The Influence of Hatching on Blastocyst Metabolomic Analysis: Mass Spectral Analysis of Spent Blastocyst Media in Ai/ML Prediction of IVF Embryo Implantation Potential– To Hatch or Not to Hatch?

There is an ever-growing need for more cost-effective, clinically applicable methods that would ultimately increase the IVF live birth rate and reduce wastage from the transfer of embryos that had little or no probability of implanting. Aneuploidy testing and morphometrics have been applied with some limited success and new systems biology approaches are required. Understanding the secreteome and metabolomic signature of the most viable In vitrocultured blastocyst may hold the answer. Mass spectrometry of spent blastocyst media (SBM) offers multidimensional information from non-invasive samples of culture media. However, in vitro environment variables, time of sampling and IVF practice, including hatching, impact the proteomic/metabolomic spectral profiles. The aim of the study was to analyse SBM samples of hatched and unhatched embryos for the differences in the mass spectral profile and the impact this has on predictive modeling the potential for an intrauterine pregnancy. Of 3,248 SBM received and analysed prospectively only 570 samples, matched inclusion criteria of day 5 collection, transferred and implantation outcome known (also excluding subsequent spontaneous termination and multiple pregnancies). Two hundred and eighty three of 570 study samples, were hatched embryos.A number of extracted spectral features from the hatched embryo profiles were significantly higher (a total of 44 features, compared to 12 of unhatched embryo profiles) for the predictive model of implantation potential. Furthermore, unlike unhatched, hatched embryos had enrichment features, adding an additional layer of the discriminative information to the algorithms; contributing to the superior intrauterine pregnancy prediction model. Thus predictive power is higher for the model generated with hatched embryo data as it gives a better area under the receiver operating characteristic curve (ROC AUC 83% versus 72%) . In conclusion, we have demonstrated, that SBM from embryos that have been hatched gave rise to much more informative spectra. This, in turn, provides the best chance of detecting metabolic and secretory spectral patterns of functional importance to IVF success.