Areli Monserrat Fuentes Trejo, Silvia Soledad Moreno Gutiérrez
This review is situated within the field of health information technologies applied to healthcare, with a focus on the development and evaluation of deep learning models as clinical decision support systems. The aim of this work is to review the available scientific evidence on deep learning models applied to the selection of human embryos for in vitro fertilization, in order to provide an overview for readers through the analysis of articles published in high-impact journals. A search was conducted in indexed databases, including Scopus, PubMed, and Web of Science, covering publications from 2021 to 2026. The search strategy employed keywords such as 'in vitro fertilization', 'embryo selection', 'deep learning', and 'artificial intelligence'. A total of 45 potentially relevant articles were identified, of which 11 met the inclusion criteria and were therefore analyzed and incorporated into the final synthesis, prioritizing studies that reported performance metrics. Heterogeneity among studies limited the comparability of results; nevertheless, intelligent models demonstrate potential for embryo evaluation and implantation prediction, with performance comparable or superior to conventional methods. The literature presents various studies; however, reliable clinical prediction still requires further development of integrated models and improved validation strategies.