Artificial Intelligence for Prenatal Detection of Cancer‑Associated Genetic Mutations: A Review of Machine Learning Approaches in Fetal Genomics

Cancer remains one of the leading causes of morbidity and mortality worldwide, and many cases arise from inherited mutations in genes such as *BRCA۱*, *BRCA۲*, *TP۵۳*, *APC*, and *PTEN*. Early identification of these genetic alterations is essential for effective prevention and personalized clinical management. Rapid advances in next‑generation sequencing (NGS) and non‑invasive prenatal testing (NIPT) have revolutionized genomic diagnostics, enabling comprehensive detection of fetal and hereditary variants. However, interpreting the massive amount of genomic data generated by these technologies remains a major challenge. Artificial intelligence (AI), including machine learning and deep learning, has emerged as a powerful solution for analyzing large‑scale genomic datasets. AI‑based approaches can improve variant classification, pathogenicity prediction, and clinical decision‑making. Integrating AI with prenatal genomic workflows offers the potential to identify cancer‑predisposing mutations before clinical onset, supporting early risk assessment and long‑term preventive healthcare. This review summarizes current applications of AI in genomic analysis and discusses future perspectives for integrating AI‑driven models into prenatal diagnostics and hereditary cancer risk prediction.

کلیدواژه ها:

Artificial Intelligence ، Genomic Analysis ، Hereditary Cancer ، Non-Invasive Prenatal Testing ، Next-Generation Sequencing ، Variant Interpretation ، Cancer Susceptibility ، Machine Learning