Breast Cancer Risk Prediction Research Articles

Comparative validation of the BOADICEA and Tyrer-Cuzick breast cancer risk models incorporating classical risk factors and polygenic risk in a population-based prospective cohort of women of European ancestry

BackgroundThe Breast and Ovarian Analysis of Disease Incidence and Carrier Estimation Algorithm (BOADICEA) and the Tyrer-Cuzick breast cancer risk prediction models are commonly used in clinical practice and have recently been extended to include polygenic risk scores (PRS). In addition, BOADICEA has also been extended to include reproductive and lifestyle factors, which were already part of Tyrer-Cuzick model. We conducted a comparative prospective validation of these models after incorporating the recently developed 313-variant PRS.MethodsCalibration and discrimination of 5-year absolute risk was assessed in a nested case-control sample of 1337 women of European ancestry (619 incident breast cancer cases) aged 23–75 years from the Generations Study.ResultsThe extended BOADICEA model with reproductive/lifestyle factors and PRS was well calibrated across risk deciles; expected-to-observed ratio (E/O) at the highest risk decile :0.97 (95 % CI 0.51 − 1.86) for women younger than 50 years and 1.09 (0.66 − 1.80) for women 50 years or older. Adding reproductive/lifestyle factors and PRS to the BOADICEA model improved discrimination modestly in younger women (area under the curve (AUC) 69.7 % vs. 69.1%) and substantially in older women (AUC 64.6 % vs. 56.8%). The Tyrer-Cuzick model with PRS showed evidence of overestimation at the highest risk decile: E/O = 1.54(0.81 − 2.92) for younger and 1.73 (1.03 − 2.90) for older women.ConclusionThe extended BOADICEA model identified women in a European-ancestry population at elevated breast cancer risk more accurately than the Tyrer-Cuzick model with PRS. With the increasing availability of PRS, these analyses can inform choice of risk models incorporating PRS for risk stratified breast cancer prevention among women of European ancestry.

Abstract SP080: Hidden clues in the mammogram: How AI can improve early breast cancer detection

Abstract Innovative methods of risk assessment that leverage the strength of Artificial Intelligence (AI) are essential to propel the goals of precision prevention forward. Since the creation of the Gail model in 1989, risk models have supported risk-adjusted screening and prevention, and their continued evolution has been a central pillar of breast cancer research. Prior research has explored multiple risk factors related to hormonal and genetic information. One factor that has received substantial attention is mammographic breast density. Incorporating mammographic breast density into clinically used models such as the Gail and Tyrer-Cuzick risk models significantly improves prediction and discrimination. However, current risk models are limited in that they incorporate only a small fraction of data available on any given patient. Using breast density as a proxy for the detailed information embedded in the mammogram is extremely limited, as breast density assessment is subjective, varies widely across radiologists, and restricts the rich information contained in the digital images to a single crude value. Patients of the same age assigned the same density score can have mammogram images that appear drastically different and can have very different future risk profiles. While previous studies have explored automated methods to assess breast density, these efforts reduce the complex data contained in the mammogram into a few statistics, which are not sufficiently rich to distinguish patients who will and will not develop breast cancer. Deep learning models can operate over full resolution mammogram images to assess a patient’s future breast cancer risk. Rather than manually identifying discriminative image patterns, machine learning models can discover these patterns directly from the data. Specifically, models are trained with full resolution mammograms and the outcome of interest, namely whether the patient developed breast cancer within five years from the date of the examination. Our recent work demonstrates that application of novel artificial intelligence applications to imaging data can significantly improve breast cancer risk prediction. In addition, unlike traditional models, our DL model performs equally well across varied races, ages, and family histories and we have built a clinical platform which is currently in use to support implementation of our risk model into clinical care. The COVID-19 pandemic has revealed severe inequities in healthcare while providing opportunities for essential reform. In breast cancer care, preliminary, conservative estimates predict the disruption of breast cancer screening due to the COVID-19 pandemic will result in a significant upward stage shift of cancers diagnosed and more than 5,000 breast cancer deaths in the U.S. alone. Due to severely limited healthcare resources during pandemics, and to protect patients and healthcare workers, state governments urge providers to focus cancer screening efforts on those patients at higher risk. These mandates are necessary responses to support fair allocation of scarce resources to maximize benefits for all patients across the full spectrum of healthcare needs. AI-based breast cancer risk models have the potential to support more effective and more equitable mammographic screening for breast cancer during these times of severely restricted access to screening. ROC Area Under the Curve Analyses of Traditional vs AI Risk Models Risk ModelTyrer-Cuzick version 8 AUCAI Image Only AUCRaceAfrican American0.58 (0.39, 0.79)0.74 (0.60, 0.90)Asian0.53 (0.35, 0.74)0.79 (0.68, 0.94)White0.64 (0.60, 0.68)0.77 (0.73, 0.80)Age<500.65 (0.57, 0.72)0.75 (0.68, 0.82)50-700.64 (0.60, 0.69)0.76 (0.72, 0.79)>700.52 (0.43, 0.60)0.77 (0.70, 0.84)DensityNon-Dense0.63 (0.58, 0.68)0.77 (0.73, 0.81)Dense0.63 (0.58, 0.69)0.77 (0.73, 0.81) Citation Format: C Lehman, A Yala, L Lamb, R Barzilay. Hidden clues in the mammogram: How AI can improve early breast cancer detection [abstract]. In: Proceedings of the 2020 San Antonio Breast Cancer Virtual Symposium; 2020 Dec 8-11; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2021;81(4 Suppl):Abstract nr SP080.

