Cluster analysis for identifying sub-groups and selecting potential discriminatory variables in human encephalitis
2010

Identifying Sub-Groups in Human Encephalitis

Sample size: 268 publication Evidence: moderate

Author Information

Author(s): Hamid Jemila S, Christopher Meaney, Natasha S Crowcroft, Julia Granerod, Joseph Beyene

Primary Institution: Ontario Agency for Health Protection and Promotion, Toronto, Canada

Hypothesis

Can cluster analysis help identify sub-groups and risk factors in human encephalitis cases?

Conclusion

Patients with encephalitis are clustered based on symptoms and diagnostic variables rather than the causal agents of the disease.

Supporting Evidence

  • Fever, personality changes, headache, and lethargy were identified as main characteristics of encephalitis.
  • Six major clusters were revealed in the data set, indicating possible sub-groups.
  • A significant proportion of patients had unknown etiology, suggesting that host factors may be more important than pathogens.

Takeaway

The study looked at patients with encephalitis and found that they can be grouped by their symptoms instead of the germs that caused their illness.

Methodology

Hierarchical cluster analysis was performed on a multicenter data set to identify sub-groups and potential risk factors associated with encephalitis.

Limitations

The study has a small sample size and some variables may be more noise than informative.

Participant Demographics

The study included 268 patients, with a slight male predominance and a mean age of 33, primarily affecting children and young adults.

Digital Object Identifier (DOI)

10.1186/1471-2334-10-364

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication