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

Real time spatial cluster detection using interpoint distances among precise patient locations.

Karen L Olson1, Marco Bonetti, Marcello Pagano

  • 1Children's Hospital Informatics Program, Children's Hospital Boston, Boston, Massachusetts, USA. karen.olson@childrens.harvard.edu

BMC Medical Informatics and Decision Making
|June 23, 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

What do LLMs value? An evaluation framework for revealing subjective trade-offs in assessment of glycemic control.

Proceedings of machine learning research·2026
Same author

Trends in Suicide Mortality by Method among US Individuals aged 10-24 Years from 1999 to 2024.

medRxiv : the preprint server for health sciences·2026
Same author

What FDA Clearance Does, and Does Not, Mean for Artificial Intelligence.

Annals of internal medicine·2026
Same author

Representation learning to advance multi-institutional studies with electronic health record data from US and France.

Nature communications·2026
Same author

Artificial intelligence for interpreting diabetes data using clinician-curated benchmarks.

The lancet. Diabetes & endocrinology·2026
Same author

Identifying Undiagnosed High-Risk Suicidality Cases by Matching Patients With a Similar Comorbidity Burden: Retrospective Observational Study.

JMIR formative research·2026
Same journal

An explainable machine learning model for predicting high phosphorus risk in patients on maintenance hemodialysis: a multicenter retrospective study.

BMC medical informatics and decision making·2026
Same journal

Physicians' preferences for the use of clinical decision support systems in the context of acutely ill children presenting to ambulatory care: a focus group study.

BMC medical informatics and decision making·2026
Same journal

Machine learning prediction of postoperative pulmonary infection in patients who underwent thoracoscopic lung cancer resection: a retrospective case-control study.

BMC medical informatics and decision making·2026
Same journal

Establishing development strategies and improvement paths for decision coach competencies in shared decision-making using an integrated accessibility-performance analysis and network relation map approach.

BMC medical informatics and decision making·2026
Same journal

Inflammatory marker-driven deep learning model for postoperative gastric cancer prognosis.

BMC medical informatics and decision making·2026
Same journal

Does clinical documentation reflect how parents and clinicians share decisions about surgery?

BMC medical informatics and decision making·2026
See all related articles

Detecting spatial clustering in public health data is sensitive, with a 62% overall detection rate for disease outbreaks. This method effectively identifies geographic disease clusters, even small ones, aiding in timely public health surveillance.

Area of Science:

  • Epidemiology
  • Spatial Analysis
  • Public Health Surveillance

Background:

  • Timely access to health data enables new outbreak surveillance approaches.
  • Geographic clustering of cases facilitates outbreak detection.
  • Analyzing spatial distribution of patient addresses can reveal disease patterns.

Purpose of the Study:

  • To exemplify a method for detecting spatial clustering by measuring its performance.
  • To determine factors affecting sensitivity to spatial clustering in respiratory syndrome cases.
  • To assess the utility of interpoint distance distribution perturbations for outbreak detection.

Main Methods:

  • Defined a baseline spatial distribution of patient addresses using historical emergency department data.
  • Created semi-synthetic data by simulating outbreaks within authentic background noise.

Related Experiment Videos

  • Compared observed spatial distributions to expected distributions and evaluated alarm strategies.

    • Main Results:

    • Achieved 62% overall sensitivity in detecting spatial clustering.
    • Demonstrated a low alarm rate (<5%) for non-clustered extra visits.
    • Identified cluster characteristics (size, radius, proximity to hospital) impacting detection sensitivity.

    Conclusions:

    • Perturbations in interpoint distance distribution offer a sensitive method for spatial clustering detection.
    • The M statistic effectively detects geographically clustered cases, including small clusters.
    • Empirically demonstrated detection limits for various outbreak scenarios by varying simulation parameters.