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 Experiment Videos

A neural network to analyze fertility data

C S Niederberger1, L I Lipshultz, D J Lamb

  • 1Scott Department of Urology, Baylor College of Medicine, Houston, Texas 77030.

Fertility and Sterility
|August 1, 1993
PubMed
Summary
This summary is machine-generated.

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

Differential modulation of transendothelial electrical resistance by TRPV4 agonists is mediated by apoptosis and/or necrosis.

Biochemistry and biophysics reports·2019
Same author

TRPV4 inhibition attenuates stretch-induced inflammatory cellular responses and lung barrier dysfunction during mechanical ventilation.

PloS one·2018
Same author

Spleen tyrosine kinase inhibition blocks airway constriction and protects from Th2-induced airway inflammation and remodeling.

Allergy·2016
Same author

Lessons learned in andrology: standing on the shoulders of giants.

Andrology·2016
Same author

Microscopic visualization of intravasal spermatozoa is positively associated with patency after bilateral microsurgical vasovasostomy.

Andrology·2015
Same author

The need to improve patient care through discriminate use of intracytoplasmic sperm injection (ICSI) and improved understanding of spermatozoa, oocyte and embryo biology.

Andrology·2015

An artificial neural network accurately predicted bovine fertility potential using semen analysis. This AI system outperformed traditional methods in predicting sperm penetration in cervical mucus and hamster egg penetration assays.

Area of Science:

  • Veterinary Medicine
  • Artificial Intelligence
  • Reproductive Biology

Background:

  • Predicting male fertility potential is crucial in bovine reproduction.
  • Traditional semen analysis methods have limitations in accurately predicting fertility outcomes.
  • The Penetrak assay and zona-free hamster egg penetration assay are established methods for assessing sperm function.

Purpose of the Study:

  • To develop and evaluate an artificial intelligence system, specifically a neural network, for predicting fertility in bulls.
  • To compare the predictive accuracy of the neural network against traditional statistical methods like linear and quadratic discriminant function analyses.
  • To assess the system's ability to predict outcomes of the Penetrak assay and zona-free hamster egg penetration assay using semen analysis data.

Main Methods:

Related Experiment Videos

  • A retrospective analysis of 139 Penetrak assays and 1,416 zona-free hamster egg penetration assays was conducted.
  • An artificial neural network was programmed and trained using semen analysis data.
  • The neural network's classification errors were compared with those of linear and quadratic discriminant function analyses.

Main Results:

  • The neural network achieved higher prediction accuracy (80% for Penetrak, 67.8% for hamster egg assay) on unseen test data compared to discriminant function analyses (69.2% and 44.7% respectively).
  • The neural network correctly predicted 92% of training set results for the Penetrak assay and 75.7% for the hamster egg assay.
  • Discriminant function analyses showed lower accuracy, predicting 64.1% and 69.2% of Penetrak test results and 64.9% and 44.7% of hamster egg test results.

Conclusions:

  • Artificial neural networks demonstrate significant potential for accurately predicting bovine fertility potential from semen analysis.
  • The developed AI system offers a more reliable method for fertility assessment compared to conventional statistical approaches.
  • This AI-driven approach may enhance the efficiency and success rates of artificial insemination programs in cattle.