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 Video

Updated: Jan 16, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.4K

ProtoMAP: prototypical network based few-shot learning for missed abortion prediction.

Xiaoli Bo1,2, Lu You3, GuoYing Li2

  • 1Reproductive Medicine Center, Xiangya Hospital of Central South University, Changsha, China.

BMC Medical Informatics and Decision Making
|September 27, 2025
PubMed
Summary

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

Reduced IL-10 in the early postnatal period contributes to pro-inflammatory phenotype and autism-like behavior in offspring mice induced by maternal hypothyroidism during pregnancy.

Cytokine·2026
Same author

Thymalfasin combined with immune checkpoint inhibitors in the treatment of non-small cell lung cancer: A retrospective study on efficacy, safety, and immunological function.

Pakistan journal of medical sciences·2026
Same author

Diaphragm assessment by multimodal ultrasound imaging in patients with interstitial lung disease: a prospective observational study.

Journal of thoracic disease·2026
Same author

Green recyclable resin-supported sulfur ionic liquid for efficient CO<sub>2</sub> cycloaddition to cyclic carbonates.

Journal of environmental management·2026
Same author

Efficacy and safety of sintilimab in the treatment of sqNSCLC.

Pakistan journal of medical sciences·2026
Same author

A decrease in Atp8a2 expression in Purkinje cells mediated acrylamide-induced cerebellar pathology in rats.

Toxicological research·2026

This study introduces ProtoMAP, a novel few-shot learning model for predicting missed abortion risk. ProtoMAP effectively identifies high-risk cases even with limited clinical data, improving maternal health outcomes.

Area of Science:

  • Reproductive Medicine
  • Machine Learning in Healthcare
  • Computational Biology

Background:

  • Missed abortion presents significant physical and psychological risks to mothers.
  • Accurate prediction of missed abortion is crucial for timely clinical intervention.
  • Limited and imbalanced data, along with complex feature interactions, hinder traditional machine learning model performance in predicting missed abortion.

Purpose of the Study:

  • To develop a few-shot learning model, ProtoMAP, for predicting missed abortion risk.
  • To achieve high prediction performance comparable to models trained on large datasets, despite using limited samples.
  • To address the challenge of scarce and imbalanced data in missed abortion prediction.

Main Methods:

  • Proposed a prototype network named ProtoMAP, utilizing few-shot learning principles.
Keywords:
Clinical data analysisCohort analysisFew-shot learningMissed abortionMultilayer perceptronPrototype network

Related Experiment Videos

Last Updated: Jan 16, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.4K
  • Trained the ProtoMAP model on limited clinical data for missed abortion prediction.
  • Compared ProtoMAP's performance against various baseline models.

    • Main Results:

    • ProtoMAP significantly outperformed baseline models in missed abortion prediction.
    • The model demonstrated strong performance in a few-shot learning setting.
    • ProtoMAP achieved prediction accuracy rivaling or exceeding models trained on larger datasets.

    Conclusions:

    • ProtoMAP is effective for missed abortion prediction, especially in data-scarce scenarios.
    • Few-shot learning offers a viable approach for medical prediction tasks with limited data.
    • The ProtoMAP model shows practical utility for clinical applications in safeguarding maternal health.