86, 1.17). The Gail 5-year risk (E/O = 0.85; 95% CI 0.58, 1.24) and IBIS remaining lifetime risk (E/O = 0.73; 95% CI 0.60, 0.87) were not well calibrated, with both under-estimating risk. BRISK improves classification of risk compared to Gail 5-year risk (NRI = 0.31; standard error [SE] = 0.031) and IBIS remaining lifetime risk (NRI = 0.287; SE = 0.035).ConclusionBRISK performs better than two commonly used clinical risk models and no worse compared to a similar model with more risk factors.

Incorporating Alternative Polygenic Risk Scores into the BOADICEA Breast Cancer Risk Prediction Model.

The multifactorial risk prediction model BOADICEA enables identification of women at higher or lower risk of developing breast cancer. BOADICEA models genetic susceptibility in terms of the effects of rare variants in breast cancer susceptibility genes and a polygenic component, decomposed into an unmeasured and a measured component - the polygenic risk score (PRS). The current version was developed using a 313 SNP PRS. Here, we evaluated approaches to incorporating this PRS and alternative PRS in BOADICEA. The mean, SD, and proportion of the overall polygenic component explained by the PRS (α2) need to be estimated. $\alpha $ was estimated using logistic regression, where the age-specific log-OR is constrained to be a function of the age-dependent polygenic relative risk in BOADICEA; and using a retrospective likelihood (RL) approach that models, in addition, the unmeasured polygenic component. Parameters were computed for 11 PRS, including 6 variations of the 313 SNP PRS used in clinical trials and implementation studies. The logistic regression approach underestimates $\alpha $, as compared with the RL estimates. The RL $\alpha $ estimates were very close to those obtained by assuming proportionality to the OR per 1 SD, with the constant of proportionality estimated using the 313 SNP PRS. Small variations in the SNPs included in the PRS can lead to large differences in the mean. BOADICEA can be readily adapted to different PRS in a manner that maintains consistency of the model. : The methods described facilitate comprehensive breast cancer risk assessment.

Breast cancer risk prediction models’ adoption by Canadian providers - an in-depth qualitative comparative analysis

The use of risk prediction models (RPMs) for breast cancer (BC) is expected to increase in the near future and is essential for BC risk stratification, which makes it crucial to better understand their adoption. To identify the conditions that impact the use of BC RPMs by Canadian healthcare professionals (HPs), a database of the clinical activities of 176 providers was used to perform statistical bivariate tests and qualitative comparative analysis. The results showed that training in BC genetics is essential for the use of BC RPMs, the proximity of genetic services is a relevant factor for users, and extended clinical experience impedes the use of such models. To increase the use of BC RPMs, two main solutions have emerged: targeting non-users and offering them training and more opportunities for inter-professional collaborations, and targeting experienced HPs with tools that provide them with a significant added value over the risk calculation.

An Improved Training Algorithm Based on Ensemble Penalized Cox Regression for Predicting Absolute Cancer Risk.

Biases in cancer incidence characteristics have led to significant imbalances in databases constructed by prospective cohort studies. Since they use imbalanced databases, many traditional algorithms for training cancer risk prediction models perform poorly. To improve prediction performance, we introduced a Bagging ensemble framework to an absolute risk model based on ensemble penalized Cox regression (EPCR). We then tested whether the EPCR model outperformed other traditional regression models by varying the censoring rate of the simulated data. Six different simulation studies were performed with 100 replicates. To assess model performance, we calculated mean false discovery rate, false omission rate, true positive rate, true negative rate, and the areas under the receiver operating characteristic curve (AUC) values. We found that the EPCR procedure could reduce the false discovery rate (FDR) for important variables at the same true positive rate (TPR), thereby achieving more accurate variable screening. In addition, we used the EPCR procedure to build a breast cancer risk prediction model based on the Breast Cancer Cohort Study in Chinese Women database. AUCs for 3- and 5-year predictions were 0.691 and 0.642, representing improvements of 0.189 and 0.117 over the classical Gail model, respectively. We conclude that the EPCR procedure can overcome challenges posed by imbalanced data and improve the performance of cancer risk assessment tools.

