Artificial Intelligence in Infertility Management: A Narrative Review of Current Evidence

Abstract

In recent years, artificial intelligence (AI) has become a powerful tool in various aspects of our daily lives. One of the most particular areas revolutionized by AI is medicine. Reproductive medicine is no exception to this integration. A narrative review was conducted to evaluate the current applications of AI-powered tools in the management of infertility. Searches were performed on October 25^th, 2025, in PubMed, Scopus, Web of Science, Google Scholar, Embase, Cochrane Library, and IEEE Xplore using predefined keywords and Boolean operators. After duplicate removal, screening, and eligibility assessment, original English-language studies relevant to AI-assisted infertility management were included for analysis. Our search identified 18 studies published between 2013 and 2025. Embryo selection and implantation prediction in in vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI) were the most common applications (8 studies), with AI models demonstrating superior performance compared to embryologists in several studies. The STORK deep neural network also demonstrated high accuracy in blastocyst quality assessment, while machine learning models showed promise in predicting ovarian reserve and fertilization outcomes. Other applications included ovarian stimulation optimization (3 studies), male infertility assessment (2 studies), and broader reproductive outcomes including live birth and miscarriage prediction (5 studies). AI shows promising potential to support infertility management by improving embryo selection, ovarian stimulation, assessment of male infertility, and broader reproductive outcomes. To ensure safe clinical adoption, future work must prioritize multi-center prospective trials, transparency, and standardized frameworks.