Abstract PD10-10: Epithelial proliferation score as an independent breast cancer risk predictor in benign breast disease

Abstract Background: Women with benign breast disease (BBD) experience an increased risk of breast cancer (BC). Histologic classification of BBD, as non-proliferative disease (NP), proliferative disease without atypia (PDWA) or atypical hyperplasia (AH), stratifies groups of patients into progressively higher categories of BC risk. However, this classification does not comprehensively assess the proliferative state of the epithelium throughout the biopsy. In addition, while AH is considered the most high-risk class of BBD, it is not always a highly proliferative lesion; atypical ductal lesions may reflect focal cytologic and architectural changes. We evaluated the association of an alternative classification of BBD severity and BC risk based on subjective grading of: 1) the maximal degree of epithelial proliferation and 2) multifocality of epithelial proliferation. Methods: Pathologists reviewed biopsies from participants aged 18 to 85 years in the Mayo BBD cohort (2002-2013), masked to BC outcomes, ascertained via questionnaires, tumor registry data and medical record review. Biopsies were classified as NP, PDWA or AH and semi-quantitatively scored for: 1) maximal degree of epithelial proliferation within a focus (DP) (0-3; none to severe) and 2) multifocality of proliferation (MP) (0-3; none to multiple foci). DP and MP scores were also summed to give a DP+MP score (0-6). Associations of DP and MP with BC risk were examined using Cox proportional hazards regression analyses, adjusting for age at BBD biopsy. Women were followed from date of initial biopsy to date of BC, death or last follow-up. Results: Of the 1529 assessable biopsies, 544 (35.6%) were classified as NP, 708 (46.3%) as PDWA and 277 (18.1%) as AH. Both DP and MP scores had significant positive correlation with increasing BBD severity (DP: r=0.51, p< 0.001; MP: r=0.52, p< 0.001). Mean (SD) DP scores were 0.6 (0.6) for NP, 1.6 (0.9) for PDWA, and 1.8 (0.7) for AH (ANOVA p<0.001). Mean (SD) for MP scores were 0.6 (0.6) for NP, 1.4 (0.8) for PDWA, and 1.8 (0.8) for AH (ANOVA p<0.001). Mean (SD) for DP+MP scores were 1.2 (1.2) for NP, 2.9 (1.5) for PDWA, and 3.6 (1.2) for AH (ANOVA p<0.001). With median follow-up of 8.8 years for controls and 5.3 years for cases, 10.6% of the women in the cohort developed BC. Compared to those with DP scores of 0, women with DP scores of 3 had significantly increased BC risk (HR 1.42, 95% CI: 1.16, 1.74, p=0.003). MP was associated with a non-significant increase in BC risk for scores of 3 versus 0 (HR: 1.20, 95% CI: 0.97,1.49, p=0.11). DP+MP scores of 6 conferred the highest BC risk (HR (score 6 vs. 0): 1.62, 95% CI 1.18,2.21, p=0.02). Results did not substantively differ after adjusting for BBD severity as NP, PDWA or AH. Conclusions: In this preliminary analysis within the Mayo BBD cohort, both proliferative degree (DP) and multifocality (MP) scores were correlated with histologic severity of BBD. DP and DP+MP scores were each associated with increased BC risk. We conclude that improved characterization of epithelial proliferation in BBD biopsies may enable refined prediction of individual BC risk. Citation Format: Jodi M Carter, Matthew R Jensen, Robert A Vierkant, Stacey J Winham, Tanya L Hoskin, Marlene Frost, Karthik Ghosh, Derek C Radisky, Amy C Degnim, Mark E Sherman. Epithelial proliferation score as an independent breast cancer risk predictor in benign breast disease [abstract]. In: Proceedings of the 2020 San Antonio Breast Cancer Virtual Symposium; 2020 Dec 8-11; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2021;81(4 Suppl):Abstract nr PD10-10.

