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

Privacy-Enhanced Vertical Federated Learning for Healthcare via Directional Noise and Subset Representations.

Qingfei Wang, Menghan Dai, Cong Wu

    IEEE Journal of Biomedical and Health Informatics
    |June 25, 2026
    PubMed
    Summary

    HEAL, a privacy-enhanced vertical federated learning (VFL) framework, improves healthcare prediction accuracy by optimizing noise direction and feature representation. This approach balances strong privacy protection with high utility, outperforming existing methods.

    Related Concept Videos

    Ethical Standards II01:23

    Ethical Standards II

    Ethical standards are the backbone of nursing practice, guiding nurses as they interact with patients, families, and colleagues. These standards are crucial for providing safe, empathetic care centered on the patient's needs.
    Nurses are entrusted with upholding various ethical principles and standards. Nurses forge solid therapeutic relationships using trust, empathy, autonomy, confidentiality, and professional competence.
    Confidentiality is crucial, embodying respect for individual privacy and...
    Ethical Standards I01:25

    Ethical Standards I

    The American Nurses Association (ANA) created and implemented the first nationally accepted Code of Ethics for Nurses with Interpretive Statements. The Code of Ethics is a living document regularly updated by the ANA and establishes an ethical standard that is non-negotiable for nurses in all roles and settings.
    The Code of Ethics provisions outline the nurse's duty to the patient, the healthcare team, the profession, and society. The Code's fundamental principles include advocacy,...

    You might also read

    Related Articles

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

    Sort by
    Same author

    Selection of proper artificial intelligence techniques developed for CT scan image analysis of liver cancer using fuzzy AHP-TOPSIS.

    BMC medical imaging·2026
    Same author

    Identification and functional characterization of a novel mutation in the NEUROD1 gene in a Chinese family with maturity-onset diabetes of the young.

    Acta diabetologica·2026
    Same author

    MFDA-UNet: Medical Image Segmentation with Frequency-Decoupled Representation and Gated Cross-Scale Integration.

    Sensors (Basel, Switzerland)·2026
    Same author

    Analysis of Long-Term and Short-Term Efficacy of Different Types of Tympanosclerosis Surgery Under Total Otoendoscopy.

    The Annals of otology, rhinology, and laryngology·2026
    Same author

    MiR-26b-5p Predicts the Severity of Crohn's Disease and the Degree of Malnutrition.

    Folia biologica·2026
    Same author

    Towards precision oncology: unsupervised manifold learning for spatial molecular profiling in cancer tissues.

    BMC bioinformatics·2026

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Healthcare Informatics

    Background:

    • Vertical federated learning (VFL) enables collaborative model training across institutions without raw data sharing.
    • Challenges in VFL include significant utility loss from strong differential privacy and scarcity of labeled medical data.

    Purpose of the Study:

    • To propose HEAL, a novel privacy-enhanced VFL framework.
    • To jointly optimize feature representation learning and privacy-preserving noise direction.
    • To enhance utility and privacy in healthcare VFL applications.

    Main Methods:

    • HEAL constructs importance-aware feature subsets and employs multi-level contrastive pre-training.
    • It unifies heterogeneous feature spaces and exploits unlabeled data.

    Related Experiment Videos

  • Direction-optimized differential privacy is applied to minimize gradient distortion while ensuring $(\epsilon, \delta)$-privacy.

    • Main Results:

    • HEAL achieved accuracy improvements of 2.6-4.7% over state-of-the-art baselines on four healthcare datasets.
    • The framework reached 96.2% of centralized performance at $\epsilon =1.0$.
    • Gradient-inversion reconstruction quality was degraded by 20-35%, indicating enhanced privacy.

    Conclusions:

    • Privacy protection and representation learning can be mutually reinforcing in VFL.
    • HEAL demonstrates that privacy need not solely be a performance cost.
    • The framework offers a viable solution for privacy-preserving, high-utility healthcare analytics.