Do Breast Cancer Risk Scores Work for You?

Prospective validation of risk models is needed to assess their clinical utility, particularly over the longer term. We evaluated the performance of six commonly used breast cancer risk models (IBIS, BOADICEA, BRCAPRO, BRCAPRO-BCRAT, BCRAT, and iCARE-lit). 15-year risk scores were estimated using lifestyle factors and family history measures from 7608 women in the Melbourne Collaborative Cohort Study who were aged 50–65 years and unaffected at commencement of follow-up two (conducted in 2003–2007), of whom 351 subsequently developed breast cancer. Risk discrimination was assessed using the C-statistic and calibration using the expected/observed number of incident cases across the spectrum of risk by age group (50–54, 55–59, 60–65 years) and family history of breast cancer. C-statistics were higher for BOADICEA (0.59, 95% confidence interval (CI) 0.56–0.62) and IBIS (0.57, 95% CI 0.54–0.61) than the other models (p-difference ≤ 0.04). No model except BOADICEA calibrated well across the spectrum of 15-year risk (p-value < 0.03). The performance of BOADICEA and IBIS was similar across age groups and for women with or without a family history. For middle-aged Australian women, BOADICEA and IBIS had the highest discriminatory accuracy of the six risk models, but apart from BOADICEA, no model was well-calibrated across the risk spectrum.

Download Full-text

Polygenic risk scores for prediction of breast cancer risk in Asian populations

Genetics in Medicine ◽

10.1016/j.gim.2021.11.008 ◽

2021 ◽

Author(s):

Weang-Kee Ho ◽

Mei-Chee Tai ◽

Joe Dennis ◽

Xiang Shu ◽

Jingmei Li ◽

...

Keyword(s):

Breast Cancer ◽

Breast Cancer Risk ◽

Cancer Risk ◽

Risk Scores ◽

Polygenic Risk ◽

Asian Populations

Download Full-text

Abstract 4177: The joint effects of polygenic risk scores and pathogenic variants in cancer predisposition genes on breast cancer risk in the general population: results from the CARRIERS study

10.1158/1538-7445.am2019-4177 ◽

2019 ◽

Author(s):

Chi Gao ◽

Chunling Hu ◽

Steven N. Hart ◽

Rohan Gnanaolivu ◽

Kun Y. Lee ◽

...

Keyword(s):

Breast Cancer ◽

Breast Cancer Risk ◽

General Population ◽

Cancer Risk ◽

Cancer Predisposition ◽

Risk Scores ◽

Polygenic Risk ◽

Joint Effects ◽

Pathogenic Variants ◽

Predisposition Genes

Download Full-text

Breast cancer risk scores in a standard screening population

Breast Cancer Management ◽

10.2217/bmt.13.52 ◽

2013 ◽

Vol 2 (6) ◽

pp. 463-479 ◽

Cited By ~ 4

Author(s):

Leila Eadie ◽

Louise Enfield ◽

Paul Taylor ◽

Michael Michell ◽

Adam Gibson

Keyword(s):

Breast Cancer ◽

Breast Cancer Risk ◽

Cancer Risk ◽

Risk Scores ◽

Screening Population

Download Full-text

The limits of personalization in precision medicine: Polygenic risk scores and racial categorization in a precision breast cancer screening trial

PLoS ONE ◽

10.1371/journal.pone.0258571 ◽

2021 ◽

Vol 16 (10) ◽

pp. e0258571

Author(s):

Jennifer Elyse James ◽

Leslie Riddle ◽

Barbara Ann Koenig ◽

Galen Joseph

Keyword(s):

Breast Cancer ◽

Cancer Screening ◽

Breast Cancer Risk ◽

Cancer Risk ◽

Breast Cancer Screening ◽

Risk Scores ◽

Polygenic Risk ◽

Genomic Knowledge ◽

Breast Cancer Risk Assessment ◽

Race Ethnicity

Population-based genomic screening is at the forefront of a new approach to disease prevention. Yet the lack of diversity in genome wide association studies and ongoing debates about the appropriate use of racial and ethnic categories in genomics raise key questions about the translation of genomic knowledge into clinical practice. This article reports on an ethnographic study of a large pragmatic clinical trial of breast cancer screening called WISDOM (Women Informed to Screen Depending On Measures of Risk). Our ethnography illuminates the challenges of using race or ethnicity as a risk factor in the implementation of precision breast cancer risk assessment. Our analysis provides critical insights into how categories of race, ethnicity and ancestry are being deployed in the production of genomic knowledge and medical practice, and key challenges in the development and implementation of novel Polygenic Risk Scores in the research and clinical applications of this emerging science. Specifically, we show how the conflation of social and biological categories of difference can influence risk prediction for individuals who exist at the boundaries of these categories, affecting the perceptions and practices of scientists, clinicians, and research participants themselves. Our research highlights the potential harms of practicing genomic medicine using under-theorized and ambiguous categories of race, ethnicity, and ancestry, particularly in an adaptive, pragmatic trial where research findings are applied in the clinic as they emerge. We contribute to the expanding literature on categories of difference in post-genomic science by closely examining the implementation of a large breast cancer screening study that aims to personalize breast cancer risk using both common and rare genomic markers.

Download Full-text

Prediction of Short-Term Breast Cancer Risk Based on Deep Convolutional Neural Networks in Mammography

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2019.2805 ◽

2019 ◽

Vol 9 (8) ◽

pp. 1663-1672

Author(s):

Yane Li ◽

Ming Fan ◽

Shichen Liu ◽

Bin Zheng ◽

Lihua Li

Keyword(s):

Breast Cancer ◽

Deep Learning ◽

Breast Cancer Risk ◽

Cancer Risk ◽

Risk Model ◽

Risk Scores ◽

Learning Models ◽

Short Term ◽

Deep Convolutional Neural Networks ◽

Central Regions

This work investigated a novel framework of predicting short-term breast cancer risk by using a deep learning approach in mammography. A dataset of 675 negative screening cases were applied. 333 cases were cancer diagnosed at next screening, while 342 cases remained negative. In order to stratify these patients into high and low cancer risk group, we first used an automatically method to segment bilateral matched central regions from right and left mammography respectively. Then, three AlexNet, GoogLeNet and ResNet based deep learning models were established with ten-fold cross validation method for both difference image of bilateral matched central regions and two whole regions of bilateral breasts respectively. Using AlexNet-, GoogLeNet- and ResNet-based risk model, areas under ROC curves (AUC) are 0.56, 0.62 and 0.64 for central regions and 0.59, 0.57 and 0.65 for whole regions, respectively. When combining prediction scores of three deep learning models with a multi-agent fusion algorithm, AUCs are 0.67 and 0.67 for central regions and whole regions respectively. When fusing scores of central region-based risk model and whole region-based risk model, AUC significantly increases to 0.71 (p < 0.01). By dividing 675 cases into five subgroups based on sorting results of risk scores, the odds ratios had an significant increasing trend as the scores increased (p = 0 003). This study demonstrates feasibility of applying deep learning technology to assist investigating novel markers in mammography for helping assessment of short-term breast cancer risk and improving the efficiency of breast cancer screening in the future.

Download Full-text