Breast Cancer Risk Genes — Association Analysis in More than 113,000 Women

BackgroundGenetic testing for breast cancer susceptibility is widely used, but for many genes, evidence of an association with breast cancer is weak, underlying risk estimates are imprecise, and reliable subtype-specific risk estimates are lacking.MethodsWe used a panel of 34 putative susceptibility genes to perform sequencing on samples from 60,466 women with breast cancer and 53,461 controls. In separate analyses for protein-truncating variants and rare missense variants in these genes, we estimated odds ratios for breast cancer overall and tumor subtypes. We evaluated missense-variant associations according to domain and classification of pathogenicity.ResultsProtein-truncating variants in 5 genes (ATM, BRCA1, BRCA2, CHEK2, and PALB2) were associated with a risk of breast cancer overall with a P value of less than 0.0001. Protein-truncating variants in 4 other genes (BARD1, RAD51C, RAD51D, and TP53) were associated with a risk of breast cancer overall with a P value of less than 0.05 and a Bayesian false-discovery probability of less than 0.05. For protein-truncating variants in 19 of the remaining 25 genes, the upper limit of the 95% confidence interval of the odds ratio for breast cancer overall was less than 2.0. For protein-truncating variants in ATM and CHEK2, odds ratios were higher for estrogen receptor (ER)–positive disease than for ER-negative disease; for protein-truncating variants in BARD1, BRCA1, BRCA2, PALB2, RAD51C, and RAD51D, odds ratios were higher for ER-negative disease than for ER-positive disease. Rare missense variants (in aggregate) in ATM, CHEK2, and TP53 were associated with a risk of breast cancer overall with a P value of less than 0.001. For BRCA1, BRCA2, and TP53, missense variants (in aggregate) that would be classified as pathogenic according to standard criteria were associated with a risk of breast cancer overall, with the risk being similar to that of protein-truncating variants.ConclusionsThe results of this study define the genes that are most clinically useful for inclusion on panels for the prediction of breast cancer risk, as well as provide estimates of the risks associated with protein-truncating variants, to guide genetic counseling. (Funded by European Union Horizon 2020 programs and others.)

Gene Selection for Cancer Classification: A New Hybrid Filter-C5.0 Approach for Breast Cancer Risk Prediction

Gene Selection for Cancer Classification: A New Hybrid Filter-C5.0 Approach for Breast Cancer Risk Prediction

Impact of Personalized Genetic Breast Cancer Risk Estimation With Polygenic Risk Scores on Preventive Endocrine Therapy Intention and Uptake.

