Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Embryologist experience affects concordance with an artificial intelligence embryo ranking algorithm: benefit of artificial intelligence assistance.

F&S reports·2026
Same author

Pseudo-observation regression for sequentially truncated data.

Biometrics·2026
Same author

Artificial intelligence-driven oocyte scores are associated with early morphokinetics and embryo outcomes after intracytoplasmic sperm injection.

Reproductive biomedicine online·2026
Same author

Risk for Autism Across Generations.

Biological psychiatry·2026
Same author

Double-stranded sperm DNA fragmentation measured with neutral comet assay as a predictor of IVF outcomes: evidence from three European clinics in a multi-centred prospective study.

Human reproduction (Oxford, England)·2026
Same author

Necrotic-cell-activated macrophages drive an ERK-Bcl-xL survival pathway in osteoclasts and confer bisphosphonate resistance.

Biochemical and biophysical research communications·2026

Related Experiment Video

Updated: Jul 24, 2025

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

625

Comparing performance between clinics of an embryo evaluation algorithm based on time-lapse images and machine

Martin N Johansen1, Erik T Parner2, Mikkel F Kragh3,4

  • 1Vitrolife A/S, Jens Juuls Vej 18-20, 8260, Viby J, Denmark. mnjohansen@vitrolife.com.

Journal of Assisted Reproduction and Genetics
|July 9, 2023
PubMed
Summary

This study introduces age-standardization to compare artificial intelligence embryo viability predictions across IVF clinics. The method reduces performance variability caused by differing maternal age distributions, enabling fairer clinic comparisons.

Keywords:
Artificial intelligenceEmbryo selectionModel performanceTime-lapse

More Related Videos

A Semi-high-throughput Imaging Method and Data Visualization Toolkit to Analyze C. elegans Embryonic Development
06:49

A Semi-high-throughput Imaging Method and Data Visualization Toolkit to Analyze C. elegans Embryonic Development

Published on: October 29, 2019

6.7K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Related Experiment Videos

Last Updated: Jul 24, 2025

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

625
A Semi-high-throughput Imaging Method and Data Visualization Toolkit to Analyze C. elegans Embryonic Development
06:49

A Semi-high-throughput Imaging Method and Data Visualization Toolkit to Analyze C. elegans Embryonic Development

Published on: October 29, 2019

6.7K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Area of Science:

  • Reproductive medicine
  • Artificial intelligence in healthcare
  • Biostatistics

Background:

  • Artificial intelligence (AI) models for embryo viability prediction show promise in improving IVF outcomes.
  • Variations in maternal age distributions across different IVF clinics can significantly impact AI model performance assessments.
  • Direct comparison of AI model performance between clinics may be misleading due to demographic differences.

Purpose of the Study:

  • To evaluate the impact of varying maternal age distributions on AI model performance for embryo viability prediction.
  • To propose and validate a method for age-standardizing AI model performance metrics across IVF clinics.

Main Methods:

  • Retrospective analysis of 4805 fresh and frozen single blastocyst transfers (5-6 days incubation).
  • Assessment of AI model discriminative performance using Area Under the ROC Curve (AUC) based on fetal heartbeat outcomes.
  • Development of an age-standardization method for AUCs, weighting embryos by clinic-specific maternal age relative to a common reference population.

Main Results:

  • Significant variation in clinic-specific AUCs (0.58-0.69) was observed before standardization.
  • Age-standardization reduced between-clinic variance in AUCs by 16%.
  • Three clinics showed similar AUCs post-standardization, indicating the method mitigates demographic influence.

Conclusions:

  • The proposed age-standardization method effectively mitigates variability in AI model performance metrics between IVF clinics.
  • This approach allows for more equitable and accurate comparisons of embryo viability prediction models across diverse patient populations.
  • Standardization is crucial for reliable benchmarking of AI tools in reproductive medicine.