Presagen’s Chief Medical Science Officer Dr Sonya Diakiw explained “Because this assessment is based on images alone, it is not as accurate as PGT-A itself, which involves actual DNA sequencing. But we are finding that PGT-A results themselves can be variable, as they depend on the embryo sample being tested. PGT-A only tests 5 cells from a total of around 200, so it is not always representative of the entire embryo. Life Whisperer Genetics is a whole-embryo assessment of genetic integrity that does not require any invasive procedures, which can be used to prioritize embryos for use in IVF procedures.”
The technology was evaluated prospectively on patients in Europe in collaboration with the IVF-Life Group. Dr Jon Aizpurua from IVF-Life said “Life Whisperer Genetics can be used for patients as a pre-screen, to ensure we only genetically test embryos that are likely to be normal, saving patients time and money. For patients who are not comfortable with invasive genetic tests, or in countries like Germany where invasive genetic tests are not permitted, Life Whisperer Genetics is a viable alternative to help select embryos that are most likely to be euploid.”
Prospective studies were also performed in collaboration with Alpha IVF & Women’s Specialists in Malaysia. Chief Embryologist Adelle Yun Xin Lim said “Computer vision with AI may revolutionise IVF treatment and this new technique is another milestone of AI in IVF. The technique will help doctors and embryologists around the world to predict the chromosome status of embryos in a rapid and non-invasive manner enabling the prioritization of embryos that are likely to be euploid for transfer or for further confirmatory PGT testing, leading to a faster time to pregnancy and reducing the cost of the treatment.”
Ovation Fertility’s VP of Scientific Advancement, Dr Matthew (Tex) VerMilyea said “This new product is very exciting. In some ways it is like a ‘Rapid Antigen Test (RAT)’ for embryo assessment, providing a non-invasive, instantaneous evaluation of genetic integrity, which will have massive potential for the US market when it receives FDA approval.”
Life Whisperer Genetics is already available for IVF clinics and their patients in over 40 countries globally. It can be used in combination with Life Whisperer Viability, which assesses if an embryo is likely to lead to a pregnancy. International clinical studies have shown that Life Whisperer Viability can perform better than embryologists’ current manual embryo assessment methods. Together, Life Whisperer Viability and Life Whisperer Genetics provide a comprehensive assessment of embryo quality.
Paper Title
Development of an artificial intelligence model for predicting the likelihood of human embryo euploidy based on blastocyst images from multiple imaging systems during IVF
https://academic.oup.com/humrep/advance-article/doi/10.1093/humrep/deac131/6604228
Authors
S. M. Diakiw1, J. M. M. Hall1,2,3, M. D. VerMilyea4,5, J. Amin6, J. Aizpurua7, L. Giardini7, Y. G. Briones7, A. Y. X. Lim8, M. A. Dakka1, T. V. Nguyen1, D. Perugini1, M. Perugini1,9
Life Whisperer Diagnostics (a subsidiary of Presagen), San Francisco, CA, USA, and Adelaide, SA, Australia Australian Research Council Centre of Excellence for Nanoscale BioPhotonics, The University of Adelaide, Adelaide, SA, Australia School of Physical Sciences, Faculty of Sciences, The University of Adelaide, Adelaide, SA, Australia Ovation Fertility, Nashville, Tennessee, USA Texas Fertility Center, Austin, Texas, USA Wings IVF Women’s Hospital, Ahmedabad, Gujarat, India IVF-Spain, Alicante, Spain Alpha IVF & Women’s Specialists, Petaling Jaya, Selangor, Malaysia Adelaide Medical School, Faculty of Health Sciences, The University of Adelaide, Adelaide, SA, Australia
Paper Abstract
STUDY QUESTION
Can an artificial intelligence (AI) model predict human embryo ploidy status using static images captured by optical light microscopy?
SUMMARY ANSWER
Results demonstrated predictive accuracy for embryo euploidy, and showed a significant correlation between AI score and euploidy rate, based on assessment of images of blastocysts at Day 5 after IVF.
MAIN RESULTS AND THE ROLE OF CHANCE
Overall accuracy for prediction of euploidy on a blind test dataset was 65.3%, with a sensitivity of 74.6%. When the blind test dataset was cleansed of poor quality and mislabeled images, overall accuracy increased to 77.4%. This performance may be relevant to clinical situations where confounding factors, such as variability in PGT-A testing, have been accounted for. There was a significant positive correlation between AI score and the proportion of euploid embryos, with very high scoring embryos (9.0-10.0) twice as likely to be euploid than the lowest scoring embryos (0.0-2.4). When using the genetics AI model to rank embryos in a cohort, the probability of the top-ranked embryo being euploid was 82.4%, which was 26.4% more effective than using random ranking, and ~13-19% more effective that using the Gardner score. The probability increased to 97.0% when considering the likelihood of one of the top two ranked embryos being euploid, and the probability of both top two ranked embryos being euploid was 66.4%. Additional analyses showed that the AI model generalized well to different patient demographics and could also be used for evaluation of Day 6 embryos and for images taken using multiple time-lapse systems. Results suggested that the AI model could potentially be used to differentiate mosaic embryos based on the level of mosaicism.
WIDER IMPLICATIONS OF THE FINDINGS