Related Experiment Video
Updated: Sep 13, 2025
11:25
Quantitative Analysis of Protein Expression to Study Lineage Specification in Mouse Preimplantation Embryos
Published on: February 22, 2016
11.0K
Association between embryo development and early pregnancy loss revealed by artificial-intelligence-annotated kinetic
Nina Gidel-Dissler1, Thais Roque1, Guillaume Canat1
1ImVitro, Paris, France.
Reproductive Biomedicine Online
|July 27, 2025
Summary
Artificial intelligence (AI) analysis of embryo development kinetics can predict pregnancy outcomes. Specific kinetic patterns, including cleavage and blastulation timing, differentiate embryos leading to clinical pregnancy versus early pregnancy loss.
Area of Science:
- Reproductive biology and artificial intelligence in medicine.
Background:
- Embryonic kinetics, the timing of developmental events, is crucial for successful pregnancy.
- Understanding these kinetics may help predict pregnancy outcomes and identify risks like early pregnancy loss.
Purpose of the Study:
- To investigate the association between artificial intelligence (AI)-annotated embryonic kinetics and early pregnancy loss.
- To determine if AI-driven analysis of embryo development can differentiate between embryos leading to clinical pregnancy and those resulting in early pregnancy loss.
Main Methods:
- A multicentric retrospective analysis of 37,717 embryos from 7028 egg retrievals using three time-lapse systems.
- AI was employed to analyze videos of embryo development, detecting key events like cleavage (t2-t8), start of blastulation (tSB), and blastocyst formation (tB).
- Univariate and multivariate logistic regressions were used to assess associations between embryo kinetics and transfer outcomes (early pregnancy loss, clinical pregnancy).
Main Results:
- Optimal embryonic kinetics for clinical pregnancy differed significantly from those associated with early pregnancy loss (P < 0.001).
- Embryos developing faster overall were more likely to result in early pregnancy.
- Specific patterns, such as deceleration during cleavage followed by acceleration during blastulation, were linked to higher rates of clinical pregnancy, while rapid cleavage and prolonged blastulation were associated with early pregnancy loss.
Conclusions:
- AI-powered annotation of numerous biological events in embryonic development can reveal patterns predictive of pregnancy outcomes.
- Subtle kinetic differences identified by AI can help distinguish embryos competent for clinical pregnancy from those likely to result in early pregnancy loss.
- This approach offers transparency to algorithms and pinpoints critical developmental phases associated with pregnancy loss risk.
Related Concept Videos
01:07Teratogenicity
2.8K
The ability of a drug to produce structural deformations and functional abnormalities in the developing embryo or the fetus is called teratogenicity, and the drug producing this effect is known as a teratogen. Teratogenic effects include stillbirth, miscarriage, intrauterine growth restriction, and neurocognitive delay. A teratogen may affect the embryo at different stages of development, which is important in determining the type and extent of the damage. During blastocyst formation, the early...
2.8K
01:21Nondisjunction
4.1K
Nondisjunction is the failure of homologous chromosomes or sister chromatids to separate correctly and move to the opposite poles of the cells. This produces daughter cells with abnormal chromosome numbers. Nondisjunction is common during anaphase I or anaphase II of meiosis. Mutations in synaptonemal complex proteins that attach homologous chromosomes increase the chances of nondisjunction in anaphase I of meiosis I. In contrast, mutations in topoisomerases and condensins that hold...
4.1K