Breast cancer is one of the most common types of cancer among women worldwide, therefore an early and precise process of diagnostics plays an important role in improving the prognosis and outcome of treatment. The application of artificial intelligence (AI) allows faster and more precise analysis of medical imaging, which contributes to the early detection of tumors and lowers the number of false-negative results. This review article analyzed 60 scientific papers and using the most recent findings about this topic, searched for AI implementation in breast cancer research and how AI may improve overall survival outcomes for breast cancer patients.

Introduction: Breast cancer (BC) is a malignant disease that predominantly affects women, with known genetic components such as mutations in tumor suppressor genes BRCA1 and BRCA2. Other risk factors include unhealthy lifestyles, lack of physical activity, and consumption of alcohol and cigarettes. Aging also plays a role in BC development, with hormonal influences such as estrogen and progesterone promoting cancer growth. Material and Methods: Research was conducted using data collection tools for risk factors and tumor markers from primary healthcare unit records. The sample comprised 200 women, divided into two groups based on BC diagnosis, with complete medical documentation. Male BC cases were excluded. Results: Statistical significance was found between genetic components, family history, aging, obesity, alcohol and cigarette consumption, longer hormone exposure, and female BC development using the Chi-Square test, confirmed by Fisher's Exact test. Tumor markers CA 15-3, CEA, CA 19-9, and CA 125 were useful for BC screening and metastasis detection, as determined by the One Sample T-test. In Sarajevo Canton, invasive ductal BC was the most common type among women, while lobular carcinoma in situ was the least common. Conclusion: Correlations between risk factors, including aging, unhealthy lifestyles, and hormone exposure, and increased BC risk were confirmed. Tumor markers CA 15-3, CEA, CA 19-9, and CA 125 were effective in diagnosis, screening, and metastasis detection in females, with sensitivity for regression detection at 81.8% and specificity at 100%.