A comparison between different prediction models for invasive breast cancer occurrence in the French E3N cohort

Understanding the contribution of lifestyle in breast cancer risk prediction: a systematic review of models applicable to Europe

BACKGROUND

Breast cancer (BC) is a significant health concern among European women, with the highest prevalence rates among all cancers. Existing BC prediction models account for major risks such as hereditary, hormonal and reproductive factors, but research suggests that adherence to a healthy lifestyle can reduce the risk of developing BC to some extent. Understanding the influence and predictive role of lifestyle variables in current risk prediction models could help identify actionable, modifiable, targets among high-risk population groups.

PURPOSE

To systematically review population-based BC risk prediction models applicable to European populations and identify lifestyle predictors and their corresponding parameter values for a better understanding of their relative contribution to the prediction of incident BC.

METHODS

A systematic review was conducted in PubMed, Embase and Web of Science from January 2000 to August 2021. Risk prediction models were included if (i) developed and/or validated in adult cancer-free women in Europe, (ii) based on easily ascertained information, and (iii) reported models' final predictors. To investigate further the comparability of lifestyle predictors across models, estimates were standardised into risk ratios and visualised using forest plots.

RESULTS

From a total of 49 studies, 33 models were developed and 22 different existing models, mostly from Gail (22 studies) and Tyrer-Cuzick and co-workers (12 studies) were validated or modified for European populations. Family history of BC was the most frequently included predictor (31 models), while body mass index (BMI) and alcohol consumption (26 and 21 models, respectively) were the lifestyle predictors most often included, followed by smoking and physical activity (7 and 6 models respectively). Overall, for lifestyle predictors, their modest predictive contribution was greater for riskier lifestyle levels, though highly variable model estimates across different models.

CONCLUSIONS

Given the increasing BC incidence rates in Europe, risk models utilising readily available risk factors could greatly aid in widening the population coverage of screening efforts, while the addition of lifestyle factors could help improving model performance and serve as intervention targets of prevention programmes.

Mammographic Classification of Breast Cancer Microcalcifications through Extreme Gradient Boosting

In this paper, we proposed an effective and efficient approach to the classification of breast cancer microcalcifications and evaluated the mathematical model for calcification on mammography with a large medical dataset. We employed several semi-automatic segmentation algorithms to extract 51 calcification features from mammograms, including morphologic and textural features. We adopted extreme gradient boosting (XGBoost) to classify microcalcifications. Then, we compared other machine learning techniques, including k-nearest neighbor (kNN), adaboostM1, decision tree, random decision forest (RDF), and gradient boosting decision tree (GBDT), with XGBoost. XGBoost showed the highest accuracy (90.24%) for classifying microcalcifications, and kNN demonstrated the lowest accuracy. This result demonstrates that it is essential for the classification of microcalcification to use the feature engineering method for the selection of the best composition of features. One of the contributions of this study is to present the best composition of features for efficient classification of breast cancers. This paper finds a way to select the best discriminative features as a collection to improve the accuracy. This study showed the highest accuracy (90.24%) for classifying microcalcifications with AUC = 0.89. Moreover, we highlighted the performance of various features from the dataset and found ideal parameters for classifying microcalcifications. Furthermore, we found that the XGBoost model is suitable both in theory and practice for the classification of calcifications on mammography.

Feasibility of personalized screening and prevention recommendations in the general population through breast cancer risk assessment: results from a dedicated risk clinic

PURPOSE

A personalized approach to prevention and early detection based on known risk factors should contribute to early diagnosis and treatment of breast cancer. We initiated a risk assessment clinic for all women wishing to undergo an individual breast cancer risk assessment.

METHODS

Women underwent a complete breast cancer assessment including a questionnaire, mammogram with evaluation of breast density, collection of saliva sample, consultation with a radiologist, and a breast cancer specialist. Women aged 40 or older, with 0 or 1 first-degree relative with breast cancer diagnosed after the age of 40 were eligible for risk assessment using MammoRisk, a machine learning-based tool that provides an individual 5-year estimated risk of developing breast cancer based on the patient's clinical data and breast density, with or without polygenic risk scores (PRSs). DNA was extracted from saliva samples for genotyping of 76 single-nucleotide polymorphisms. The individual risk was communicated to the patient, with individualized screening and prevention recommendations.

RESULTS

A total of 290 women underwent breast cancer assessment, among which 196 women (68%) were eligible for risk assessment using MammoRisk (median age 52, range 40-72). When PRS was added to MammoRisk, 40% (n = 78) of patients were assigned a different risk category, with 28% (n = 55) of patients changing from intermediate to moderate or high risk.

CONCLUSION

Individual risk assessment is feasible in the general population. Screening recommendations could be given based on individual risk. The use of PRS changed the risk score and screening recommendations in 40% of women.