Endocrine therapy is underutilized to reduce breast cancer incidence among women at increased risk. Polygenic risk scores (PRSs) assessing 77 breast cancer genetic susceptibility loci personalizes risk estimates. We examined effect of personalized PRS breast cancer risk prediction on intention to take and endocrine therapy uptake among women at increased risk. Eligible participants had a 10-year breast cancer risk ≥5% by Tyrer-Cuzick model [International Breast Cancer Intervention Study (IBIS)] or ≥3.0 % 5-year Gail Model risk with no breast cancer history or hereditary breast cancer syndrome. Breast cancer risk was estimated, endocrine therapy options were discussed, and endocrine therapy intent was assessed at baseline. After genotyping, PRS-updated breast cancer risk estimates, endocrine therapy options, and intent to take endocrine therapy were reassessed; endocrine therapy uptake was assessed during follow-up. From March 2016 to October 2017, 151 patients were enrolled [median (range) age, 56.1 (36.0-76.4 years)]. Median 10-year and lifetime IBIS risks were 7.9% and 25.3%. Inclusion of PRS increased lifetime IBIS breast cancer risk estimates for 81 patients (53.6%) and reduced risk for 70 (46.4%). Of participants with increased breast cancer risk by PRS, 39 (41.9%) had greater intent to take endocrine therapy; of those with decreased breast cancer risk by PRS, 28 (46.7%) had less intent to take endocrine therapy (P < 0.001). On multivariable regression, increased breast cancer risk by PRS was associated with greater intent to take endocrine therapy (P < 0.001). Endocrine therapy uptake was greater among participants with increased breast cancer risk by PRS (53.4%) than with decreased risk (20.9%; P < 0.001). PRS testing influenced intent to take and endocrine therapy uptake. Assessing PRS effect on endocrine therapy adherence is needed.Prevention Relevance: Counseling women at increased breast cancer risk using polygenic risk score (PRS) risk estimates can significantly impact preventive endocrine therapy uptake. Further development of PRS testing to personalize breast cancer risk assessments and endocrine therapy counselling may serve to potentially reduce the incidence of breast cancer in the future.

Integrating Clinical and Polygenic Factors to Predict Breast Cancer Risk in Women Undergoing Genetic Testing.

PURPOSEScreening and prevention decisions for women at increased risk of developing breast cancer depend on genetic and clinical factors to estimate risk and select appropriate interventions. Integration of polygenic risk into clinical breast cancer risk estimators can improve discrimination. However, correlated genetic effects must be incorporated carefully to avoid overestimation of risk.MATERIALS AND METHODSA novel Fixed-Stratified method was developed that accounts for confounding when adding a new factor to an established risk model. A combined risk score (CRS) of an 86–single-nucleotide polymorphism polygenic risk score and the Tyrer-Cuzick v7.02 clinical risk estimator was generated with attenuation for confounding by family history. Calibration and discriminatory accuracy of the CRS were evaluated in two independent validation cohorts of women of European ancestry (N = 1,615 and N = 518). Discrimination for remaining lifetime risk was examined by age-adjusted logistic regression. Risk stratification with a 20% risk threshold was compared between CRS and Tyrer-Cuzick in an independent clinical cohort (N = 32,576).RESULTSSimulation studies confirmed that the Fixed-Stratified method produced accurate risk estimation across patients with different family history. In both validation studies, CRS and Tyrer-Cuzick were significantly associated with breast cancer. In an analysis with both CRS and Tyrer-Cuzick as predictors of breast cancer, CRS added significant discrimination independent of that captured by Tyrer-Cuzick (P < 10−11 in validation 1; P < 10−7 in validation 2). In an independent cohort, 18% of women shifted breast cancer risk categories from their Tyrer-Cuzick–based risk compared with risk estimates by CRS.CONCLUSIONIntegrating clinical and polygenic factors into a risk model offers more effective risk stratification and supports a personalized genomic approach to breast cancer screening and prevention.

Toward robust mammography-based models for breast cancer risk.

Improved breast cancer risk models enable targeted screening strategies that achieve earlier detection and less screening harm than existing guidelines. To bring deep learning risk models to clinical practice, we need to further refine their accuracy, validate them across diverse populations, and demonstrate their potential to improve clinical workflows. We developed Mirai, a mammography-based deep learning model designed to predict risk at multiple timepoints, leverage potentially missing risk factor information, and produce predictions that are consistent across mammography machines. Mirai was trained on a large dataset from Massachusetts General Hospital (MGH) in the United States and tested on held-out test sets from MGH, Karolinska University Hospital in Sweden, and Chang Gung Memorial Hospital (CGMH) in Taiwan, obtaining C-indices of 0.76 (95% confidence interval, 0.74 to 0.80), 0.81 (0.79 to 0.82), and 0.79 (0.79 to 0.83), respectively. Mirai obtained significantly higher 5-year ROC AUCs than the Tyrer-Cuzick model ( P < 0.001) and prior deep learning models Hybrid DL ( P < 0.001) and Image-Only DL ( P < 0.001), trained on the same dataset. Mirai more accurately identified high-risk patients than prior methods across all datasets. On the MGH test set, 41.5% (34.4 to 48.5) of patients who would develop cancer within 5 years were identified as high risk, compared with 36.1% (29.1 to 42.9) by Hybrid DL ( P = 0.02) and 22.9% (15.9 to 29.6) by the Tyrer-Cuzick model ( P < 0.001).

