Hematologic Biomarkers and AI in Breast Cancer: A New Frontier for Risk Stratification and Treatment Response Prediction
Abstract:
Background: Precision oncology for breast cancer increasingly relies on hematologic biomarkers and artificial intelligence (AI) to enhance risk stratification and predict treatment response. Recent advancements in liquid biopsy technologies and machine learning have significantly accelerated progress in this field since 2020. Methods: We conducted a comprehensive review of literature published between 2020 and 2025, examining publicly available data on blood-based biomarkers, including complete blood count (CBC) indices, circulating tumor DNA (ctDNA), and circulating microRNAs (miRNAs) in breast cancer. Special emphasis was placed on studies utilizing AI and advanced statistical modeling for risk assessment and prediction of therapy outcomes. Findings from major cohorts and novel pilot studies were synthesized, and an illustrative AI-driven analysis of publicly accessible data was highlighted. Results: Evidence increasingly shows that both routine hematologic parameters and advanced liquid biopsy mark ers have significant prognostic and predictive value. For example, Araujo et al. (2024) demonstrated in a cohort of approximately 400,000 women that machine learning models incorporating age and neutrophil-to-lymphocyte ratio (NLR) effectively stratify breast cancer risk. Elevated NLR has consistently predicted worse survival outcomes, and dynamic changes in NLR during neoadjuvant chemotherapy reliably forecast pathological complete response. Fur thermore, ctDNA has emerged as a sensitive indicator of minimal residual disease and early recurrence, with AI-driv en analyses enhancing detection of cancer-specific genomic fragmentation patterns. In metastatic breast cancer, shallow whole-genome sequencing combined with Bayesian modeling of ctDNA predicted treatment responses with up to 75% sensitivity, surpassing traditional tumor marker assessments. Additionally, circulating miRNA signatures, especially total circulating miRNA levels, have shown significant prognostic implications for relapse. Discussion: These findings underscore the substantial yet underexplored potential of hematologic biomarkers, espe cially when integrated with machine learning approaches. Such integration may facilitate non-invasive, cost-effective screening for breast cancer risk and provide real-time monitoring of treatment efficacy. However, challenges remain, particularly in data standardization, prospective validation, and clinical integration of AI-driven methodologies. Conclusion: Hematologic biomarkers—ranging from straightforward CBC indices to sophisticated liquid biopsy an alytes—are increasingly positioned to complement traditional risk assessment and tissue-based biomarkers. AI-driv en analyses offer powerful tools to decode complex biomarker interactions, providing innovative opportunities for personalized breast cancer screening and therapy. Future multidisciplinary research and rigorous clinical trials are essential to validate and incorporate these promising approaches into standard clinical practice, ultimately improv ing patient outcomes and enabling tailored treatments
