The Use of Machine Learning for Human Sperm and Oocyte Selection and Success Rate in IVF Methods

Objective: Infertility is indeed a significant global health concern. The quality of gametes plays a pivotal role in determining the success rates of assisted reproductive technology (ART) cycles. In contemporary fertility and reproductive medicine, the utilization of machine learning (ML) has emerged as a powerful tool for processing large datasets, offering the potential to enhance existing ART practices. The objective of this review study was to assess sperm and oocyte characteristics in humans using ML techniques. This approach can contribute to a more precise evaluation of the gamete, leading to improved decision-making and potentially higher success rates in ART procedures. Using of ML abilities, researchers can obtain valuable insights into the quality of gametes, thereby optimizing fertility treatments for individuals and couples experiencing infertility issues.

Materials and Methods: We conducted a comprehensive search on PubMed, Google Scholar, and Scopus using the keywords “Machine Learning AND Quantification AND IVF.” Eligible articles were initially screened based on their titles. After the title screening, a second screening was performed based on the abstracts of the selected articles. Finally, the full articles of the remaining studies were reviewed to ensure they met our inclusion criteria. From each eligible study, we extracted the following information: author(s) of the study, publication year, and the method employed to evaluate human oocyte quality.

Conclusion: The development of a properly trained ML system will require careful attention to data quality, measurement, sample size, and ethics issues agreement.