Improving embryo ploidy prediction: a machine learning approach using morphokinetic meta-variables and clinical data
Reproductive BioMedicine Online · 2025
DOI: 10.1016/j.rbmo.2025.105404 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Reproductive BioMedicine Online, 2025. Verfasst von Enric Güell-Penas und 15 weiteren Autor:innen. Beteiligte Einrichtung: Consultfiv Data Science, Valls, Spain; Centre Procrear, Reus, Spain. Electronic address: contact@consultfiv.com. Hauptthemen laut MEDLINE: Aneuploidy, Blastocyst, Machine Learning, Ploidies.
Abstract (Originalsprache)
RESEARCH QUESTION: Can a machine learning model integrating time-lapse morphokinetic meta-variables with clinical data predict embryo aneuploidy accurately for improved non-invasive embryo selection? DESIGN: A retrospective multicentre cohort study using time-lapse data from 1190 blastocysts from nine Spanish fertility clinics (2017-2024), with 70% (n = 833) and 30% (n = 357) used for model training/testing and external validation, respectively. The primary dataset included well-defined outcomes (live birth or aneuploidy diagnosis via preimplantation genetic testing). The LIFE Predict v1.1 model integrated clinical data and novel morphokinetic meta-variables (range and mean absolute error) representing deviations from expected embryo development. Model performance was assessed using area under the receiver operating characteristic curve (AUC-ROC) and confusion matrix metrics. Logistic regression was used to calculate OR for risk of aneuploidy. Morphological assessments using ASEBIR grading were combined with algorithmic scoring. RESULTS: The final ensemble model achieved an AUC of 0.824 (95% CI 0.796-0.857) in cross-validation and 0.818 (95% CI 0.794-0.851) in external validation. The LIFE Predict v1.1 score showed a significant inverse relationship with risk of aneuploidy, with each one-point decrease increasing the odds of aneuploidy by 76% (OR = 1.76, 95% CI 1.52-2.05). The aneuploidy rate decreased across ascending score quartiles: 76.4% (lowest), 64.0%, 25.8% and 13.3% (highest). Combining morphological grading with the LIFE Predict v1.1 model revealed substantial risk stratification within identical morphological categories, with A-grade (Day 5) embryos showing aneuploidy rates from 11-14% (highest score quartiles) to 60-86% (lowest quartiles). CONCLUSIONS: The LIFE Predict v1.1 model predicts embryo outcomes accurately using morphokinetic meta-variables and clinical data, providing actionable risk stratification that complements conventional morphological assessment for enhanced non-invasive embryo selection. Prospective clinical validation is required to confirm its real-world utility.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Consultfiv Data Science, Valls, Spain; Centre Procrear, Reus, Spain. Electronic address: contact@consultfiv.com.
- CREA, Medicina de la Reproducción, València, Spain.
- Instituto de Reproducción CEFER, Barcelona, Spain.
- UR CEFIVA, Oviedo, Spain.
- Instituto de Reproducción CEFER, Lleida, Spain.
- IRAGA, Unidad de Reproducción Asistida La Rosaleda, Santiago de Compostela, Spain.
Zitieren
APA
Güell-Penas, E., Ferrer-Buitrago, M., Robles, E. F. I., Lliso, C. C., Rugero, F. M., Olmedo, P. N., Rodié, E. V. I., Rubira, M. J. L., Arcos, I. M., Álvarez, E. S., Soler, L. M., Riuró, E. F., Miguel, I. S. Á., Méndez, E. P., López, A. M., & Pérez, J. I. M. (2025). Improving embryo ploidy prediction: a machine learning approach using morphokinetic meta-variables and clinical data. Reproductive BioMedicine Online. https://doi.org/10.1016/j.rbmo.2025.105404
Vancouver
Güell-Penas E, Ferrer-Buitrago M, Robles EFI, Lliso CC, Rugero FM, Olmedo PN, et al. Improving embryo ploidy prediction: a machine learning approach using morphokinetic meta-variables and clinical data. Reproductive BioMedicine Online. 2025. doi:10.1016/j.rbmo.2025.105404
BibTeX
@article{GellPenas2025,
author = {Güell-Penas, Enric and Ferrer-Buitrago, Minerva and Robles, Empar Ferrer I and Lliso, Carmen Calatayud and Rugero, Fernando Marina and Olmedo, Pilar Nieto and Rodié, Ester Vilamajó I and Rubira, María José López and Arcos, Iria Martínez and Álvarez, Elsi Suárez and Soler, Laura Marquès and Riuró, Eugènia Francisco-Busquets and Miguel, Ignacio Santiago Álvarez and Méndez, Eva Palacios and López, Alba Mauri and Pérez, José Ignacio Mazzanti},
title = {Improving embryo ploidy prediction: a machine learning approach using morphokinetic meta-variables and clinical data},
journal = {Reproductive BioMedicine Online},
year = {2025},
doi = {10.1016/j.rbmo.2025.105404}
}
EUVIMED