Improving our ability to detect disease outbreaks within a given population as early as possible is a never-ending quest – for obvious reasons.
Whether the cause is bioterrorism, such as an anthrax attack, or a novel virus, such as COVID-19, early detection enables early public health interventions and possibly the fleeting chance to limit morbidity and mortality.
Public health surveillance has traditionally focused on finding evidence of syndromes, i.e., cases with well-defined sets of symptoms that are classified via standard diagnostic codes. Alerts are issued after the number of cases crosses a specified threshold.
In this 40-minute webinar, Sam Edgemon shows how the use of more granular symptoms-level data combined with innovative statistical techniques has the potential to identify disease outbreaks faster while limiting false positives.
Using data from emergency departments, ambulance services, poison control centers and social media, Sam demonstrates:
- How unstructured textual data can be combined with a wide breadth of other symptom-level data to spot previously hidden outbreaks.
- How to identify potential “hot spots” earlier using statistical techniques not usually associated with biological surveillance.
- How these techniques could be used to make a difference during the current pandemic, as well as the next one.