Cytoplasmic movements of the early human embryo: imaging and artificial intelligence to predict blastocyst development

Coticchio, Giovanni; Fiorentino, Giulia; Nicora, Giovanna; Sciajno, Raffaella; Cavalera, Federica; Bellazzi, Riccardo; Garagna, Silvia; Borini, Andrea; Zuccotti, Maurizio

doi:10.1016/j.rbmo.2020.12.008

Cited by 24 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence (AI)-based models outdo human learning and decision-making even with limited sample sizes [15,16]. In ART, AI-based analysis combined with patient characteristics, embryo morphokinetics, or embryo microscopic image analysis has been used to predict implantation and pregnancy outcomes [17][18][19][20][21]. The combination of "omics" technology and machine learning (ML) has been suggested to be able to improve ART outcome prediction [22].…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2022

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

et al. 2022

View full text Add to dashboard Cite

show abstract

“…However, we have not yet realized the maximum potential benefit of AI. The accuracy of machine learning in predicting embryo growth [9] or implantation potential [10] remains too low for clinical use, with accuracies and AUCs in the 0.60-0.80 range [11]. Tran et al recently reached an AUC of over 90% using video data taken from over 10,000 embryos.…”

Section: Discussionmentioning

confidence: 99%

Utilization of standardized preimplantation genetic testing for aneuploidy (PGT-A) via artificial intelligence (AI) technology is correlated with improved pregnancy outcomes in single thawed euploid embryo transfer (STEET) cycles

Buldo-Licciardi

Large

McCulloh

et al. 2023

J Assist Reprod Genet

View full text Add to dashboard Cite

Purpose To investigate the role of standardized preimplantation genetic testing for aneuploidy (PGT-A) using artificial intelligence (AI) in patients undergoing single thawed euploid embryo transfer (STEET) cycles. Methods Retrospective cohort study at a single, large university-based fertility center with patients undergoing in vitro fertilization (IVF) utilizing PGT-A from February 2015 to April 2020. Controls included embryos tested using subjective NGS. The first experimental group included embryos analyzed by NGS utilizing AI and machine learning (PGTaiSM Technology Platform, AI 1.0). The second group included embryos analyzed by AI 1.0 and SNP analysis (PGTai2.0, AI 2.0). Primary outcomes included rates of euploidy, aneuploidy and simple mosaicism. Secondary outcomes included rates of implantation (IR), clinical pregnancy (CPR), biochemical pregnancy (BPR), spontaneous abortion (SABR) and ongoing pregnancy and/or live birth (OP/LBR). Results A total of 24,908 embryos were analyzed, and classification rates using AI platforms were compared to subjective NGS. Overall, those tested via AI 1.0 showed a significantly increased euploidy rate (36.6% vs. 28.9%), decreased simple mosaicism rate (11.3% vs. 14.0%) and decreased aneuploidy rate (52.1% vs. 57.0%). Overall, those tested via AI 2.0 showed a significantly increased euploidy rate (35.0% vs. 28.9%) and decreased simple mosaicism rate (10.1% vs. 14.0%). Aneuploidy rate was insignificantly decreased when comparing AI 2.0 to NGS (54.8% vs. 57.0%). A total of 1,174 euploid embryos were transferred. The OP/LBR was significantly higher in the AI 2.0 group (70.3% vs. 61.7%). The BPR was significantly lower in the AI 2.0 group (4.6% vs. 11.8%). Conclusion Standardized PGT-A via AI significantly increases euploidy classification rates and OP/LBR, and decreases BPR when compared to standard NGS.

show abstract

“…Early parameters of zygotic (cytoplasmic movement) development, analyzed by AIpowered methods, have been shown to be predictive of BL development. Compared to human evaluation and prediction using morphological parameters, AI-based methods using cytoplasmic kinetics showed on average 10% higher accuracy (Coticchio et al, 2021).…”

Section: Ai Application On Pronuclear Stage Embryosmentioning

confidence: 96%

Artificial intelligence in the embryology laboratory: a review

Dimitriadis

Zaninović

Badiola

et al. 2022

Reproductive BioMedicine Online

View full text Add to dashboard Cite

Cytoplasmic movements of the early human embryo: imaging and artificial intelligence to predict blastocyst development

Cited by 24 publications

References 29 publications

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

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

Utilization of standardized preimplantation genetic testing for aneuploidy (PGT-A) via artificial intelligence (AI) technology is correlated with improved pregnancy outcomes in single thawed euploid embryo transfer (STEET) cycles

Artificial intelligence in the embryology laboratory: a review

Contact Info

Product

Resources

About