Applications of Artificial Intelligence and Machine Learning in Assisted Reproductive Technology: Focus on in Vitro Fertilization (Ivf) and Intracytoplasmic Sperm Injection (Icsi) Publisher



Jamshidvand H ; Mohsennezhad A ; Salehisedeh N ; Riahi A ; Sahbafar H ; Sabbaghian M
Source: Tissue and Cell Published:2027

Abstract

In vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI) are two medical treatments intended to treat infertility that are included in the category of assisted reproductive technology (ART). In view of the growing incidence of infertility and the psychological and financial costs of treatment, the combination of artificial intelligence (AI) and machine learning (ML) with assisted reproductive technologies (ART) seeks to enhance results and accessibility. The present study reviews the most current research employing AI and ML algorithms to improve ART-related procedures, including IVF and ICSI, with the objective of increasing fertilization process success rates. Numerous AI and ML techniques, including random forests, support vector machine (SVM), extreme gradient boosting (XGBoost), and convolutional neural networks (CNNs), are used in the literature to optimize treatment results and predict embryo evaluation and assessment. Significant progress has been made in AI and ML applications in ART, according to the research. AI-enhanced preimplantation genetic testing (PGT) has been shown to increase euploidy rates and pregnancy outcomes. When it comes to predicting clinical pregnancy rates and embryo viability, predictive algorithms have proven to be fairly precise. Maternal age and certain embryo features were key determinants of favorable outcomes. Additionally, the study brought to light ethical questions about genetic testing procedures, especially in light of cultural and religious beliefs. By increasing prediction accuracy and streamlining treatment regimens, the combination of AI and ML technologies is redefining ART and boosting patient outcomes. Further research should focus on resolving the ethical issues surrounding genetic testing and verifying these prediction models in larger and broader cohorts. In addition, the efficiency and accessibility of infertility therapies may be enhanced by optimizing clinical procedures and introducing real-time quality assurance in ART laboratories. © 2026