A Comprehensive Review of Artificial Intelligence-Driven Enhancements in Non-Invasive Prenatal Testing: Advancing Genomic Precision Through Deep Learning and Computational Genomics

Non-Invasive Prenatal Testing (NIPT) has emerged as a pivotal tool in prenatal care by enabling early, risk-free detection of fetal chromosomal anomalies. However, despite its clinical significance, challenges such as limited sensitivity in low fetal fraction samples and a narrow detection spectrum persist.Current methodologies largely depend on statistical techniques and conventional sequencing interpretation, which may not fully exploit the complex and high-dimensional nature of cffDNA data. There is a lack of comprehensive analysis on how Artificial Intelligence (AI) can systematically address these limitations and enhance the accuracy and scope of NIPT.This review synthesizes existing research to evaluate the role of AI particularly machine learning and deep learning models in improving NIPT accuracy, reducing false positives, and expanding the spectrum of detectable conditions.An extensive literature review was conducted on AI applications in NIPT, including studies using Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), Random Forests, and ensemble methods. The analysis includes performance comparisons, case studies, and evaluations of emerging trends such as multi-omics integration and explainable AI.AI has demonstrated superior accuracy and predictive power over traditional models in detecting common aneuploidies like trisomy 21, 18, and 13. AI also shows potential in detecting rarer conditions, improving diagnostic clarity, and minimizing "no-call" results.This review highlights AI’s transformative potential in prenatal diagnostics. Continued interdisciplinary research and ethical oversight are essential to guide the integration of AI into clinical practice.