A streamlined model for use in clinical breast cancer risk assessment maintains predictive power and is further improved with inclusion of a polygenic risk score.

Five-year absolute breast cancer risk prediction models are required to comply with national guidelines regarding risk reduction regimens. Models including the Gail model are under-utilized in the general population for various reasons, including difficulty in accurately completing some clinical fields. The purpose of this study was to determine if a streamlined risk model could be designed without substantial loss in performance. Only the clinical risk factors that were easily answered by women will be retained and combined with an objective validated polygenic risk score (PRS) to ultimately improve overall compliance with professional recommendations. We first undertook a review of a series of 2,339 Caucasian, African American and Hispanic women from the USA who underwent clinical testing. We first used deidentified test request forms to identify the clinical risk factors that were best answered by women in a clinical setting and then compared the 5-year risks for the full model and the streamlined model in this clinical series. We used OPERA analysis on previously published case-control data from 11,924 Gail model samples to determine clinical risk factors to include in a streamlined model: first degree family history and age that could then be combined with the PRS. Next, to ensure that the addition of PRS to the streamlined model was indeed beneficial, we compared risk stratification using the Streamlined model with and without PRS for the existing case-control datasets comprising 1,313 cases and 10,611 controls of African-American (n = 7421), Caucasian (n = 1155) and Hispanic (n = 3348) women, using the area under the curve to determine model performance. The improvement in risk discrimination from adding the PRS risk score to the Streamlined model was 52%, 46% and 62% for African-American, Caucasian and Hispanic women, respectively, based on changes in log OPERA. There was no statistically significant difference in mean risk scores between the Gail model plus risk PRS compared to the Streamlined model plus PRS. This study demonstrates that validated PRS can be used to streamline a clinical test for primary care practice without diminishing test performance. Importantly, by eliminating risk factors that women find hard to recall or that require obtaining medical records, this model may facilitate increased clinical adoption of 5-year risk breast cancer risk prediction test in keeping with national standards and guidelines for breast cancer risk reduction.

Deep Learning Image Analysis of Benign Breast Disease to Identify Subsequent Risk of Breast Cancer.

BackgroundNew biomarkers of risk may improve breast cancer (BC) risk prediction. We developed a computational pathology method to segment benign breast disease (BBD) whole slide images into epithelium, fibrous stroma, and fat. We applied our method to the BBD BC nested case-control study within the Nurses’ Health Studies to assess whether computer-derived tissue composition or a morphometric signature was associated with subsequent risk of BC.MethodsTissue segmentation and nuclei detection deep-learning networks were established and applied to 3795 whole slide images from 293 cases who developed BC and 1132 controls who did not. Percentages of each tissue region were calculated, and 615 morphometric features were extracted. Elastic net regression was used to create a BC morphometric signature. Associations between BC risk factors and age-adjusted tissue composition among controls were assessed using analysis of covariance. Unconditional logistic regression, adjusting for the matching factors, BBD histological subtypes, parity, menopausal status, and body mass index evaluated the relationship between tissue composition and BC risk. All statistical tests were 2-sided.ResultsAmong controls, direction of associations between BBD subtypes, parity, and number of births with breast composition varied by tissue region; select regions were associated with childhood body size, body mass index, age of menarche, and menopausal status (all P < .05). A higher proportion of epithelial tissue was associated with increased BC risk (odds ratio = 1.39, 95% confidence interval = 0.91 to 2.14, for highest vs lowest quartiles, Ptrend = .047). No morphometric signature was associated with BC.ConclusionsThe amount of epithelial tissue may be incorporated into risk assessment models to improve BC risk prediction.

Deep Learning-Based Artificial Intelligence for Mammography.

During the past decade, researchers have investigated the use of computer-aided mammography interpretation. With the application of deep learning technology, artificial intelligence (AI)-based algorithms for mammography have shown promising results in the quantitative assessment of parenchymal density, detection and diagnosis of breast cancer, and prediction of breast cancer risk, enabling more precise patient management. AI-based algorithms may also enhance the efficiency of the interpretation workflow by reducing both the workload and interpretation time. However, more in-depth investigation is required to conclusively prove the effectiveness of AI-based algorithms. This review article discusses how AI algorithms can be applied to mammography interpretation as well as the current challenges in its implementation in real-world practice.

