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

FPECGNET: A deep learning framework based on federated learning and prototype learning for interpretable ECG

Jiang He1, Jie He2, Jin Xiong3

  • 1Medical College, Guizhou University, Guiyang, China.

Iscience
|May 22, 2026
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

Novel genetic associations for blood pressure identified via gene-alcohol interaction in up to 570K individuals across multiple ancestries.

PloS one·2018
Same author

[Classification, distribution and change of Uighur medicinal materials resources].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2018
Same author

[Determination of 3 components in Xinjiang Ziziphora bungeana by HPLC].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2018
Same author

Self-Reported Tobacco, Alcohol, and Illicit Drug Use and Progression of Chronic Kidney Disease.

Clinical journal of the American Society of Nephrology : CJASN·2018
Same author

Trends in Prevalence and Control of Hypertension According to the 2017 American College of Cardiology/American Heart Association (ACC/AHA) Guideline.

Journal of the American Heart Association·2018
Same author

Estimating the Association of the 2017 and 2014 Hypertension Guidelines With Cardiovascular Events and Deaths in US Adults: An Analysis of National Data.

JAMA cardiology·2018
Same journal

Topological skeleton analysis for network-based shape representation in biology and beyond.

iScience·2026
Same journal

Condition-specific neural signatures of reactivation during post-retrieval rest: An EEG study.

iScience·2026
Same journal

Multi-chaotic signal identification employing a causal cross-correlation neural network.

iScience·2026
Same journal

Repeated insertions at positions 261-280 in KPC-2 highlight a ceftazidime-avibactam resistance hotspot.

iScience·2026
Same journal

ROS inhibits microtubule dynamics and cell growth heterogeneity during Arabidopsis sepal morphogenesis.

iScience·2026
Same journal

Type 1 diabetes alters early macrophage-<i>Mycobacterium tuberculosis</i> transcriptional coordination during infection.

iScience·2026
See all related articles
This summary is machine-generated.

This study introduces a novel deep learning framework using federated learning and prototype learning to address data silos in healthcare. The interpretable AI model achieves superior performance, overcoming data scarcity and enhancing medical AI applications.

Area of Science:

  • Artificial Intelligence in Medicine
  • Machine Learning for Healthcare Data

Background:

  • Data privacy regulations create data silos, limiting AI model performance in healthcare.
  • Lack of interpretability in AI models hinders their adoption in clinical decision-making.

Purpose of the Study:

  • To develop an interpretable deep learning framework addressing hospital data silos.
  • To improve AI model performance and transparency in medical applications.

Main Methods:

  • A deep learning framework combining federated learning and prototype learning was proposed.
  • The model was trained on the PTB-XL dataset, simulating data silos by dividing it into subsets.
  • Federated learning was employed to train the model across these distributed subsets.
Keywords:
Cardiovascular medicineMachine learning

Related Experiment Videos

Main Results:

  • The federated learning framework achieved superior performance on individual data subsets.
  • The aggregated model demonstrated performance comparable to state-of-the-art methods on the complete PTB-XL dataset.
  • The proposed framework successfully simulated data silos while maintaining model interpretability.

Conclusions:

  • Federated and prototype learning offer a viable solution for AI in healthcare despite data silos.
  • The developed interpretable AI framework enhances trust and applicability in medical settings.
  • This approach paves the way for more robust and transparent AI-driven medical diagnostics.