Biology Reference
In-Depth Information
Timeliness
Data Quality
Click-stream/Keyword searching
Blogs/Chat rooms
News Sources
- Local
- National
- International
Mailing lists (ProMED-mail)
Multi-national surveillance(Eurosurveillance)
Validated ocial global alerts (WHO)
Specificity
Reliability
Figure 6.6
Quality of data scaled by timeliness and specificity/reliability.
In an effort to further develop data filtering, HealthMap is working to
improve natural language processing capabilities for additional automated
data processing, such as distinguishing discrete outbreaks from endemic
activity, the spatial resolution of location extraction, and identifying reports
indicating the absence of disease or the end of a previously identified out-
break (Freifeld et al. 2008).
Continued system evaluation is another essential part of future work
for HealthMap. The sensitivity, specificity, and timeliness of different
news source types need to be quantified and considered (see Figure 6.6).
Integrating unstructured online information sources with other health indi-
cator data needs to be considered as well to provide a broader context for
reports. Finally, in an effort to define populations at risk and predict disease
spread, the integration of additional pertinent data sets such as mortality
and morbidity estimates, laboratory data, field surveillance, environmental
predictors, population density and mobility, and pathogen seasonality and
transmissibility need to also be considered (Brownstein et al. 2008).
References
Brownstein, John S., Clark C. Freifeld, and Lawrence C. Madoff. 2009. Digital Disease
Detection—Harnessing the Web for Public Health Surveillance.
N Engl J Med
360 (21):5.
Brownstein, John S., Clark C. Freifeld, and Lawrence C. Madoff. 2009. Influenza A
H1N1 Virus, 2009—Online Detection and Monitoring.
N Engl J Med
360 (21):1.