[First results of a breast cancer risk assessment and management consultation]

INTRODUCTION

In France, participation in the organized breast cancer screening program remains insufficient. A personalized approach adapted to the risk factors for breast cancer (RBC) should make screening more efficient. A RBC evaluation consultation would therefore make it possible to personalize this screening. Here we report our initial experience.

MATERIAL AND METHOD

This is a prospective study on women who were seen at the RBC evaluation consultation and analyzing: their profile, their risk assessed according to Tyrer Cuzick model (TC)±Mammorisk© (MMR), the existence of an indication of oncogenetic consultation (Eisinger and Manchester score), their satisfaction and the recommended monitoring.

RESULTS

Among the women who had had a TCS and/or MMR evaluation of SCR (n=153), 76 (50%) had a high risk (n=67) or a very high risk (n=9). Almost half (47%) had a possible (15%) or certain (32%) indication to an oncogenetic consultation. Regarding this consultation, 98% of women were satisfied or very satisfied. In total, 60% of women had a change in screening methods.

CONCLUSION

This RBC evaluation consultation satisfies women and for a majority of them, modifies their methods of breast cancer screening.

Assessment of the risk of developing breast cancer using the Gail model in Asian females: A systematic review

Introduction

Currently, the Breast Cancer Risk Assessment Tool (BCRAT), also known as the Gail model (GM) has been widely recognized and adapted for to study disparity in racial and ethnic groups in America including Asian and Pacific Islander American females. However, its applicability outside America remains uncertain due to diversity in epidemiology and risk factors of breast cancer in populations especially in Asian females. We sought to evaluate the performance of the GM to predict breast cancer risk in Asian countries.

Material and methods

This study identified articles published from 2010 by searching PubMed, MEDLINE, Scopus, Web of Science, Google Scholar and gray literature. The initial search terms were breast cancer, mammary, carcinoma, tumor, neoplasm, risk assessment tool, BCRAT, breast cancer prediction, Gail model, Asia, and Asian.

Results

The search yielded 20 articles, with 7 articles addressing the AUC and/or the expected (E) to observed (O) ratio of predicted breast cancer risk, representing the accuracy of the GM in the Asian population. One publication reported the sensitivity and specificity but no AUC. None of the studies were accepted as the standard for reporting prognostic models. Several studies reported good prognostic testing and likely developed a new model modifying the items in the instrument.

Conclusion

The results are not strong enough to develop breast cancer risk in the setting of Asian countries. Involving the breast cancer risk of the Asian population in developing a prognostic model with good statistical understanding is particularly important and can reduce flawed or biased models. Identifying the best methods to achieve well-suited prognostic models in the Asian population should be a priority.

Breast cancer risk prediction in women aged 35-50 years: impact of including sex hormone concentrations in the Gail model

Background

Models that accurately predict risk of breast cancer are needed to help younger women make decisions about when to begin screening. Premenopausal concentrations of circulating anti-Müllerian hormone (AMH), a biomarker of ovarian reserve, and testosterone have been positively associated with breast cancer risk in prospective studies. We assessed whether adding AMH and/or testosterone to the Gail model improves its prediction performance for women aged 35–50.

Methods

In a nested case-control study including ten prospective cohorts (1762 invasive cases/1890 matched controls) with pre-diagnostic serum/plasma samples, we estimated relative risks (RR) for the biomarkers and Gail risk factors using conditional logistic regression and random-effects meta-analysis. Absolute risk models were developed using these RR estimates, attributable risk fractions calculated using the distributions of the risk factors in the cases from the consortium, and population-based incidence and mortality rates. The area under the receiver operating characteristic curve (AUC) was used to compare the discriminatory accuracy of the models with and without biomarkers.

Results

The AUC for invasive breast cancer including only the Gail risk factor variables was 55.3 (95% CI 53.4, 57.1). The AUC increased moderately with the addition of AMH (AUC 57.6, 95% CI 55.7, 59.5), testosterone (AUC 56.2, 95% CI 54.4, 58.1), or both (AUC 58.1, 95% CI 56.2, 59.9). The largest AUC improvement (4.0) was among women without a family history of breast cancer.

Conclusions

AMH and testosterone moderately increase the discriminatory accuracy of the Gail model among women aged 35–50. We observed the largest AUC increase for women without a family history of breast cancer, the group that would benefit most from improved risk prediction because early screening is already recommended for women with a family history.

Electronic supplementary material

The online version of this article (10.1186/s13058-019-1126-z) contains supplementary material, which is available to authorized users.

