Application of a methodological framework for the development and multicenter validation of reliable artificial intelligence in embryo evaluation.

Journal: Reproductive biology and endocrinology : RB&E
PMID:

Abstract

BACKGROUND: Artificial intelligence (AI) models analyzing embryo time-lapse images have been developed to predict the likelihood of pregnancy following in vitro fertilization (IVF). However, limited research exists on methods ensuring AI consistency and reliability in clinical settings during its development and validation process. We present a methodology for developing and validating an AI model across multiple datasets to demonstrate reliable performance in evaluating blastocyst-stage embryos.

Authors

  • D Gilboa
    AIVF Ltd, Tel Aviv, Israel.
  • Akhil Garg
    Faculty of Medicine, McGill University, Montréal, Québec, Canada.
  • M Shapiro
    AIVF Ltd, Tel Aviv, Israel.
  • M Meseguer
    IVIRMA Valencia, Valencia, Spain.
  • Y Amar
    AIVF Ltd, Tel Aviv, Israel.
  • N Lustgarten
    AIVF Ltd, Tel Aviv, Israel.
  • N Desai
    Department of Obstetrics and Gynecology, Division of Reproductive Endocrinology and Infertility, Women's Health Institute, Cleveland Clinic, Beachwood, OH, USA.
  • T Shavit
    In Vitro Fertilization (IVF) Unit, Assuta Ramat HaHayal, Tel-Aviv, Israel.
  • V Silva
    Ferticentro - Centro de Estudos de Fertilidade, Coimbra, Portugal.
  • A Papatheodorou
    Embryolab Fertility Clinic, Thessaloniki, Greece.
  • A Chatziparasidou
    Embryolab Fertility Clinic, Thessaloniki, Greece.
  • S Angras
    FIRST IVF Clinic, Clane, Ireland.
  • J H Lee
    a National Leading Research Laboratory (NLRL) of Molecular Modeling & Drug Design, College of Pharmacy and Graduate School of Pharmaceutical Sciences , Ewha Womans University , Seoul , Republic of Korea.
  • L Thiel
    Praxis Dres.med. Göhring, Tübingen, Germany.
  • C L Curchoe
    CCRM Fertility Orange County, Newport Beach, CA, USA.
  • Y Tauber
    AIVF Ltd, Tel Aviv, Israel.
  • D S Seidman
    AIVF Ltd, Tel Aviv, Israel.