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

Medical big data: promise and challenges.

Choong Ho Lee1, Hyung-Jin Yoon1

  • 1Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul, Korea.

Kidney Research and Clinical Practice
|April 11, 2017
PubMed
Summary

Big data in healthcare offers advanced analytics for hypothesis generation, moving beyond traditional methods. Overcoming challenges in medical big data is key to improving patient outcomes and reducing healthcare waste.

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

A Web3-Based Patient-Centric Health Data Management System.

Studies in health technology and informatics·2026
Same author

Causal Inference on Air Pollutants and Atopic Dermatitis Outpatient Visits in Young Children: An Instrumental Variable Approach.

Studies in health technology and informatics·2026
Same author

Causal Effect of Air Pollution on Outpatient Visits for Chronic Rhinitis.

The Laryngoscope·2026
Same author

Risk of congenital malformation in newborns from mothers with kidney diseases in a nationwide cohort study.

Communications medicine·2026
Same author

An interactive cascaded deep learning framework with expert refinement for accurate striatal subregion segmentation.

Scientific reports·2026
Same author

Beyond Fine-Tuning: Leveraging Domain-Aware In-Context learning with large language models for clinical named entity recognition.

Journal of biomedical informatics·2026

Area of Science:

  • Utilizes advanced data analytics and data mining techniques for healthcare applications.

Background:

  • Defines big data beyond its characteristics (volume, variety, velocity, veracity) to include analytical aspects like hypothesis generation.
  • Highlights unique features of medical big data compared to other disciplines and traditional clinical epidemiology.
  • Discusses applications in healthcare, including predictive modeling, clinical decision support, surveillance, public health, and research.

Purpose of the Study:

  • To explore the concept of big data in healthcare and its analytical implications.
  • To identify the complexities and limitations inherent in medical big data analysis.
  • To discuss methods for overcoming limitations and realizing the potential of medical big data.

Main Methods:

  • Leverages data mining methods such as classification, clustering, and regression for big data analytics.
Keywords:
Big dataData miningEpidemiologyHealthcareStatistics

Related Experiment Videos

  • Introduces advanced statistical techniques like propensity score analysis and instrumental variable analysis to address causality limitations.
  • Acknowledges technical challenges including missing values, dimensionality, and bias control.

    • Main Results:

    • Big data analytics in healthcare enables hypothesis generation and focuses on temporal associations rather than strict causality.
    • Advanced methods like propensity score and instrumental variable analysis show promise in mitigating limitations of observational studies.
    • Despite progress, significant challenges remain in demonstrating practical benefits and clinical integration.

    Conclusions:

    • Medical big data holds potential for a continuous learning healthcare system, improving patient outcomes and reducing waste.
    • Addressing methodological, legal, ethical, and clinical integration issues is crucial for realizing big data's promise.
    • Further research and practical validation are needed to fully harness the benefits of big data in fields like nephrology.