Applications of Artificial Intelligence in Mammography from a Development and Validation Perspective

유방촬영술은 유방암 검진 및 진단을 위한 기본적인 영상 검사이지만, 판독이 어려우며 높은 숙련도를 필요로 한다고 잘 알려져 있다. 이러한 어려움을 극복하기 위해 최근 몇 년 사이에 인공지능을 이용한 유방암 검출 알고리즘들이 활발히 연구되고 있다. 본 종설에서 저자는 고전적인 computer-aided detection 소프트웨어 대비 최근 많이 사용되는 딥러닝의 특징을 알아보고, 딥러닝 알고리즘의 개발 방법과 임상적 검증 방법에 대해서 기술하였다. 또한 딥러닝 기반의 검진 유방촬영술의 판독 방법 분류, 유방 치밀도 평가, 그리고 유방암 위험도 예측 모델 등을 위한 딥러닝 연구들도 소개하였다. 마지막으로 유방촬영술 관련 인공지능 기술들에 대한 영상의학과 전문의의 관심과 의견의 필요성을 기술하였다.

CARDIOTOXICITY RISK PREDICTION IN BREAST CANCER PATIENTS.

to develop a CT risk model score taking into account cardiological, oncological and individual risks. The study included 52 breast cancer patients with retrospective analysis of their medicalhistory, risk factors, and echocardiographic parameters before the onset and in 12 months follow up. Based on theanalysis of the data, a CT risk model score was developed and recommended. The patients were divided into groupsaccording to the score: Group 1 - low risk of CT development - score < 4 points, Group 2 - moderate risk - 5-7points, Group 3 - high risk > 8 points. According to the scale, BC patients with a total of > 8 points are consideredto be at high risk for CT complications. Radiation therapy and anthracyclines, as well as associated cardiovasculardiseases were the most important risk factors of CT. Based on the study of retrospective analysis of risk factors, data of heart function monitoring during follow-up,the risk model score of cardiotoxicity has been developed for the BC patients' stratification. According to the proposedscore risk model, BC patients with a total score of > 8 points considered to have high risk of cardiotoxic complications. Using of the proposed risk model score with calculation of CT risk factors both before the beginningand during cancer therapy is important, because it allows predicting the risk of CT development - to identify high-risk patients, accordingly, to develop an individualized plan for cardiac function monitoring and to start timely cardioprotective therapy.

Breast cancer risk prediction in African women using Random Forest Classifier

IntroductionOne of the most important steps in combating breast cancer is early and accurate diagnosis. Unfortunately, breast cancer is asymptomatic at the early stage, although some symptoms are presented at a later time, but at symptomatic stage treatment could be complicated or even become impossible thereby leading to death. Proper risk assessment is hence very important in reducing mortality. Some computational techniques have been developed for breast cancer risk assessment in the developed world, but such techniques do not work well in Africa because of the difference in risk profiles of African women e.g. later menarche, low drug abuse and low smoking rate. AimIn this work, we propose a bespoke risk prediction model for African women using Random Forest Classifier (RFC) machine learning technique. MethodsA total of 180 subjects were studied out of which 90 were confirmed cases of breast cancer and 90 were benign. Twenty-five risk factors were included, for example, smoking, alcohol intake, occupational hazards and age at menopause. Four approaches were empirically used in the feature selection, these are the use of Chi-Square, mutual information gain, Spearman correlation and the entire features. RFC algorithm was used to develop the prediction model. ResultsWe found that family history of breast cancer, dense breast, deliberate abortion, age at first child, fruit intake and regular exercise are predictors of breast cancer. The RFC model gave an accuracy of 91.67%, sensitivity of 87.10%, specificity of 96.55% and Area under curve (AUC) of 92% when all the risk factors were included in the model while an accuracy of 96.67%, sensitivity of 93.75%, specificity of 100% and AUC of 97% were obtained when correlation-selected features were included in the model. The Chi-Square selected features gave the best performance with 98.33% accuracy, 100% sensitivity, 96.55 specificity and 98% AUC. Mutual information gain selected feature gave the same results as Chi-Square selected features. ConclusionRandom Forest Classifier has a good potential at predicting the risk of breast cancer in African women. The study helped to identify the risk factors of breast cancer in African women. This is a valuable information which can help African women to pay attention to those risk factors with the intention of reducing the incidence of breast cancer in Africa.

