Background: Breast cancer is the most common cancer among Iranian women. Therefore, its early diagnosis can reduce death and health costs. There is no specific method or model for detecting individuals at a high-risk of breast cancer in Iran. Thus, a native model for detecting groups at higher risk of breast cancer seems necessary. This research was designed to develop a predictive model for detecting women with high-risk of breast cancer in Iran.
Patients and Methods: With a case control study, we will recruit 1000 women diagnosed with breast cancer from Tehran’s cancer centers and another 1000 healthy controls from all regions of Tehran City. Data will be collected by a valid and reliable questionnaire consisting of 8 sections: 1) demographic and socio-economic information; 2) data related to pregnancy, medical records and life events; 3) family history of cancer and gynecological diseases; 4) history of drug use and occupational exposures; 5) weight and height measurement; 6) physical activity; 7) use of cigarettes, hookah, alcohol, narcotics; 8) food consumption. Data analysis will be done with logistic regression models; to check the appropriateness of the model, both ROC and net reclassification index will be applied. Moreover, h-fold cross-validation and bootstrap techniques will be applied to examine the validity of the model.
Conclusions: We intend to build a suitable prediction model for detecting high-risk groups of breast cancer in Iran. The results can be useful to estimate the risk of breast cancer for health service providers in healthcare centers.