Artificial Intelligence – a key to the development of embryology laboratory
Begimbaeva A.A. Rybina A.N. Nigmetova K.T. Saylau Z.K. Ermekova A.Sh. Karibayeva S.K. Lokshin V.N.
2024Kaz Med Print LLP
Reproductive Medicine (Central Asia)
2024#2024Issue 342 - 49 pp.
Relevance: Introducing artificial intelligence (AI) in assisted reproductive technologies (ART) is a relevant and exciting topic. While the potential success of AI is evident, there are still questions about its correctness that require the collective effort of our research community to address. The study aimed to underscore the immense potential of using artificial intelligence to predict blastocyst yield, ploidy, and pregnancy frequency in assisted reproductive technology programs using noninvasive diagnostics. If harnessed, this potential could revolutionize the field of ART. Materials and Methods: We conducted a cross-sectional retrospective study of 655 programs of married couples diagnosed with infertility. The patients were divided into 2 age groups: Group 1 – up to 38 years old, Group 2 – 39 years and older. The embryos were categorized into 2 groups based on the AI assessment on the 5th day of development: Group 1 with an evaluation of 0-5 points, and Group 2 – 6-10 points. According to the morphological quality, the embryos were divided into 2 groups: Group 1 – embryos with an assessment of excellent blastocyst quality ≥2BC according to Gardner, and Group 2 – blastocysts of good quality and below <2BC. Results: We revealed a statistically significant moderate positive correlation between the AI assessment of embryos on the 5th day of development and the morphological quality of blastocysts. Prediction of a euploid embryo using AI reaches 90.9%. Regardless of the womans age, embryos with a low AI score on the 5th day of development are statistically significantly less likely to result in pregnancy (p<0.001). The sensitivity of the obtained model was 79.6%, and the specificity was 47.1%. Conclusion: The obtained results demonstrate the high potential for artificial intelligence to increase the effectiveness of ART programs outcomes, including as a non-invasive preimplantation diagnosis. Further study of the possibilities of using artificial intelligence in ART clinics is necessary.
artificial intelligence , blastocyst , developmental assessment , embryos , ploidy , preimplantation diagnosis
Text of the article Перейти на текст статьи
International Clinical Center of Reproduction PERSONA,, Almaty, Kazakhstan
International Clinical Center of Reproduction PERSONA
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026