P-289 Evaluation of AI-based, non-invasive and annotation free EMBRYOAID software with embryologists: time and prediction

2023

Share this post

P-289 Evaluation of AI-based, non-invasive and annotation free EMBRYOAID software with embryologists: time and prediction

P Wygocki, M Siennicki, P Pawlik, H Kompanowski, T Gilewicz, P Sankowski, J Kuśmierczyk-Kubiak, CSS Lee, AYX Lim, B Stankiewicz, K Zielińsk, J Liss, T Barut, R Milewski, W Kuczyński | Human Reproduction 38 (Supplement_1), dead093. 647

This study evaluated whether an AI model can match the performance of experienced embryologists in selecting embryos with the highest likelihood of implantation. Using a test of 150 embryo pairs, where one embryo in each pair led to pregnancy, both the AI and a group of expert embryologists were asked to choose the more promising embryo. The AI demonstrated similar accuracy to the embryologists and showed particularly strong agreement with experts when they all concurred. In cases with expert disagreement, both human and AI predictions were less reliable. A notable advantage of the AI model was its decisiveness, producing results significantly faster than human experts.

Share this post

Are you a medical professional?

This content is intended exclusively for qualified medical professionals and may include specialized information that should not be interpreted by individuals without appropriate medical training.