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

A flexibly shaped spatial scan statistic for detecting clusters.

Toshiro Tango1, Kunihiko Takahashi

  • 1Department of Technology Assessment and Biostatistics, National Institute of Public Health, 3-6 Minami 2 chome Wako, Saitama 351-0197, Japan. tango@niph.go.jp

International Journal of Health Geographics
|May 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

Packaged intervention targeting oral antimicrobials in Japanese tertiary care outpatient setting: a quasi-experimental study.

JAC-antimicrobial resistance·2026
Same author

Association between food group intakes and metabolic acidosis in patients with non-dialysis-dependent chronic kidney disease.

BMC nephrology·2026
Same author

Registry-based estimation of cardiac event-free survival in congenital heart disease complicated by pulmonary hypertension: A nationwide registry study from Japan.

International journal of cardiology. Congenital heart disease·2026
Same author

Association of dietary diversity measured by the number of dishes with cardiovascular risk factors among Japanese adults: findings from the National Health and Nutrition Survey, 2018-19.

Nutrition journal·2026
Same author

Prediction of Paroxysmal Atrial Fibrillation With Incorporating Genomic Information Into AI-Based ECG Analysis.

JACC. Asia·2026
Same author

Comparison of the Safety and Efficacy between Endovascular Coiling and Surgical Clipping of Posterior Communicating Artery Aneurysms: A 10-year Retrospective Analysis of 851 Aneurysms.

Neurologia medico-chirurgica·2026

A new flexibly shaped spatial scan statistic accurately detects noncircular disease clusters. This method improves upon circular scan statistics, especially for irregular cluster shapes and sizes up to 30 regions.

Area of Science:

  • Epidemiology
  • Spatial Statistics
  • Biostatistics

Background:

  • The widely used Kulldorff's spatial scan statistic employs a circular window, limiting its effectiveness in detecting noncircular disease clusters.
  • Existing methods for noncircular cluster detection have shown limitations, sometimes identifying clusters much larger than the actual affected area.

Purpose of the Study:

  • To introduce a novel flexibly shaped spatial scan statistic designed for improved detection of irregular and noncircular disease clusters.
  • To evaluate the performance of the proposed statistic against Kulldorff's circular method using Monte Carlo simulations.

Main Methods:

  • Development of a flexibly shaped spatial scan statistic capable of identifying clusters within localized regions.
  • Comparison of the proposed method with the circular spatial scan statistic using various circular and noncircular cluster models.

Related Experiment Videos

  • Introduction of a bivariate power distribution for classifying cluster detection accuracy.

    • Main Results:

    • The proposed flexibly shaped spatial scan statistic demonstrates superior accuracy in detecting noncircular hot-spot clusters compared to the traditional circular method.
    • The circular spatial scan statistic accurately detects circular clusters but struggles with noncircular shapes.
    • The new statistic maintains good power while enhancing the detection of irregularly shaped clusters.

    Conclusions:

    • The proposed flexibly shaped spatial scan statistic is effective for detecting clusters of small to moderate size (up to approximately 30 regions).
    • For larger cluster sizes, the current method's computational feasibility is limited, necessitating the development of more efficient algorithms.