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 simulation study of three methods for detecting disease clusters.

Geir Aamodt1, Sven O Samuelsen, Anders Skrondal

  • 1Akershus University Hospital, University of Oslo, Norway. geir.aamodt@fhi.no

International Journal of Health Geographics
|April 13, 2006
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

Corrigendum to "Environmental exposure and cancer incidence in offshore petroleum workers in Norway" [Environ. Res. 264 (2025) 121407].

Environmental research·2026
Same author

Bayesian Identification and Estimation of Growth Mixture Models.

Psychometrika·2025
Same author

Benzene exposure and risk of colorectal cancer by anatomical subsite in the Norwegian offshore petroleum workers cohort.

Environmental research·2025
Same author

Occupational exposures and kidney cancer among 25 000 male offshore petroleum industry workers: relative risks and healthy worker survivor bias.

American journal of epidemiology·2025
Same author

Association between urban green space and transmission of COVID-19 in Oslo, Norway: A Bayesian SIR modeling approach.

Spatial and spatio-temporal epidemiology·2025
Same author

[Spatial data in medicine and health sciences].

Tidsskrift for den Norske laegeforening : tidsskrift for praktisk medicin, ny raekke·2025
Same journal

EpiGIS pro: an AI-powered geospatial intelligence platform for integrated disease surveillance and predictive analytics.

International journal of health geographics·2026
Same journal

Disparities of children's obesogenic environments in Louisiana.

International journal of health geographics·2026
Same journal

Spatial non-stationarity in son preference: a district-level geographically weighted regression analysis of NFHS-5 in India.

International journal of health geographics·2026
Same journal

Modeling hospital catchment areas in pediatric oncology using an empirically parameterized extended Huff-model.

International journal of health geographics·2026
Same journal

Spatio-temporal epidemic forecasting with graph-based transformer.

International journal of health geographics·2026
Same journal

Spatial and telehealth accessibility to eating disorder treatment in the United States: evidence from registry and LLM-augmented data.

International journal of health geographics·2026
See all related articles

This study compared spatial cluster detection methods for disease mapping. Bayesian disease mapping (BYM) and spatial scan statistics (SaTScan) are generally effective, especially for higher relative risks and circular clusters.

Area of Science:

  • Spatial epidemiology
  • Disease cluster detection
  • Geographic analysis

Background:

  • Identifying environmental factors linked to disease is crucial for etiological investigations.
  • Local spatial cluster detection methods aid in pinpointing disease hotspots.
  • Three methods were evaluated: spatial scan statistic (SaTScan), generalized additive models (GAM), and Bayesian disease mapping (BYM).

Purpose of the Study:

  • To compare the performance of SaTScan, GAM, and BYM for detecting local spatial disease clusters.
  • To assess method sensitivity, specificity, and correct classification rates under varying relative risk scenarios.
  • To evaluate the impact of cluster shape on detection accuracy.

Main Methods:

  • A simulation study was conducted using seven predefined geographic clusters with varying shapes and relative risks.

Related Experiment Videos

  • Performance metrics included sensitivity, specificity, and percentage correctly classified.
  • Methods compared were SaTScan, GAM, and BYM.

    • Main Results:

    • All methods effectively detect clusters with relative risks >1.5, but struggle with lower risks.
    • Generalized additive models (GAM) offer high sensitivity but can overestimate cluster areas due to lower specificity.
    • Bayesian disease mapping (BYM) and SaTScan demonstrate robust performance, with SaTScan being preferable for lower relative risks and BYM for higher risks. Irregularly shaped clusters are harder to detect.

    Conclusions:

    • Method selection for spatial cluster detection should consider cluster size, shape, and desired balance between sensitivity and specificity.
    • BYM is recommended for high relative risk clusters, while SaTScan is suitable for lower relative risk scenarios.
    • GAM requires tuning, such as cross-validation, for optimal performance in spatial cluster detection.