Improving Detection of Irregular Disease Clusters
Author Information
Author(s): Yiannakoulias Nikolaos, Rosychuk Rhonda J, Hodgson John
Primary Institution: McMaster University
Hypothesis
Can adaptations to spatial scan methods improve the detection of irregularly shaped disease clusters?
Conclusion
The adaptations may enhance the ability to detect irregular disease clusters without compromising the detection of regular shapes.
Supporting Evidence
- The adaptations improve detection of irregular shapes without losing the ability to find regular clusters.
- Using a non-connectivity penalty helps prevent clusters from taking on unusual shapes.
- A depth limit can help distinguish between nearby clusters.
Takeaway
This study looks at ways to better find disease clusters that aren't round or neat, like those along roads or rivers.
Methodology
The study tested two adaptations to existing spatial scan methods using simulated data to evaluate their effectiveness in detecting irregular disease clusters.
Potential Biases
The need for prior decision-making on parameters may introduce bias.
Limitations
The study's findings may not generalize to real-world scenarios with more complex disease patterns and variations.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website