Factors Influencing Mammographic Density in Asian Women: A Retrospective Cohort Study in the Northeast Region of Peninsular Malaysia

Associations between breast cancer risk factors and mammographic breast density in a large cross-section of Korean women

BACKGROUND

We investigated the association between established risk factors for breast cancer and mammographic breast density in Korean women.

METHODS

This large cross-sectional study included 8 460 928 women aged >40 years, who were screened for breast cancer between 2009 and 2018. Breast density was assessed using the Breast Imaging Reporting and Data System. This study used multiple logistic regression analyses of age, BMI, age at menarche, menopausal status, menopausal age, parity, breastfeeding status, oral contraceptive use, family history of breast cancer, physical activity, smoking, drinking and hormone replacement therapy use to investigate their associations with mammographic breast density. Analyses were performed using SAS software.

RESULTS

Of 8 460 928 women, 4 139 869 (48.9%) had nondense breasts and 4 321 059 (51.1%) had dense breasts. Factors associated with dense breasts were: earlier age at menarche [<15 vs. ≥15; adjusted odds ratio (aOR), 1.18; 95% confidence interval (CI), 1.17-1.18], premenopausal status (aOR, 2.01; 95% CI, 2.00-2.02), later age at menopause (≥52 vs. <52; aOR, 1.23; 95% CI, 1.22-1.23), nulliparity (aOR, 1.64; 95% CI, 1.63-1.65), never breastfed (aOR, 1.23; 95% CI, 1.23-1.24) and use of hormone replacement therapy (aOR, 1.29; 95% CI, 1.28-1.29). Women with a higher BMI and the use of oral contraceptives were more likely to have nondense breasts.

CONCLUSION

Lower BMI, reproductive health and behavioral factors were associated with dense breasts in Korean women. Additional research should investigate the relationship between mammographic breast density, breast cancer risk factors and breast cancer risk.

Over-the-Counter Breast Cancer Classification Using Machine Learning and Patient Registration Records

This study aims to determine the feasibility of machine learning (ML) and patient registration record to be utilised to develop an over-the-counter (OTC) screening model for breast cancer risk estimation. Data were retrospectively collected from women who came to the Hospital Universiti Sains Malaysia, Malaysia for breast-related problems. Eight ML models were used: k-nearest neighbour (kNN), elastic-net logistic regression, multivariate adaptive regression splines, artificial neural network, partial least square, random forest, support vector machine (SVM), and extreme gradient boosting. Features utilised for the development of the screening models were limited to information in the patient registration form. The final model was evaluated in terms of performance across a mammographic density. Additionally, the feature importance of the final model was assessed using the model agnostic approach. kNN had the highest Youden J index, precision, and PR-AUC, while SVM had the highest F2 score. The kNN model was selected as the final model. The model had a balanced performance in terms of sensitivity, specificity, and PR-AUC across the mammographic density groups. The most important feature was the age at examination. In conclusion, this study showed that ML and patient registration information are feasible to be used as the OTC screening model for breast cancer.