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

Protecting medical data for decision-making analyses.

Bostjan Brumen1, Tatjana Welzer, Marjan Druzovec

  • 1Faculty of Electrical Engineering and Computer Science, University of Maribor, Smetanova 17, Si-2000 Maribor, Slovenia. bostjan.brumen@uni-mb.si

Journal of Medical Systems
|April 21, 2005
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

Overview of Machine Learning Process Modelling.

Entropy (Basel, Switzerland)·2021
Same author

A Model of Perception of Privacy, Trust, and Self-Disclosure on Online Social Networks.

Entropy (Basel, Switzerland)·2020
Same author

An Integrated Approach to Goal Selection in MobileRobot Exploration.

Sensors (Basel, Switzerland)·2019
Same author

Knowledge Formalization to Support Decision-Making in Heart Failure Treatment.

Studies in health technology and informatics·2018
Same author

Formalization and acquisition of temporal knowledge for decision support in medical processes.

Computer methods and programs in biomedicine·2018
Same author

Outsourcing medical data analyses: can technology overcome legal, privacy, and confidentiality issues?

Journal of medical Internet research·2013
Same journal

Exploring the Potential of Ambient AI for Inpatient Documentation: A Qualitative Study with Junior Doctors.

Journal of medical systems·2026
Same journal

Automatic Sleep Staging Using Cardiorespiratory Signals: A Systematic Review of Methodologies and Performance.

Journal of medical systems·2026
Same journal

Security Analysis of a Federated Learning Framework for Medical Image-to-Image Translation.

Journal of medical systems·2026
Same journal

Correction to: Designing Operating Rooms as an Integrated Socio-Technical Ecosystem: Practical Lessons from a High-Volume Tertiary Center.

Journal of medical systems·2026
Same journal

AI-enabled clinical decision support in breast cancer care: a blinded multicenter benchmarking study comparing medically specialized with a general-purpose system.

Journal of medical systems·2026
Same journal

Starmate: A Lightweight AI Assistant for Autism Caregivers Developed and Evaluated Through a User-Centered Mixed-Methods Framework.

Journal of medical systems·2026
See all related articles

This study introduces a novel data protection method for medical data analysis. It enables secure data exploration by preserving data distributions while altering values, ensuring privacy without compromising model accuracy.

Area of Science:

  • Medical Informatics
  • Data Security
  • Statistical Modeling

Background:

  • Medical environments possess vast amounts of underutilized data containing valuable insights.
  • Analyzing medical data is often hindered by privacy concerns and security requirements, especially for external analysts.
  • Existing data protection methods may impede necessary data analysis for knowledge discovery.

Purpose of the Study:

  • To propose a data protection procedure applicable before model building.
  • To enable secure analysis of sensitive medical data while preserving privacy.
  • To ensure that data analysis models built on protected data are equivalent to those built on original data.

Main Methods:

  • Developed a data protection procedure applied prior to model building.

Related Experiment Videos

  • Focused on preserving the statistical distributions of original data values.
  • Ensured transformed data values allow for equivalent model construction.

    • Main Results:

    • The proposed procedure enhances data security and privacy in medical environments.
    • Data distributions are maintained, allowing for meaningful analysis.
    • Models built using the protected data yield equivalent results to models built with original data.

    Conclusions:

    • The procedure effectively balances data protection and analytical utility in medical settings.
    • It facilitates the exploration of valuable, life-saving knowledge hidden in medical data.
    • This approach supports secure collaboration between data owners and external analysts.