Breast Cancer-Related Low Penetrance Genes.

Susceptibility genes involved in disease etiology and prognosis are categorized into two groups: high penetrance genes (i.e., BRCA1, CHEK2, ATM, etc.) and low penetrance genes (i.e., NATs, GSTs, CYPs, etc., and variants identified by genome-wide association studies). Since low penetrance genes have high population attributable risk, the usefulness of those genes to research on breast cancer prevention is not small. In this chapter, the previous studies on low-penetrance genetic susceptibility through a candidate gene approach and genome-wide association of breast cancer were summarized. The contribution of low-penetrance susceptibility genes to the breast cancer risk prediction models will also be discussed on the utility in clinical or public health application.

Histological Findings of Mammary Gland Development and Risk of Breast Cancer in BRCA1 Mutant Mouse Models.

PurposeThe breast cancer susceptibility gene, BRCA1, is involved in normal development and carcinogenesis of mammary glands. Here, we aimed to evaluate the relationship between histological findings of mammary gland development and breast cancer risk in BRCA1 mutant mice.MethodsFive BRCA1 mutant mice and five non-mutant FVB/NJ mice were used for each group of 1-month-old (pubertal), 3-month-old (fertile), and 8-month-old (menopausal) mice. In another experiment, 15 BRCA1 mutant mice were followed up to 8 months after birth and classified into tumor-bearing (11 mice) and tumor-free (4 mice) groups. Excised mammary gland tissues were stained with Carmine Alum, and the number of terminal end buds (or alveolar buds), branching density, and duct elongation were measured using image analysis programs. Differences between the two groups were assessed using paired t-test.ResultsOne-month-old BRCA1 mutant mice showed a higher number of terminal end buds (23.8 ± 1.0 vs. 15.6 ± 0.8, p = 0.0002), branching density (11.7 ± 0.4 vs. 9.6 ± 0.5%, p = 0.0082), and duct elongation (9.7 ± 0.7 vs. 7.3 ± 0.4 mm, p = 0.0186) than controls. However, there was no difference between the 3- and 8-month-old groups. In BRCA1 mutant mice, the tumor-bearing group showed a significantly higher number of alveolar buds (142.7 ± 5.5 vs. 105.5 ± 5.4, p = 0.0008) and branching density (30.0 ± 1.0 vs. 24.1 ± 1.1%, p = 0.008) than the tumor-free group; however, duct elongation was not different (23.9 ± 0.6 vs. 23.6 ± 0.6 mm, p = 0.8099) between the groups.ConclusionBRCA1 mutant mice exhibited early pubertal mammary gland development and delayed age-related mammary gland involution was associated with breast cancer. Our results may have clinical implications for predicting breast cancer risk and developing prevention strategies for BRCA1 mutation carriers.

Prediction of Breast Cancer Risk Factors Using Neural Network Analytics: an Empirical Study

Breast cancer is the most prevalent cancer affecting women. Identifying breast cancer risk factors are crucially to be established. The main objectives of the present study were to identify the predictors of breast cancer risk factors and their relative importance using neural network analysis. The present study depended on neural network analysis of data posted on [1]. The dataset is about predictors of breast cancer. There were 9 covariates included and one dependent variable, output (no disease (1), or disease (2)). The dataset was composed of 116 cases. The category of no disease comprised 79 (68.1%) cases, whereas the disease category included 37 cases (31.9%). Architecture model was built with some characteristics such as training part: gross entropy error was 23.7884, the percent of incorrect predictions was 10.1%. Stopping rule used was 1 consecutive step(s) with no decrease in error. For testing part, gross entropy error was 14,327, the percent of incorrect predictions was 13.5%. The relative importance of breast cancer was in the following order: glucose, resistin, BMI, age, leptin, adiponectin, MCP-1, insulin, and HOMA. Taken together, neural network analysis is an efficient tool to predict breast cancer risk factors.

