Abstract:
Breast cancer is a leading cause of morbidity and mortality among women worldwide. This study investigates the multifactorial risks associated with breast cancer in Bangladeshi women, emphasizing socio-cultural, lifestyle, and biological factors. Leveraging machine learning techniques and a dataset of 988 samples across 11 attributes, this research identifies significant predictors, including age, tobacco use, and obesity, while highlighting their role in breast cancer risk. The Random Forest model achieved a classification accuracy of 96.59%, underscoring its robustness in predictive analysis. Key findings reveal that modifiable factors, such as dietary habits, taking regular exercise, breastfeeding, OCP uses, tobacco consumption, significantly impact breast cancer risk by altering hormonal balances and amplifying genetic damage pathways. This research provides actionable insights for targeted awareness campaigns, lifestyle interventions, and public health initiatives to mitigate breast cancer risks in Bangladeshi women. It underscores the potential of machine learning in healthcare for early detection and informed decision-making.
