Combining Machine Learning with Metabolomic and Embryologic Data Improves Embryo Implantation Prediction

Abstract

This study investigated whether combining metabolomic and embryologic data with machine learning (ML) models improve the prediction of embryo implantation potential. In this prospective cohort study, infertile couples (n=56) undergoing day-5 single blastocyst transfer between February 2019 and August 2021 were included. After day-5 single blastocyst transfer, spent culture medium (SCM) was subjected to metabolite analysis using nuclear magnetic resonance (NMR) spectroscopy. Derived metabolite levels and embryologic parameters between successfully implanted and failed groups were incorporated into ML models to explore their predictive potential regarding embryo implantation. The SCM of blastocysts that resulted in successful embryo implantation had significantly lower pyruvate (p<0.05) and threonine (p<0.05) levels compared to medium control but not compared to SCM related to embryos that failed to implant. Notably, the prediction accuracy increased when classical ML algorithms were combined with metabolomic and embryologic data. Specifically, the custom artificial neural network (ANN) model with regularized parameters for metabolomic data provided 100% accuracy, indicating the efficiency in predicting implantation potential. Hence, combining ML models (specifically, custom ANN) with metabolomic and embryologic data improves the prediction of embryo implantation potential. The approach could potentially be used to derive clinical benefits for patients in real-time.

Associations of the Single Bovine Embryo Growth Media Metabolome with Successful Pregnancy

“…Thr levels were significantly lower in media from successfully implanted embryos relative to empty control media; however, we did not observe significant differences between the successful and failed implantation groups. This finding is consistent with other recent works [8].…”

“…There are currently three main trending research areas in the embryo industry: timelapse microscopy empowered by AI-based computational modelling [6]; the analysis of extracellular vesicles (EVs) secreted by blastocysts [7]; and, lastly, the correlation of metabolomic/proteomic markers in spent culture medium to embryo viability [8][9][10][11].…”

Understanding conceptus–maternal interactions: what tools do we need to develop?

“…In silico approaches can also be combined with in vitro and in vivo studies to gain detailed mechanistic and functional insights. In silico studies are already helping researchers understand various cell states at different points throughout the reproductive cycle, with the multi-omic analysis of different stages of the cycle/ developmental competency of embryos as well as validation of new in vitro model systems (recently reviewed in three review papers from the International Ruminant Reproduction conference; Huang et al 2021;Yi git et al 2022;Cheredath et al 2023). In recent years, the quality, quantity, and taxonomic breadth of available gene sequences and full genomes has increased dramatically.…”

Data-Driven Medicine in the Diagnosis and Treatment of Infertility

“…Figure 2 presents examples of the different types of data that are starting to be incorporated into an overall precision medicine picture in infertility. Several examples already exist in different areas of the reproductive sector, such as oocyte retrieval and selection [ 32 ], embryo culture and selection [ 33 , 34 ], embryo implantation prediction [ 35 ], male sperm selection [ 36 , 37 ], preeclampsia [ 38 ], and preterm birth [ 39 ].…”