The EMory BrEast imaging Dataset (EMBED): A Racially Diverse, Granular Dataset of 3.4 Million Screening and Diagnostic Mammographic Images.

Supplemental material is available for this article. Keywords: Mammography, Breast, Machine Learning © RSNA, 2023.

Performance of risk prediction models in breast cancer screening among women in Cyprus.

Tools that can predict breast cancer risk in women will have a significant impact on women and healthcare systems in low- and middle-income countries. We compared the performances of the Breast and Ovarian Analysis of Disease Incidence and Carrier Estimation Algorithm (BOADICEA) model, the International Breast Cancer Intervention Study (IBIS) model, and the Gail model in predicting breast cancer risk among women in Cyprus. We recruited 655 women from Dr Burhan Nalbantoglu Devlet Hastanesi Hospital in Lefkosa: 318 had breast cancer and 337 did not have breast cancer (hospital-based controls). We collected retrospective data from the hospital's medical records and interviews with the women after informed consent. Data collected included: age, age at diagnosis, age at menarche, menopausal status, presence of benign breast disease, breast cancer in relatives, BRCA-1 and BRCA-2 mutations, history of hormone replacement therapy, and breast density. We calculated the 5-year risk of breast cancer and the risk values were used to plot receiver operating curves. For the area under the curve (95% confidence interval, CI), sensitivity and specificity for the models were: BOADICEA 0.81 (95% CI: 0.77-0.84), 26.4% and 98.8%; IBIS 0.80 (95% CI: 0.77-0.84), 19.4% and 97.3%; and Gail 0.76 (95% CI: 0.73-0.80), 17.3% and 98.5%. The breast cancer risk prediction models performed similarly although on closer appraisal, the BOADICEA and IBIS models performed slightly better. These models are simple, appropriate, cost-effective, and non-invasive tools for identifying high-risk women in low- and middle-income countries who could benefit from mammography screening.

BRCA-CRisk: A Contralateral Breast Cancer Risk Prediction Model for BRCA Carriers.

The absolute cumulative risk of contralateral breast cancer (CBC) for patients with BRCA1/2 variants is unknown. The purpose of this study was to develop a CBC risk prediction model for assessing CBC risk for BRCA1/2 carriers. The primary cohort of 491 patients with BRCA1/2 variants was derived from a large series of unselected patients with breast cancer. A nomogram was established on the basis of the results of a multivariate Cox regression analysis from this cohort. This model, named BRCA-CRisk, was further validated by an independent cohort of 205 patients with BRCA1/2 variants. Discrimination and calibration of the model were assessed. In the primary cohort of 491 patients, 66 developed contralateral breast cancer after a median follow-up of 7.0 years. Four variables were significantly associated with risk of CBC and were incorporated in the establishment of the BRCA-CRisk prediction model: younger age at first breast cancer (with continuous variable, P = .002), positive first-degree family history of breast and/or ovarian cancer (hazard ratio [HR], 1.89; 95% CI, 1.16 to 3.08; P = .011), variant located near the 3' region of BRCA (HR, 2.01; 95% CI, 1.23 to 3.30; P = .006), and endocrine therapy (HR, 0.54; 95% CI, 0.33 to 0.88; P = .013). The area under the time-dependent curves for the 5- and 10-year cumulative risks of CBC were 0.775 and 0.702, respectively. The model was well validated in the independent cohort of 205 BRCA1/2 carriers, with area under the curves of 0.750 and 0.691 for 5 and 10 years, respectively. BRCA-CRisk model provides a useful tool for assessing the absolute cumulative risk of CBC for BRCA1/2 carriers and may help carriers and clinicians optimally select risk-reducing strategies on the basis of individual CBC risk.