Artificial intelligence in IVF

Artificial intelligence (AI) is basically a computer program that can learn to execute tasks involving forms of intelligence normally attributed to humans. The Apple voice assistant Siri, product recommendations on Amazon, face recognition on Facebook and the growing industry of self-driving cars are all examples of AI. 

The field of IVF has embraced AI like other areas in medicine (radiology, pathology, etc.). AI can be potentially useful for embryo evaluation and selection, for the assessment of ovarian reserve parameters and sperm selection. Indeed, AI may be effective in providing an individualized patient-centered treatment by analyzing vast data sets of patient characteristics with diverse infertility treatment outcomes. In clinical embryology, AI may provide an objective method for evaluating human embryos, enabling the identification of key developmental hallmarks of embryo viability. A model predicting the probability of fetal heart pregnancy directly from raw time-lapse videos without the need for any subjective manual morphokinetic annotations or blastocyst morphology assessment has already been described (Tran et al., 2019). 

Indeed, today embryo classification is done by embryologists who manually inspect pictures for size, area, shape, proportion, and symmetry. AI utilizes computer vision algorithms to augment this process and predict the likely effectiveness of implantations. AI algorithms are trained from very large datasets drawn from a diverse patient demographic giving the AI models the power to analyze minute features that are often undetectable by even the most experienced embryologist (https://www.forbes.com/sites/ganeskesari/2022/06/30/heres-how-ai-is-helping-make-babies-by-revolutionizing-ivf/?sh=42b56d187330).

  • Advantages of AI:
    • Integrated with time-lapse imaging (TLI) systems providing continuous predictions from fertilization to the blastocyst stage. 
    • Embryological information coupled with implantation probability facilitating embryologists to make data-driven decisions for every embryo cultured in the Embryoscope.

 

  • Disadvantages of AI:
    • Despite improved results in embryo selection, studies have yet to demonstrate concrete improvements in live birth rates.
    • High cost depending on the IVF clinic.

Leave a Comment