Artificial intelligence in the in vitro fertilization laboratory: A scoping review and SWOT-based evaluation of emerging applications

Objective: Artificial intelligence (AI) represents a potentially transformative tool in assisted reproductive technology (ART), particularly in vitro fertilization (IVF), for gamete assessment, embryo selection, non-invasive genetic testing, and laboratory automation. This scoping review synthesized recent evidence on AI applications in IVF laboratories and evaluated their translational maturity using an evidence maturity framework and a strengths, weaknesses, opportunities, and threats (SWOT) analysis. Methods: This scoping review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) Extension for Scoping Reviews guidelines. PubMed, Scopus, and Web of Science were searched for peer-reviewed studies published from January 2020 to February 2025. Eligible studies evaluated AI, machine learning, or deep learning in laboratory components of ART. Data were charted on AI methods, dataset characteristics, validation strategies, clinical endpoints, and performance metrics. Results: Ninety-four studies were included. Most applications addressed embryo grading and implantation prediction using convolutional neural networks and were evaluated through internal cross-validation. Reported areas under the receiver operating characteristic curve ranged from 0.75 to 0.92, depending on the endpoint and dataset size. AI applications in sperm analysis and oocyte assessment showed greater reproducibility than manual evaluation. Non-invasive genetic prediction models displayed promising but heterogeneous sensitivity and remained predominantly limited to internal validation. Few studies reported prospective evaluation or external validation using multicenter datasets. Conclusion: AI applications in IVF are expanding, but most remain at early stages of clinical translation. Standardized datasets, external validation, interpretable algorithms, and regulatory oversight remain necessary for safe, equitable clinical integration. AI should function as a decision-support tool that supplements, rather than replaces, embryologists' expertise.