Assessment of performance of the Gail model for predicting breast cancer risk: a systematic review and meta-analysis with trial sequential analysis

BACKGROUND

The Gail model has been widely used and validated with conflicting results. The current study aims to evaluate the performance of different versions of the Gail model by means of systematic review and meta-analysis with trial sequential analysis (TSA).

METHODS

Three systematic review and meta-analyses were conducted. Pooled expected-to-observed (E/O) ratio and pooled area under the curve (AUC) were calculated using the DerSimonian and Laird random-effects model. Pooled sensitivity, specificity and diagnostic odds ratio were evaluated by bivariate mixed-effects model. TSA was also conducted to determine whether the evidence was sufficient and conclusive.

RESULTS

Gail model 1 accurately predicted breast cancer risk in American women (pooled E/O = 1.03; 95% CI 0.76-1.40). The pooled E/O ratios of Caucasian-American Gail model 2 in American, European and Asian women were 0.98 (95% CI 0.91-1.06), 1.07 (95% CI 0.66-1.74) and 2.29 (95% CI 1.95-2.68), respectively. Additionally, Asian-American Gail model 2 overestimated the risk for Asian women about two times (pooled E/O = 1.82; 95% CI 1.31-2.51). TSA showed that evidence in Asian women was sufficient; nonetheless, the results in American and European women need further verification. The pooled AUCs for Gail model 1 in American and European women and Asian females were 0.55 (95% CI 0.53-0.56) and 0.75 (95% CI 0.63-0.88), respectively, and the pooled AUCs of Caucasian-American Gail model 2 for American, Asian and European females were 0.61 (95% CI 0.59-0.63), 0.55 (95% CI 0.52-0.58) and 0.58 (95% CI 0.55-0.62), respectively. The pooled sensitivity, specificity and diagnostic odds ratio of Gail model 1 were 0.63 (95% CI 0.27-0.89), 0.91 (95% CI 0.87-0.94) and 17.38 (95% CI 2.66-113.70), respectively, and the corresponding indexes of Gail model 2 were 0.35 (95% CI 0.17-0.59), 0.86 (95% CI 0.76-0.92) and 3.38 (95% CI 1.40-8.17), respectively.

CONCLUSIONS

The Gail model was more accurate in predicting the incidence of breast cancer in American and European females, while far less useful for individual-level risk prediction. Moreover, the Gail model may overestimate the risk in Asian women and the results were further validated by TSA, which is an addition to the three previous systematic review and meta-analyses.

TRIAL REGISTRATION

PROSPERO CRD42016047215 .

[Breast cancer screening: On our way to the future]

Breast cancer remains a potentially lethal disease, which requires aggressive treatments and is associated with long-term consequences. Its prognosis is linked to both tumor biology and burden at diagnosis. Although treatments have allowed important improvements in prognosis over the past 20 years, breast cancer screening remains necessary. Mammographic screening allows earlier stage diagnoses and a decrease of breast cancer specific mortality. However, breast cancer screening modalities should be revised with the objective to address demonstrated limitations of mammographic screening (limited benefit, imperfect sensitivity and specificity, overdiagnoses, radiation-induced morbidity). Furthermore, both objective and perceived performances of screening procedures should be improved. Numerous large international efforts are ongoing, leading to scientific progresses that should have rapid clinical implications in this area. Among them is improvement of imaging techniques performance, development of real time diagnosis, and development of new non radiological screening techniques such as the search for circulating tumor DNA, development of biomarkers able to allow precise risk evaluation and stratified screening. As well, overtreatment is currently addressed by biomarker-based de-escalation clinical trials. These advances need to be associated with strong societal support, as well as major paradigm changes regarding the way health and cancer prevention is perceived by individuals.

Discrimination of Breast Cancer with Microcalcifications on Mammography by Deep Learning

Microcalcification is an effective indicator of early breast cancer. To improve the diagnostic accuracy of microcalcifications, this study evaluates the performance of deep learning-based models on large datasets for its discrimination. A semi-automated segmentation method was used to characterize all microcalcifications. A discrimination classifier model was constructed to assess the accuracies of microcalcifications and breast masses, either in isolation or combination, for classifying breast lesions. Performances were compared to benchmark models. Our deep learning model achieved a discriminative accuracy of 87.3% if microcalcifications were characterized alone, compared to 85.8% with a support vector machine. The accuracies were 61.3% for both methods with masses alone and improved to 89.7% and 85.8% after the combined analysis with microcalcifications. Image segmentation with our deep learning model yielded 15, 26 and 41 features for the three scenarios, respectively. Overall, deep learning based on large datasets was superior to standard methods for the discrimination of microcalcifications. Accuracy was increased by adopting a combinatorial approach to detect microcalcifications and masses simultaneously. This may have clinical value for early detection and treatment of breast cancer.