Several research groups from around the world have been developing Artificial Intelligence (AI) and using ‘deep learning’ to develop mathematical models and algorithms to improve the selection of embryos at embryo transfer.
This type of AI—the same neural network that identifies faces, animals, and objects in pictures uploaded to things like Google’s online services—has proven to work in medical settings also. It has learned to diagnose medical conditions and identify mutations related to cancer for example and IVF clinics look to be the next recipient of the technology.
Tens of thousands of anonymised videos of developing embryos (the same as those used in EmbryoScope at CRGW) have been fed into a neural network for computers to assess using mathematical models. There’s a lot going on in an embryo that’s invisible to the human eye but might not be to a computer.
It is hoped that the use of AI in IVF will actually improve outcomes (time to baby particularly) —not just implantation rates but successful, full-term pregnancies. It may end up simply changing the order in which we select embryos for transfer and freezing.
In addition to embryo grading, it may be that in the future artificial intelligence can detect chromosome abnormalities in embryos simply by watching how they develop and spotting things the human eye cannot see. CRGW are keeping abreast of developments and will as always be at the forefront of the technology is evidence sufficiently supports improved outcomes in patients.