How an algorithm could be used to improve IVF success rates
Anyone with an interest in IVF will know that embryos are examined and graded by an embryologist prior to transfer. Embryologists hope to boost the chances of a successful pregnancy by implanting the highest quality embryo possible.
This grading process takes time and skill, but embryologists might be about to receive help in the form of a Google deep learning algorithm developed by researchers at Cornell University in New York. The algorithm known as ‘STORK’ was developed using time-lapse recordings of the development of more than 10,000 embryos. Stork’s performance was compared to the work of five international embryologists and found to be in line with their majority decisions on grading.
Olivier Elemento, Director of Cornell’s Englander Institute for Precision Medicine said:
“Our algorithm will help embryologists maximise the chances that their patients will have a single healthy pregnancy. IVF procedures will remain the same, but we'll be able to improve outcomes by harnessing the power of artificial intelligence.'
More research is needed before we see STORK being widely used, but anything that improves IVF outcomes for patients would be very welcome.
npj Digital Medicine, volume 2, Article number: 21 (2019)
