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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Using AI Disagreement to Expose Gaps in Coverage Rules.

JAMA·2026
Same author

Phenotypic prediction of missense variants via deep contrastive learning.

Nature biomedical engineering·2026
Same author

Forecasting left ventricular systolic dysfunction in heart failure with artificial intelligence.

EClinicalMedicine·2026
Same author

Scaling medical AI across clinical contexts.

Nature medicine·2026
Same author

LDLR variant classification through activity-normalized prime editing screening.

bioRxiv : the preprint server for biology·2025
Same author

Heterogenous effect of automated alerts on mortality.

Journal of the American Medical Informatics Association : JAMIA·2025

Related Experiment Video

Updated: Jul 18, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

An unsupervised classification method for inferring original case locations from low-resolution disease maps.

John S Brownstein1, Christopher A Cassa, Isaac S Kohane

  • 1Children's Hospital Informatics Program at the Harvard-MIT Division of Health Sciences and Technology, 1 Autumn St, Boston, MA, USA. john_brownstein@harvard.edu

International Journal of Health Geographics
|December 13, 2006
PubMed
Summary

Lowering the resolution of disease maps does not adequately protect patient privacy. Even low-resolution maps allow for precise re-identification of patient addresses, highlighting the need for stricter privacy guidelines in publications.

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Related Experiment Videos

Last Updated: Jul 18, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Area of Science:

  • Medical Informatics
  • Public Health
  • Geographic Information Systems (GIS)

Background:

  • Geographic Information Systems (GIS) software is widely used in academia, government, and the private sector.
  • Disease maps displaying patient addresses are frequently published in journals and shared publicly.
  • Previous analysis found over 19,000 patient addresses in 19 articles from 1994-2004.

Purpose of the Study:

  • To evaluate the risk of patient privacy breaches in the publication of low-resolution disease maps.
  • To assess the re-identification accuracy of patient addresses from published maps.

Main Methods:

  • Created a hypothetical low-resolution map of geocoded patient addresses.
  • Employed georeferencing and unsupervised classification techniques.
  • Analyzed the precision of re-identifying patient addresses from presentation and publication quality maps.

Main Results:

  • Precisely re-identified 26% of addresses from a presentation quality map and 79% from a publication quality map.
  • For publication quality maps, all addresses were re-identified within 14 meters and 11 buildings.
  • For presentation quality maps, 99.8% of addresses were within 70 meters of the predicted location.

Conclusions:

  • Reducing map resolution is insufficient for protecting patient address privacy.
  • Current privacy guidelines for medical journals need to be updated.
  • Stricter policies are required to ensure patient privacy when publishing spatial data.