Modeling and detection of respiratory-related outbreak signatures
2007

Modeling and Detection of Respiratory-Related Outbreak Signatures

Sample size: 500 publication Evidence: moderate

Author Information

Author(s): Craigmile Peter F, Kim Namhee, Fernandez Soledad A, Bonsu Bema K

Primary Institution: Department of Statistics, Ohio State University

Hypothesis

Can time series methods effectively model and detect respiratory-related outbreak signatures using chest radiograph data?

Conclusion

The study demonstrates that using seasonal autoregressive integrated average time series models (SARIMA) with covariates is crucial for modeling respiratory-related time series data.

Supporting Evidence

  • The study used simulation experiments based on a stochastic model for an anthrax attack.
  • It found that the balance between specificity, sensitivity, and timeliness to detect an outbreak signature differs by emergency department.
  • The models showed some homogeneity in the time series for respiratory-complaint backgrounds across the studied emergency departments.

Takeaway

The researchers used data from children's hospitals to find patterns in chest X-rays that could help detect outbreaks of respiratory illnesses like anthrax.

Methodology

The study used time series models for chest radiograph data, incorporating covariates like patient visit counts and temperature, to detect outbreak signatures.

Limitations

The study assumes stationarity of the resulting series and does not account for multiple ED visits by individuals.

Participant Demographics

Data was collected from five metropolitan children's hospitals in the Midwest USA.

Digital Object Identifier (DOI)

10.1186/1472-6947-7-28

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication