Risk prediction models for breast cancer: a systematic review

Abstract

ObjectivesTo systematically review and critically appraise published studies of risk prediction models for breast cancer in the general population without breast cancer, and provide evidence for future research in the field.DesignSystematic review using the Prediction model study Risk Of Bias Assessment Tool (PROBAST) framework.Data sourcesPubMed, the Cochrane Library and Embase were searched from inception to 16 December 2021.Eligibility criteriaWe included studies reporting multivariable models to estimate the individualised risk of developing female breast cancer among different ethnic groups. Search was limited to English language only.Data extraction and synthesisTwo reviewers independently screened, reviewed, extracted and assessed studies with discrepancies resolved through discussion or a third reviewer. Risk of bias was assessed according to the PROBAST framework.Results63 894 studies were screened and 40 studies with 47 risk prediction models were included in the review. Most of the studies used logistic regression to develop breast cancer risk prediction models for Caucasian women by case–control data. The most widely used risk factor was reproductive factors and the highest area under the curve was 0.943 (95% CI 0.919 to 0.967). All the models included in the review had high risk of bias.ConclusionsNo risk prediction models for breast cancer were recommended for different ethnic groups and models incorporating mammographic density or single-nucleotide polymorphisms among Asian women are few and poorly needed. High-quality breast cancer risk prediction models assessed by PROBAST should be developed and validated, especially among Asian women.PROSPERO registration numberCRD42020202570.

Acceptability of risk stratification within population‐based cancer screening from the perspective of the general public: A mixed‐methods systematic review

“… 2 A multitude of risk prediction models have been developed across different cancer types using a variety of risk factors. 7 , 8 , 9 , 10 …”

“…Additionally, personal risk information may confer benefits for screening decision‐making and opportunities to engage in primary prevention and risk management, such as lifestyle change, risk‐reducing medication or prophylactic surgery 2 . A multitude of risk prediction models have been developed across different cancer types using a variety of risk factors 7–10 …”

“…2 A multitude of risk prediction models have been developed across different cancer types using a variety of risk factors. [7][8][9][10] Risk stratification incurs ethical challenges associated with introducing systematic differences between population subgroups, including concerns about equity and accessibility, for example, which risk factors to include in risk modelling, including modifiable factors like alcohol consumption or smoking, and how to screen participants with missing data. Public acceptability is fundamental to success, as it has direct implications for uptake and adherence.…”

A contemporary review of breast cancer risk factors and the role of artificial intelligence

“…Race or ethnicity and geographic location: Research underscores significant variations in breast cancer predisposition across ethnicities and geographic locations, influenced by genetic, environmental, and socioeconomic factors. Studies like ( 112 ) emphasize diverse risk prediction models’ necessity, especially for Asian women. Disparities persist despite similar treatments, as shown by ( 4 ) among Black and White women.…”

Breast cancer risk prediction using machine learning: a systematic review

“…Precise assessment of an individual woman’s risk of breast cancer is essential for customizing screening and preventive measures according to the specific risk levels. Acknowledging the importance of early breast cancer detection and risk categorization, several models, including Gail, BCSC, Rosner–Colditz, and Tyrer–Cuzick, have been developed to predict breast cancer risk ( 13 ).…”