#92 : An Artificial Intelligence Algorithm Outperforms Highly Variable Embryologist Grading for Predicting the Likelihood of Pregnancy Outcome from Embryo Images
Matthew VerMilyea, Jonathan Hall, Michelle Perugini, Tuc Nguyen, Don Perugini, Sonya Diakiw- General Medicine
Background and Aims: Embryologist evaluation of embryos is critical for ensuring successful pregnancy outcomes. Standard, manual evaluation is variable, subjective, and time-consuming. The aim of this study was to evaluate whether an artificial intelligence (AI) algorithm can standardize and improve embryo evaluation during IVF.
Method: 20 images of blastocyst-stage embryos on day 5 of in vitro development were selected to represent a range of morphological qualities. All embryos had been transferred and the clinical pregnancy outcome was known for each embryo based on detection of fetal heartbeat at first ultrasound scan (∼7-9 weeks gestation). 50% of embryos in the dataset resulted in pregnancy.
158 embryologists made a total of 236 attempts at providing their evaluation of the morphological quality of the 20 embryo images using the Gardner system. The embryologist-assigned grades were then used to generate their prediction of whether that embryo would lead to pregnancy or not (≥ 3BB indicated a pregnancy prediction, and <3BB indicated a non-pregnancy prediction).
The same 20 embryo images were also assessed by a previously developed viability AI algorithm for evaluating the likelihood of clinical pregnancy based on embryo images. An AI score of ≥5.0/10 indicated a pregnancy prediction, and <5.0/10 indicated a non-pregnancy prediction. The AI algorithm provided the same score for each embryo image regardless of how many times the analysis was performed.
Results: The AI algorithm correctly predicted pregnancy outcome for 14/20 embryo images (70%). Embryologists also correctly predicted 14/20 images in 14/236 attempts (6%), and in 1 attempt correctly predicted 15/20 images. In the remaining 221 attempts (94%) embryologists correctly predicted between 6-13 images, representing a range of accuracies from 30-75%.
Conclusion: This study demonstrates the inherent variability and lack of objectivity associated with an embryologist’s evaluation of embryos. It highlights the benefits of accurate AI algorithms for standardizing embryo assessment