One of the challenges facing public health is the early recognition of problems. With the benefit of hindsight, we look back at outbreaks such as SARS and now more recently Swine Flu (H1N1) and we can see the information trail that precedes the Eureka moment or discovery point.

In retrospect, with SARS, there was chatter on discussion boards that pointed to a problem in Asia that was puzzling health care workers. While there was no name for the problem at the time, the discussion was largely about symptoms and the associated problems. Interestingly, the response to SARS required an unprecedented collaboration between public health resources around the globe — another KM challenge.

A virtual network of epidemiologists brought together public health institutions, ministries of health, and WHO Country Offices to analyze the spread of SARS and to define appropriate public health measures. (Learning from SARS: Preparing for the Next Disease Outbreak — Workshop Summary, 2004, p. 44)

So, lessons from the SARS experience now influence how we respond to global health issues in a flat, interconnected world. Here is the online version of the book referenced above:

And here is a paper on SARS and the KM opportunity for public health — From SARS to systems: developing advanced knowledge management for public health. [Stud Health Technol Inform. 2004;100:149-56.]

Back to swine flu. Can information sources be used to predict an outbreak like swine flu?

Google’s flu trends uses a number of terms, in aggregate, to spot trends in flu enquireies on their site. They even developed a version specific to the Mexico outbreak. The spike on this chart in January and February precedes the recognition by public health authorities.

Similarly, Veratect, a small company in Washington state [@Veratrect on Twitter] claims to have spotted this flu outbreak and notified a number of its corporate clients in advance of the general public health warnings. They were even accused of not reporting this information to Mexico authorities.

The Associated Press reports …

Veratect Inc., a 2-year-old company with fewer than 50 employees, combines computer algorithms with human analysts to monitor online and off-line sources for hints of disease outbreaks and civil unrest worldwide. It tracks thousands of “events” each month — an odd case of respiratory illness, or a run on over-the-counter medicines, for example — then ranks them for severity and posts them on a subscription-only Web portal for clients who want early warnings.

The idea fueling Veratect and similar companies is that blogs, online chat rooms, Twitter feeds and news media and government Web sites are full of data that public health agencies could use to respond faster to problems like outbreaks of swine flu.

Detecting public health outbreaks and even foiling terrorism has become more and more an information problem. Data scattered on the web can be turned into information and ultimately knowledge with the right tools and lenses. Knowledge pattern recognition has become one of the great challenges for today’s organizations and for society.

Addendum (May 26, 2009): Here is another related article from Wired — This article refers to Veratect and also HealthMap.