The Breast Cancer Cohort Study in Chinese Women: the construction and progress of the pan-shared biobank

Objective: Biobank construction plays an irreplaceable role in the research of accurate prevention and treatment of diseases. Shared biobank network based on a large crowd queue is the way of the future. This subject is one of the key contents of national precision medicine "The Breast Cancer Cohort Study in Chinese Women: (BCCS-CW)" , aiming to solve the bottleneck of insufficient standardization and sharing. Methods: The establishment of "entity library-information library-extension library" , the widely Shared network of biobank of breast cancer specific disease cohort, and the establishment of strict standard setting and quality control standard to construct the standardized biobank. Results: This biobank provides a shared biobank resource for breast cancer risk assessment, prediction and early warning, early screening, classification, individualized treatment, efficacy and safety prediction and monitoring and other accurate prevention and treatment programs and clinical decision-making system research. Conclusion: The data of this biological sample bank is refined and complete, and the sample size of cases is sufficient, which can meet the research needs of medical big data, genomics, metabonomics, epigenetics and other fields.

Novel mammogram‐based measures improve breast cancer risk prediction beyond an established mammographic density measure

Mammograms contain information that predicts breast cancer risk. We developed two novel mammogram-based breast cancer risk measures based on image brightness (Cirrocumulus) and texture (Cirrus). Their risk prediction when fitted together, and with an established measure of conventional mammographic density (Cumulus), is not known. We used three studies consisting of: 168 interval cases and 498 matched controls; 422 screen-detected cases and 1197 matched controls; and 354 younger-diagnosis cases and 944 controls frequency-matched for age at mammogram. We conducted conditional and unconditional logistic regression analyses of individually- and frequency-matched studies, respectively. We estimated measure-specific risk gradients as the change in odds per standard deviation of controls after adjusting for age and body mass index (OPERA) and calculated the area under the receiver operating characteristic curve (AUC). For interval, screen-detected and younger-diagnosis cancer risks, the best fitting models (OPERAs [95% confidence intervals]) involved: Cumulus (1.81 [1.41-2.31]) and Cirrus (1.72 [1.38-2.14]); Cirrus (1.49 [1.32-1.67]) and Cirrocumulus (1.16 [1.03 to 1.31]); and Cirrus (1.70 [1.48 to 1.94]) and Cirrocumulus (1.46 [1.27-1.68]), respectively. The AUCs were: 0.73 [0.68-0.77], 0.63 [0.60-0.66], and 0.72 [0.69-0.75], respectively. Combined, our new mammogram-based measures have twice the risk gradient for screen-detected and younger-diagnosis breast cancer (P ≤ 10-12 ), have at least the same discriminatory power as the current polygenic risk score, and are more correlated with causal factors than conventional mammographic density. Discovering more information about breast cancer risk from mammograms could help enable risk-based personalised breast screening.

Simplified Breast Risk Tool Integrating Questionnaire Risk Factors, Mammographic Density, and Polygenic Risk Score: Development and Validation.

Clinical use of breast cancer risk prediction requires simplified models. We evaluate a simplified version of the validated Rosner-Colditz model and add percent mammographic density (MD) and polygenic risk score (PRS), to assess performance from ages 45-74. We validate using the Mayo Mammography Health Study (MMHS). We derived the model in the Nurses' Health Study (NHS) based on: MD, 77 SNP PRS and a questionnaire score (QS; lifestyle and reproductive factors). A total of 2,799 invasive breast cancer cases were diagnosed from 1990-2000. MD (using Cumulus software) and PRS were assessed in a nested case-control study. We assess model performance using this case-control dataset and evaluate 10-year absolute breast cancer risk. The prospective MMHS validation dataset includes 21.8% of women age <50, and 434 incident cases identified over 10 years of follow-up. In the NHS, MD has the highest odds ratio (OR) for 10-year risk prediction: ORper SD = 1.48 [95% confidence interval (CI): 1.31-1.68], followed by PRS, ORper SD = 1.37 (95% CI: 1.21-1.55) and QS, ORper SD = 1.25 (95% CI: 1.11-1.41). In MMHS, the AUC adjusted for age + MD + QS 0.650; for age + MD + QS + PRS 0.687, and the NRI was 6% in cases and 16% in controls. A simplified assessment of QS, MD, and PRS performs consistently to discriminate those at high 10-year breast cancer risk. This simplified model provides accurate estimation of 10-year risk of invasive breast cancer that can be used in a clinical setting to identify women who may benefit from chemopreventive intervention.See related commentary by Tehranifar et al., p. 587.