Use of Artificial Intelligence Reduces the Time to Achieve Pregnancy Through Assisted Reproduction by 7%

• Additionally, AI-driven embryo selection increases pregnancy rates by 5%, reaching a cumulative increase of 7%
• Regarding gamete selection, AI potentially identifies sperm with the highest fertilization potential and embryos more likely to result in successful pregnancy. It also selects higher-quality eggs, particularly valuable for fertility preservation programs
• AI advancements presented at the congress offer substantial benefits, including personalized treatment, reduced time and patient stress, and enhanced clinical decision-making, significantly optimizing outcomes in reproductive procedures

BARCELONA, APRIL 25th, 2025

The Artificial Intelligence (AI) is increasingly revolutionizing reproductive medicine, particularly in selecting gametes (eggs and sperm) and embryos. The study ” Predicting time to live Birth with Deep Learning embryo Ranking: a novel multiple imputation approach”, led by researchers at IVI Valencia and presented at the 11th International IVIRMA Congress currently taking place in Barcelona, demonstrates how AI application can reduce the time required to achieve pregnancy by approximately 7%. This study evaluates IVI’s use of this technology over the last seven years, analyzing data from over 3,000 assisted reproductive treatments.

Dr. Marcos Meseguer, Global Director of Embryology in IVI RMA and coordinator of this study, explains: “Our study, involving a substantial sample of 70,000 embryos, allows for superior outcomes in less time with greater certainty. This significantly reduces both treatment duration and emotional stress for many patients”.

Additionally, several studies presented at the congress illustrate how AI can enhance decision-making in assisted reproductive treatments (ART) by providing objective, data-driven support. AI shows substantial potential across embryo selection, gamete selection, and ovarian stimulation.

Data presented confirm AI-driven embryo selection has improved pregnancy rates by 5%, with cumulative rates increasing to 7% (over multiple cycles), as highlighted in “Undisturbed culture: a clinical examination of this culture strategy on embryo in vitro development and clinical outcomes”, released in Fertility and Sterility. “Our research revealed that in 80% of cases where embryologists selected embryos, AI provided an alternative with a better prognosis. This data underscores that AI’s impact on assisted reproduction has only just begun”, Dr. Meseguer notes.

Beyond these promising results, IVI is also leading research into AI application for gamete selection. At the IVI congress, “AI Powered Oocyte Assessment” is presented, where more than 3,000 oocytes and 300 semen samples are analyzed using artificial intelligence to assist the embryologist in the laboratory.

“When applied to predict oocyte quality, AI greatly supports fertility preservation strategies and egg donation programs by determining the optimal number of eggs required for specific procedures. AI can aid embryologists in two significant ways: firstly, predicting the chance of obtaining a blastocyst per single oocyte; secondly, allocating the ideal number of oocytes for cryopreservation or insemination accordi  

Promising Applications in Ovarian Stimulation

Within this transformative application of AI in reproductive medicine, one of the most promising areas is ovarian stimulation, as egg number and quality significantly influences success rates in assisted reproductive treatments.

However, eggs have been the only key ART component lacking standardized evaluation methods. Thus, efforts have been directed toward developing AI-based tools for their assessment. Another study published by our group Garg, et al., 2025, also presented at the IVIRMA Congress, provides patients with accurate predictions on the expected number of eggs, stimulation duration, and the timing of egg retrieval.

Benefits include treatment personalization, as the AI tool employs deep-learning algorithms to analyze previous ovarian stimulation cycles, accurately predicting individualized outcomes. This allows physicians to tailor ovarian stimulation protocols to each patient’s unique profile, enhancing the likelihood of successful results.

Additionally, it reduces unnecessary clinic visits by precisely predicting trigger day and egg numbers, minimizing patient appointments and associated stress.

“Another significant contribution is improved clinical decision-making facilitated by precise preliminary information about the stimulation cycle. This allows more informed and timely decisions, increasing accuracy and reducing bias compared to traditional methods, which can vary by doctor or clinic. AI offers consistent, data-driven predictions, significantly enhancing overall treatment outcomes”, concludes Prof. Rienzi.