Comparing Methods for Detecting Disease Clusters
Author Information
Author(s): Aamodt Geir, Samuelsen Sven O, Skrondal Anders
Primary Institution: Akershus University Hospital, University of Oslo, Norway
Hypothesis
How do different methods for detecting disease clusters perform in identifying local spatial patterns?
Conclusion
The study concludes that the methods differ in their ability to detect spatial clusters, with the BYM method being preferable for high relative risks and SaTScan for lower relative risks.
Supporting Evidence
- The GAM method had the highest sensitivity but lower specificity.
- The BYM method is preferable for local cluster detection with high relative risks.
- SaTScan is better for detecting clusters with lower relative risks.
- Clusters with irregular shapes are more difficult to detect than circular clusters.
Takeaway
This study looked at three ways to find areas where diseases are more common, and found that some methods work better than others depending on the situation.
Methodology
The study used simulations to compare the performance of SaTScan, GAM, and BYM methods in detecting disease clusters based on relative risk.
Potential Biases
The results may be influenced by the specific characteristics of the Norwegian population and municipalities used in the study.
Limitations
The study is limited to spatial clusters and may not generalize to clusters in both space and time.
Participant Demographics
The study used data from the Norwegian population statistics, which included 4,577,457 inhabitants across 434 municipalities.
Statistical Information
P-Value
p<0.05
Confidence Interval
95%
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website