BACKGROUND
Breast cancer is the most common cancer among women globally and a major public health challenge in India, where incidence continues to rise, including among younger women. Strengthening early detection is essential for reducing mortality, and risk assessment tools can help guide women toward timely clinical evaluation. However, most existing prediction models were developed in Western populations and may not adequately reflect the reproductive patterns, lifestyle factors, and demographic characteristics of Indian women. This study aimed to develop and validate a breast cancer risk prediction model specifically suited to the Indian subcontinent.
 
OBJECTIVES
To develop the Snehita BRISK model using locally derived data and to evaluate its ability to identify women at elevated risk of breast cancer. 
 
METHODS
A case–control study was conducted with 660 women diagnosed with breast cancer and 910 controls. Trained interviewers collected information on socio?demographic characteristics, reproductive and menstrual history, breastfeeding duration, family history of breast cancer, and previous breast biopsies. Logistic regression analysis was used to identify independent predictors of breast cancer and to construct the Snehita BRISK model. Model performance was evaluated using ROC analysis and associated accuracy measures.
 
RESULTS
Independent predictors of increased breast cancer risk included older age, earlier menarche, irregular menstrual cycles, nulliparity, later age at first childbirth, family history of breast cancer, and prior breast biopsy. Longer breastfeeding duration was protective. The final model demonstrated an overall predictive accuracy of 67.3%, with an AUC of 0.699, sensitivity of 45.6%, and specificity of 83%. Among women aged 50 years and above, performance improved substantially (accuracy 71.1%; AUC 0.750).
 
IMPLICATIONS
The Snehita BRISK model offers a population?specific approach to breast cancer risk assessment for women in the Indian subcontinent. By identifying women at higher risk and encouraging timely clinical evaluation, the model can support risk?stratified early detection strategies in resource?constrained settings. Presented as the Snehita Breast Cancer Risk Calculator, this tool has the potential to strengthen community?based early detection initiatives. The model has been incorporated into the Kerala state government’s pilot early detection programme, demonstrating its feasibility for public health implementation.