In silico method for IVF embryo selection
2023
Weill Cornell Medicine, New York, USA
One challenge in the field of in-vitro fertilization (IVF) is the selection of the most viable embryos for transfer. Current methods have multiple disadvantages including variability, invasiveness and cost. In this retrospective study, the researchers used machine-learning and deep-learning approaches to develop STORK-A, a non-invasive and automated method of embryo evaluation that uses artificial intelligence to predict embryo ploidy status. Analysis and model development included the use of 10 378 embryos from 1385 patients. STORK-A predicted aneuploid versus euploid embryos within three classification tasks with high accuracy. As a proof of concept, STORK-A shows an ability to predict embryo ploidy in a non-invasive manner and shows future potential as a standardised supplementation to traditional methods of embryo selection and prioritisation for implantation or recommendation for further tests.
A non-invasive artificial intelligence approach for the prediction of human blastocyst ploidy: a retrospective model development and validation study
Iman Hajirasouliha
Added on: 01-05-2023
[1] https://www.sciencedirect.com/science/article/pii/S2589750022002138?via%3Dihub[2] https://www.drugtargetreview.com/news/107454/harnessing-ai-technology-for-ivf-embryo-selection/