Investigating Disease Patterns Using Space-Time Models
Author Information
Author(s): Abellan Juan Jose, Richardson Sylvia, Best Nicky
Primary Institution: Imperial College London
Hypothesis
How does including the time dimension in disease-mapping models strengthen the epidemiologic interpretation of overall risk patterns?
Conclusion
Extending hierarchical disease-mapping models to include both space and time improves interpretation and detection of localized disease risk patterns.
Supporting Evidence
- Bayesian hierarchical models can effectively capture spatial and temporal patterns in disease data.
- Using a mixture model helps distinguish stable from unstable risk patterns.
- Simulation studies confirmed the model's ability to classify areas based on risk variability.
Takeaway
This study looks at how diseases change over time and place, helping us understand if high disease rates are consistent or just temporary.
Methodology
The study used Bayesian hierarchical models to analyze congenital anomalies data over a 16-year period in England.
Potential Biases
Potential biases may arise from the aggregation of data and the assumptions made in the modeling process.
Limitations
The study may be affected by the modifiable areal unit problem and the choice of variable-size grid squares.
Participant Demographics
The study focused on congenital anomalies in England, analyzing data from live births and stillbirths.
Statistical Information
Confidence Interval
95% credibility interval
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website