Integrations of Artificial Intelligence to Predict Breast Cancer Risk from Routine Blood Tests: A Narrative Review

Abstract

Breast cancer remains a leading cause of cancer-related mortality globally, with early detection being vital for improving patient outcomes. Traditional diagnostic methods such as mammography and biopsy, although effective, have limitations including cost, invasiveness, and limited accessibility in resource-constrained settings. Routine blood tests offer a minimally invasive, widely available, and cost-effective alternative source of data that could aid in early risk assessment if analyzed effectively. Recent advances in artificial intelligence (AI), particularly machine learning and deep learning, have demonstrated significant potential in extracting meaningful patterns from complex biomedical data. This review examines the current state of AI applications leveraging routine blood test parameters—including hematological and biochemical markers—to predict breast cancer risk. The integration of AI facilitates improved risk stratification, enabling personalized screening approaches and potentially reducing unnecessary invasive procedures. Despite promising results, challenges such as data variability, limited large-scale validation, and model interpretability remain. Future efforts should focus on multicenter studies, development of explainable AI models, and seamless integration into clinical workflows. Keywords: Artificial Intelligence, Breast Cancer Prediction, Routine Blood Tests, Machine Learning, Hematological Markers